mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-13 23:11:40 +00:00
Merge remote-tracking branch 'origin/main' into fix_anthropic_tool_streaming_index
This commit is contained in:
Paul Lang
commit
b0d13f42ed
108 changed files with 3004 additions and 1550 deletions
|
|
@ -605,6 +605,12 @@ class LangFuseLogger:
|
|||
if "cache_key" in litellm.langfuse_default_tags:
|
||||
_hidden_params = metadata.get("hidden_params", {}) or {}
|
||||
_cache_key = _hidden_params.get("cache_key", None)
|
||||
if _cache_key is None:
|
||||
# fallback to using "preset_cache_key"
|
||||
_preset_cache_key = kwargs.get("litellm_params", {}).get(
|
||||
"preset_cache_key", None
|
||||
)
|
||||
_cache_key = _preset_cache_key
|
||||
tags.append(f"cache_key:{_cache_key}")
|
||||
return tags
|
||||
|
||||
|
|
|
|||
|
|
@ -7,9 +7,11 @@ import subprocess
|
|||
import sys
|
||||
import traceback
|
||||
import uuid
|
||||
from typing import Optional
|
||||
|
||||
import litellm
|
||||
from litellm._logging import print_verbose, verbose_logger
|
||||
from litellm.types.utils import StandardLoggingPayload
|
||||
|
||||
|
||||
class S3Logger:
|
||||
|
|
@ -123,29 +125,13 @@ class S3Logger:
|
|||
else:
|
||||
clean_metadata[key] = value
|
||||
|
||||
# Build the initial payload
|
||||
payload = {
|
||||
"id": id,
|
||||
"call_type": call_type,
|
||||
"cache_hit": cache_hit,
|
||||
"startTime": start_time,
|
||||
"endTime": end_time,
|
||||
"model": kwargs.get("model", ""),
|
||||
"user": kwargs.get("user", ""),
|
||||
"modelParameters": optional_params,
|
||||
"messages": messages,
|
||||
"response": response_obj,
|
||||
"usage": usage,
|
||||
"metadata": clean_metadata,
|
||||
}
|
||||
|
||||
# Ensure everything in the payload is converted to str
|
||||
for key, value in payload.items():
|
||||
try:
|
||||
payload[key] = str(value)
|
||||
except:
|
||||
# non blocking if it can't cast to a str
|
||||
pass
|
||||
payload: Optional[StandardLoggingPayload] = kwargs.get(
|
||||
"standard_logging_object", None
|
||||
)
|
||||
|
||||
if payload is None:
|
||||
return
|
||||
|
||||
s3_file_name = litellm.utils.get_logging_id(start_time, payload) or ""
|
||||
s3_object_key = (
|
||||
|
|
|
|||
|
|
@ -5,11 +5,13 @@ import copy
|
|||
import datetime
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
import traceback
|
||||
import uuid
|
||||
from datetime import datetime as dt_object
|
||||
from typing import Any, Callable, Dict, List, Literal, Optional, Union
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
|
@ -33,6 +35,9 @@ from litellm.types.utils import (
|
|||
EmbeddingResponse,
|
||||
ImageResponse,
|
||||
ModelResponse,
|
||||
StandardLoggingHiddenParams,
|
||||
StandardLoggingMetadata,
|
||||
StandardLoggingPayload,
|
||||
TextCompletionResponse,
|
||||
TranscriptionResponse,
|
||||
)
|
||||
|
|
@ -617,6 +622,16 @@ class Logging:
|
|||
total_time=float_diff,
|
||||
)
|
||||
|
||||
## STANDARDIZED LOGGING PAYLOAD
|
||||
|
||||
self.model_call_details["standard_logging_object"] = (
|
||||
get_standard_logging_object_payload(
|
||||
kwargs=self.model_call_details,
|
||||
init_response_obj=result,
|
||||
start_time=start_time,
|
||||
end_time=end_time,
|
||||
)
|
||||
)
|
||||
return start_time, end_time, result
|
||||
except Exception as e:
|
||||
raise Exception(f"[Non-Blocking] LiteLLM.Success_Call Error: {str(e)}")
|
||||
|
|
@ -2166,3 +2181,156 @@ def use_custom_pricing_for_model(litellm_params: Optional[dict]) -> bool:
|
|||
if k in SPECIAL_MODEL_INFO_PARAMS:
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def is_valid_sha256_hash(value: str) -> bool:
|
||||
# Check if the value is a valid SHA-256 hash (64 hexadecimal characters)
|
||||
return bool(re.fullmatch(r"[a-fA-F0-9]{64}", value))
|
||||
|
||||
|
||||
def get_standard_logging_object_payload(
|
||||
kwargs: Optional[dict],
|
||||
init_response_obj: Any,
|
||||
start_time: dt_object,
|
||||
end_time: dt_object,
|
||||
) -> Optional[StandardLoggingPayload]:
|
||||
try:
|
||||
if kwargs is None:
|
||||
kwargs = {}
|
||||
|
||||
hidden_params: Optional[dict] = None
|
||||
if init_response_obj is None:
|
||||
response_obj = {}
|
||||
elif isinstance(init_response_obj, BaseModel):
|
||||
response_obj = init_response_obj.model_dump()
|
||||
hidden_params = getattr(init_response_obj, "_hidden_params", None)
|
||||
else:
|
||||
response_obj = {}
|
||||
# standardize this function to be used across, s3, dynamoDB, langfuse logging
|
||||
litellm_params = kwargs.get("litellm_params", {})
|
||||
proxy_server_request = litellm_params.get("proxy_server_request") or {}
|
||||
end_user_id = proxy_server_request.get("body", {}).get("user", None)
|
||||
metadata = (
|
||||
litellm_params.get("metadata", {}) or {}
|
||||
) # if litellm_params['metadata'] == None
|
||||
completion_start_time = kwargs.get("completion_start_time", end_time)
|
||||
call_type = kwargs.get("call_type")
|
||||
cache_hit = kwargs.get("cache_hit", False)
|
||||
usage = response_obj.get("usage", None) or {}
|
||||
if type(usage) == litellm.Usage:
|
||||
usage = dict(usage)
|
||||
id = response_obj.get("id", kwargs.get("litellm_call_id"))
|
||||
|
||||
_model_id = metadata.get("model_info", {}).get("id", "")
|
||||
_model_group = metadata.get("model_group", "")
|
||||
|
||||
request_tags = (
|
||||
metadata.get("tags", [])
|
||||
if isinstance(metadata.get("tags", []), list)
|
||||
else []
|
||||
)
|
||||
|
||||
# cleanup timestamps
|
||||
if isinstance(start_time, datetime.datetime):
|
||||
start_time_float = start_time.timestamp()
|
||||
elif isinstance(start_time, float):
|
||||
start_time_float = start_time
|
||||
if isinstance(end_time, datetime.datetime):
|
||||
end_time_float = end_time.timestamp()
|
||||
elif isinstance(end_time, float):
|
||||
end_time_float = end_time
|
||||
if isinstance(completion_start_time, datetime.datetime):
|
||||
completion_start_time_float = completion_start_time.timestamp()
|
||||
elif isinstance(completion_start_time, float):
|
||||
completion_start_time_float = completion_start_time
|
||||
# clean up litellm hidden params
|
||||
clean_hidden_params = StandardLoggingHiddenParams(
|
||||
model_id=None,
|
||||
cache_key=None,
|
||||
api_base=None,
|
||||
response_cost=None,
|
||||
additional_headers=None,
|
||||
)
|
||||
if hidden_params is not None:
|
||||
clean_hidden_params = StandardLoggingHiddenParams(
|
||||
**{ # type: ignore
|
||||
key: hidden_params[key]
|
||||
for key in StandardLoggingHiddenParams.__annotations__.keys()
|
||||
if key in hidden_params
|
||||
}
|
||||
)
|
||||
# clean up litellm metadata
|
||||
clean_metadata = StandardLoggingMetadata(
|
||||
user_api_key_hash=None,
|
||||
user_api_key_alias=None,
|
||||
user_api_key_team_id=None,
|
||||
user_api_key_user_id=None,
|
||||
user_api_key_team_alias=None,
|
||||
spend_logs_metadata=None,
|
||||
requester_ip_address=None,
|
||||
)
|
||||
if isinstance(metadata, dict):
|
||||
# Filter the metadata dictionary to include only the specified keys
|
||||
clean_metadata = StandardLoggingMetadata(
|
||||
**{ # type: ignore
|
||||
key: metadata[key]
|
||||
for key in StandardLoggingMetadata.__annotations__.keys()
|
||||
if key in metadata
|
||||
}
|
||||
)
|
||||
|
||||
if metadata.get("user_api_key") is not None:
|
||||
if is_valid_sha256_hash(str(metadata.get("user_api_key"))):
|
||||
clean_metadata["user_api_key_hash"] = metadata.get(
|
||||
"user_api_key"
|
||||
) # this is the hash
|
||||
|
||||
if litellm.cache is not None:
|
||||
cache_key = litellm.cache.get_cache_key(**kwargs)
|
||||
else:
|
||||
cache_key = None
|
||||
if cache_hit is True:
|
||||
import time
|
||||
|
||||
id = f"{id}_cache_hit{time.time()}" # do not duplicate the request id
|
||||
|
||||
payload: StandardLoggingPayload = StandardLoggingPayload(
|
||||
id=str(id),
|
||||
call_type=call_type or "",
|
||||
cache_hit=cache_hit,
|
||||
startTime=start_time_float,
|
||||
endTime=end_time_float,
|
||||
completionStartTime=completion_start_time_float,
|
||||
model=kwargs.get("model", "") or "",
|
||||
metadata=clean_metadata,
|
||||
cache_key=cache_key,
|
||||
response_cost=kwargs.get("response_cost", 0),
|
||||
total_tokens=usage.get("total_tokens", 0),
|
||||
prompt_tokens=usage.get("prompt_tokens", 0),
|
||||
completion_tokens=usage.get("completion_tokens", 0),
|
||||
request_tags=request_tags,
|
||||
end_user=end_user_id or "",
|
||||
api_base=litellm_params.get("api_base", ""),
|
||||
model_group=_model_group,
|
||||
model_id=_model_id,
|
||||
requester_ip_address=clean_metadata.get("requester_ip_address", None),
|
||||
messages=kwargs.get("messages"),
|
||||
response=(
|
||||
response_obj if len(response_obj.keys()) > 0 else init_response_obj
|
||||
),
|
||||
model_parameters=kwargs.get("optional_params", None),
|
||||
hidden_params=clean_hidden_params,
|
||||
)
|
||||
|
||||
verbose_logger.debug(
|
||||
"Standard Logging: created payload - payload: %s\n\n", payload
|
||||
)
|
||||
|
||||
return payload
|
||||
except Exception as e:
|
||||
verbose_logger.warning(
|
||||
"Error creating standard logging object - {}\n{}".format(
|
||||
str(e), traceback.format_exc()
|
||||
)
|
||||
)
|
||||
return None
|
||||
|
|
|
|||
218
litellm/llms/base_aws_llm.py
Normal file
218
litellm/llms/base_aws_llm.py
Normal file
|
|
@ -0,0 +1,218 @@
|
|||
import json
|
||||
from typing import List, Optional
|
||||
|
||||
import httpx
|
||||
|
||||
from litellm._logging import verbose_logger
|
||||
from litellm.caching import DualCache, InMemoryCache
|
||||
from litellm.utils import get_secret
|
||||
|
||||
from .base import BaseLLM
|
||||
|
||||
|
||||
class AwsAuthError(Exception):
|
||||
def __init__(self, status_code, message):
|
||||
self.status_code = status_code
|
||||
self.message = message
|
||||
self.request = httpx.Request(
|
||||
method="POST", url="https://us-west-2.console.aws.amazon.com/bedrock"
|
||||
)
|
||||
self.response = httpx.Response(status_code=status_code, request=self.request)
|
||||
super().__init__(
|
||||
self.message
|
||||
) # Call the base class constructor with the parameters it needs
|
||||
|
||||
|
||||
class BaseAWSLLM(BaseLLM):
|
||||
def __init__(self) -> None:
|
||||
self.iam_cache = DualCache()
|
||||
super().__init__()
|
||||
|
||||
def get_credentials(
|
||||
self,
|
||||
aws_access_key_id: Optional[str] = None,
|
||||
aws_secret_access_key: Optional[str] = None,
|
||||
aws_session_token: Optional[str] = None,
|
||||
aws_region_name: Optional[str] = None,
|
||||
aws_session_name: Optional[str] = None,
|
||||
aws_profile_name: Optional[str] = None,
|
||||
aws_role_name: Optional[str] = None,
|
||||
aws_web_identity_token: Optional[str] = None,
|
||||
aws_sts_endpoint: Optional[str] = None,
|
||||
):
|
||||
"""
|
||||
Return a boto3.Credentials object
|
||||
"""
|
||||
import boto3
|
||||
|
||||
## CHECK IS 'os.environ/' passed in
|
||||
params_to_check: List[Optional[str]] = [
|
||||
aws_access_key_id,
|
||||
aws_secret_access_key,
|
||||
aws_session_token,
|
||||
aws_region_name,
|
||||
aws_session_name,
|
||||
aws_profile_name,
|
||||
aws_role_name,
|
||||
aws_web_identity_token,
|
||||
aws_sts_endpoint,
|
||||
]
|
||||
|
||||
# Iterate over parameters and update if needed
|
||||
for i, param in enumerate(params_to_check):
|
||||
if param and param.startswith("os.environ/"):
|
||||
_v = get_secret(param)
|
||||
if _v is not None and isinstance(_v, str):
|
||||
params_to_check[i] = _v
|
||||
# Assign updated values back to parameters
|
||||
(
|
||||
aws_access_key_id,
|
||||
aws_secret_access_key,
|
||||
aws_session_token,
|
||||
aws_region_name,
|
||||
aws_session_name,
|
||||
aws_profile_name,
|
||||
aws_role_name,
|
||||
aws_web_identity_token,
|
||||
aws_sts_endpoint,
|
||||
) = params_to_check
|
||||
|
||||
verbose_logger.debug(
|
||||
"in get credentials\n"
|
||||
"aws_access_key_id=%s\n"
|
||||
"aws_secret_access_key=%s\n"
|
||||
"aws_session_token=%s\n"
|
||||
"aws_region_name=%s\n"
|
||||
"aws_session_name=%s\n"
|
||||
"aws_profile_name=%s\n"
|
||||
"aws_role_name=%s\n"
|
||||
"aws_web_identity_token=%s\n"
|
||||
"aws_sts_endpoint=%s",
|
||||
aws_access_key_id,
|
||||
aws_secret_access_key,
|
||||
aws_session_token,
|
||||
aws_region_name,
|
||||
aws_session_name,
|
||||
aws_profile_name,
|
||||
aws_role_name,
|
||||
aws_web_identity_token,
|
||||
aws_sts_endpoint,
|
||||
)
|
||||
|
||||
### CHECK STS ###
|
||||
if (
|
||||
aws_web_identity_token is not None
|
||||
and aws_role_name is not None
|
||||
and aws_session_name is not None
|
||||
):
|
||||
verbose_logger.debug(
|
||||
f"IN Web Identity Token: {aws_web_identity_token} | Role Name: {aws_role_name} | Session Name: {aws_session_name}"
|
||||
)
|
||||
|
||||
if aws_sts_endpoint is None:
|
||||
sts_endpoint = f"https://sts.{aws_region_name}.amazonaws.com"
|
||||
else:
|
||||
sts_endpoint = aws_sts_endpoint
|
||||
|
||||
iam_creds_cache_key = json.dumps(
|
||||
{
|
||||
"aws_web_identity_token": aws_web_identity_token,
|
||||
"aws_role_name": aws_role_name,
|
||||
"aws_session_name": aws_session_name,
|
||||
"aws_region_name": aws_region_name,
|
||||
"aws_sts_endpoint": sts_endpoint,
|
||||
}
|
||||
)
|
||||
|
||||
iam_creds_dict = self.iam_cache.get_cache(iam_creds_cache_key)
|
||||
if iam_creds_dict is None:
|
||||
oidc_token = get_secret(aws_web_identity_token)
|
||||
|
||||
if oidc_token is None:
|
||||
raise AwsAuthError(
|
||||
message="OIDC token could not be retrieved from secret manager.",
|
||||
status_code=401,
|
||||
)
|
||||
|
||||
sts_client = boto3.client(
|
||||
"sts",
|
||||
region_name=aws_region_name,
|
||||
endpoint_url=sts_endpoint,
|
||||
)
|
||||
|
||||
# https://docs.aws.amazon.com/STS/latest/APIReference/API_AssumeRoleWithWebIdentity.html
|
||||
# https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sts/client/assume_role_with_web_identity.html
|
||||
sts_response = sts_client.assume_role_with_web_identity(
|
||||
RoleArn=aws_role_name,
|
||||
RoleSessionName=aws_session_name,
|
||||
WebIdentityToken=oidc_token,
|
||||
DurationSeconds=3600,
|
||||
)
|
||||
|
||||
iam_creds_dict = {
|
||||
"aws_access_key_id": sts_response["Credentials"]["AccessKeyId"],
|
||||
"aws_secret_access_key": sts_response["Credentials"][
|
||||
"SecretAccessKey"
|
||||
],
|
||||
"aws_session_token": sts_response["Credentials"]["SessionToken"],
|
||||
"region_name": aws_region_name,
|
||||
}
|
||||
|
||||
self.iam_cache.set_cache(
|
||||
key=iam_creds_cache_key,
|
||||
value=json.dumps(iam_creds_dict),
|
||||
ttl=3600 - 60,
|
||||
)
|
||||
|
||||
session = boto3.Session(**iam_creds_dict)
|
||||
|
||||
iam_creds = session.get_credentials()
|
||||
|
||||
return iam_creds
|
||||
elif aws_role_name is not None and aws_session_name is not None:
|
||||
sts_client = boto3.client(
|
||||
"sts",
|
||||
aws_access_key_id=aws_access_key_id, # [OPTIONAL]
|
||||
aws_secret_access_key=aws_secret_access_key, # [OPTIONAL]
|
||||
)
|
||||
|
||||
sts_response = sts_client.assume_role(
|
||||
RoleArn=aws_role_name, RoleSessionName=aws_session_name
|
||||
)
|
||||
|
||||
# Extract the credentials from the response and convert to Session Credentials
|
||||
sts_credentials = sts_response["Credentials"]
|
||||
from botocore.credentials import Credentials
|
||||
|
||||
credentials = Credentials(
|
||||
access_key=sts_credentials["AccessKeyId"],
|
||||
secret_key=sts_credentials["SecretAccessKey"],
|
||||
token=sts_credentials["SessionToken"],
|
||||
)
|
||||
return credentials
|
||||
elif aws_profile_name is not None: ### CHECK SESSION ###
|
||||
# uses auth values from AWS profile usually stored in ~/.aws/credentials
|
||||
client = boto3.Session(profile_name=aws_profile_name)
|
||||
|
||||
return client.get_credentials()
|
||||
elif (
|
||||
aws_access_key_id is not None
|
||||
and aws_secret_access_key is not None
|
||||
and aws_session_token is not None
|
||||
): ### CHECK FOR AWS SESSION TOKEN ###
|
||||
from botocore.credentials import Credentials
|
||||
|
||||
credentials = Credentials(
|
||||
access_key=aws_access_key_id,
|
||||
secret_key=aws_secret_access_key,
|
||||
token=aws_session_token,
|
||||
)
|
||||
return credentials
|
||||
else:
|
||||
session = boto3.Session(
|
||||
aws_access_key_id=aws_access_key_id,
|
||||
aws_secret_access_key=aws_secret_access_key,
|
||||
region_name=aws_region_name,
|
||||
)
|
||||
|
||||
return session.get_credentials()
|
||||
|
|
@ -57,6 +57,7 @@ from litellm.utils import (
|
|||
)
|
||||
|
||||
from .base import BaseLLM
|
||||
from .base_aws_llm import BaseAWSLLM
|
||||
from .bedrock import BedrockError, ModelResponseIterator, convert_messages_to_prompt
|
||||
from .prompt_templates.factory import (
|
||||
_bedrock_converse_messages_pt,
|
||||
|
|
@ -87,7 +88,6 @@ BEDROCK_CONVERSE_MODELS = [
|
|||
]
|
||||
|
||||
|
||||
iam_cache = DualCache()
|
||||
_response_stream_shape_cache = None
|
||||
bedrock_tool_name_mappings: InMemoryCache = InMemoryCache(
|
||||
max_size_in_memory=50, default_ttl=600
|
||||
|
|
@ -312,7 +312,7 @@ def make_sync_call(
|
|||
return completion_stream
|
||||
|
||||
|
||||
class BedrockLLM(BaseLLM):
|
||||
class BedrockLLM(BaseAWSLLM):
|
||||
"""
|
||||
Example call
|
||||
|
||||
|
|
@ -380,183 +380,6 @@ class BedrockLLM(BaseLLM):
|
|||
prompt += f"{message['content']}"
|
||||
return prompt, chat_history # type: ignore
|
||||
|
||||
def get_credentials(
|
||||
self,
|
||||
aws_access_key_id: Optional[str] = None,
|
||||
aws_secret_access_key: Optional[str] = None,
|
||||
aws_session_token: Optional[str] = None,
|
||||
aws_region_name: Optional[str] = None,
|
||||
aws_session_name: Optional[str] = None,
|
||||
aws_profile_name: Optional[str] = None,
|
||||
aws_role_name: Optional[str] = None,
|
||||
aws_web_identity_token: Optional[str] = None,
|
||||
aws_sts_endpoint: Optional[str] = None,
|
||||
):
|
||||
"""
|
||||
Return a boto3.Credentials object
|
||||
"""
|
||||
import boto3
|
||||
|
||||
print_verbose(
|
||||
f"Boto3 get_credentials called variables passed to function {locals()}"
|
||||
)
|
||||
|
||||
## CHECK IS 'os.environ/' passed in
|
||||
params_to_check: List[Optional[str]] = [
|
||||
aws_access_key_id,
|
||||
aws_secret_access_key,
|
||||
aws_session_token,
|
||||
aws_region_name,
|
||||
aws_session_name,
|
||||
aws_profile_name,
|
||||
aws_role_name,
|
||||
aws_web_identity_token,
|
||||
aws_sts_endpoint,
|
||||
]
|
||||
|
||||
# Iterate over parameters and update if needed
|
||||
for i, param in enumerate(params_to_check):
|
||||
if param and param.startswith("os.environ/"):
|
||||
_v = get_secret(param)
|
||||
if _v is not None and isinstance(_v, str):
|
||||
params_to_check[i] = _v
|
||||
# Assign updated values back to parameters
|
||||
(
|
||||
aws_access_key_id,
|
||||
aws_secret_access_key,
|
||||
aws_session_token,
|
||||
aws_region_name,
|
||||
aws_session_name,
|
||||
aws_profile_name,
|
||||
aws_role_name,
|
||||
aws_web_identity_token,
|
||||
aws_sts_endpoint,
|
||||
) = params_to_check
|
||||
|
||||
### CHECK STS ###
|
||||
if (
|
||||
aws_web_identity_token is not None
|
||||
and aws_role_name is not None
|
||||
and aws_session_name is not None
|
||||
):
|
||||
print_verbose(
|
||||
f"IN Web Identity Token: {aws_web_identity_token} | Role Name: {aws_role_name} | Session Name: {aws_session_name}"
|
||||
)
|
||||
|
||||
if aws_sts_endpoint is None:
|
||||
sts_endpoint = f"https://sts.{aws_region_name}.amazonaws.com"
|
||||
else:
|
||||
sts_endpoint = aws_sts_endpoint
|
||||
|
||||
iam_creds_cache_key = json.dumps(
|
||||
{
|
||||
"aws_web_identity_token": aws_web_identity_token,
|
||||
"aws_role_name": aws_role_name,
|
||||
"aws_session_name": aws_session_name,
|
||||
"aws_region_name": aws_region_name,
|
||||
"aws_sts_endpoint": sts_endpoint,
|
||||
}
|
||||
)
|
||||
|
||||
iam_creds_dict = iam_cache.get_cache(iam_creds_cache_key)
|
||||
if iam_creds_dict is None:
|
||||
oidc_token = get_secret(aws_web_identity_token)
|
||||
|
||||
if oidc_token is None:
|
||||
raise BedrockError(
|
||||
message="OIDC token could not be retrieved from secret manager.",
|
||||
status_code=401,
|
||||
)
|
||||
|
||||
sts_client = boto3.client(
|
||||
"sts",
|
||||
region_name=aws_region_name,
|
||||
endpoint_url=sts_endpoint,
|
||||
)
|
||||
|
||||
# https://docs.aws.amazon.com/STS/latest/APIReference/API_AssumeRoleWithWebIdentity.html
|
||||
# https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sts/client/assume_role_with_web_identity.html
|
||||
sts_response = sts_client.assume_role_with_web_identity(
|
||||
RoleArn=aws_role_name,
|
||||
RoleSessionName=aws_session_name,
|
||||
WebIdentityToken=oidc_token,
|
||||
DurationSeconds=3600,
|
||||
)
|
||||
|
||||
iam_creds_dict = {
|
||||
"aws_access_key_id": sts_response["Credentials"]["AccessKeyId"],
|
||||
"aws_secret_access_key": sts_response["Credentials"][
|
||||
"SecretAccessKey"
|
||||
],
|
||||
"aws_session_token": sts_response["Credentials"]["SessionToken"],
|
||||
"region_name": aws_region_name,
|
||||
}
|
||||
|
||||
iam_cache.set_cache(
|
||||
key=iam_creds_cache_key,
|
||||
value=json.dumps(iam_creds_dict),
|
||||
ttl=3600 - 60,
|
||||
)
|
||||
|
||||
session = boto3.Session(**iam_creds_dict)
|
||||
|
||||
iam_creds = session.get_credentials()
|
||||
|
||||
return iam_creds
|
||||
elif aws_role_name is not None and aws_session_name is not None:
|
||||
print_verbose(
|
||||
f"Using STS Client AWS aws_role_name: {aws_role_name} aws_session_name: {aws_session_name}"
|
||||
)
|
||||
sts_client = boto3.client(
|
||||
"sts",
|
||||
aws_access_key_id=aws_access_key_id, # [OPTIONAL]
|
||||
aws_secret_access_key=aws_secret_access_key, # [OPTIONAL]
|
||||
)
|
||||
|
||||
sts_response = sts_client.assume_role(
|
||||
RoleArn=aws_role_name, RoleSessionName=aws_session_name
|
||||
)
|
||||
|
||||
# Extract the credentials from the response and convert to Session Credentials
|
||||
sts_credentials = sts_response["Credentials"]
|
||||
from botocore.credentials import Credentials
|
||||
|
||||
credentials = Credentials(
|
||||
access_key=sts_credentials["AccessKeyId"],
|
||||
secret_key=sts_credentials["SecretAccessKey"],
|
||||
token=sts_credentials["SessionToken"],
|
||||
)
|
||||
return credentials
|
||||
elif aws_profile_name is not None: ### CHECK SESSION ###
|
||||
# uses auth values from AWS profile usually stored in ~/.aws/credentials
|
||||
print_verbose(f"Using AWS profile: {aws_profile_name}")
|
||||
client = boto3.Session(profile_name=aws_profile_name)
|
||||
|
||||
return client.get_credentials()
|
||||
elif (
|
||||
aws_access_key_id is not None
|
||||
and aws_secret_access_key is not None
|
||||
and aws_session_token is not None
|
||||
): ### CHECK FOR AWS SESSION TOKEN ###
|
||||
print_verbose(f"Using AWS Session Token: {aws_session_token}")
|
||||
from botocore.credentials import Credentials
|
||||
|
||||
credentials = Credentials(
|
||||
access_key=aws_access_key_id,
|
||||
secret_key=aws_secret_access_key,
|
||||
token=aws_session_token,
|
||||
)
|
||||
return credentials
|
||||
else:
|
||||
print_verbose("Using Default AWS Session")
|
||||
session = boto3.Session(
|
||||
aws_access_key_id=aws_access_key_id,
|
||||
aws_secret_access_key=aws_secret_access_key,
|
||||
region_name=aws_region_name,
|
||||
)
|
||||
|
||||
return session.get_credentials()
|
||||
|
||||
def process_response(
|
||||
self,
|
||||
model: str,
|
||||
|
|
@ -1414,7 +1237,7 @@ class AmazonConverseConfig:
|
|||
return optional_params
|
||||
|
||||
|
||||
class BedrockConverseLLM(BaseLLM):
|
||||
class BedrockConverseLLM(BaseAWSLLM):
|
||||
def __init__(self) -> None:
|
||||
super().__init__()
|
||||
|
||||
|
|
@ -1554,173 +1377,6 @@ class BedrockConverseLLM(BaseLLM):
|
|||
"""
|
||||
return urllib.parse.quote(model_id, safe="")
|
||||
|
||||
def get_credentials(
|
||||
self,
|
||||
aws_access_key_id: Optional[str] = None,
|
||||
aws_secret_access_key: Optional[str] = None,
|
||||
aws_session_token: Optional[str] = None,
|
||||
aws_region_name: Optional[str] = None,
|
||||
aws_session_name: Optional[str] = None,
|
||||
aws_profile_name: Optional[str] = None,
|
||||
aws_role_name: Optional[str] = None,
|
||||
aws_web_identity_token: Optional[str] = None,
|
||||
aws_sts_endpoint: Optional[str] = None,
|
||||
):
|
||||
"""
|
||||
Return a boto3.Credentials object
|
||||
"""
|
||||
import boto3
|
||||
|
||||
## CHECK IS 'os.environ/' passed in
|
||||
params_to_check: List[Optional[str]] = [
|
||||
aws_access_key_id,
|
||||
aws_secret_access_key,
|
||||
aws_session_token,
|
||||
aws_region_name,
|
||||
aws_session_name,
|
||||
aws_profile_name,
|
||||
aws_role_name,
|
||||
aws_web_identity_token,
|
||||
aws_sts_endpoint,
|
||||
]
|
||||
|
||||
# Iterate over parameters and update if needed
|
||||
for i, param in enumerate(params_to_check):
|
||||
if param and param.startswith("os.environ/"):
|
||||
_v = get_secret(param)
|
||||
if _v is not None and isinstance(_v, str):
|
||||
params_to_check[i] = _v
|
||||
# Assign updated values back to parameters
|
||||
(
|
||||
aws_access_key_id,
|
||||
aws_secret_access_key,
|
||||
aws_session_token,
|
||||
aws_region_name,
|
||||
aws_session_name,
|
||||
aws_profile_name,
|
||||
aws_role_name,
|
||||
aws_web_identity_token,
|
||||
aws_sts_endpoint,
|
||||
) = params_to_check
|
||||
|
||||
### CHECK STS ###
|
||||
if (
|
||||
aws_web_identity_token is not None
|
||||
and aws_role_name is not None
|
||||
and aws_session_name is not None
|
||||
):
|
||||
print_verbose(
|
||||
f"IN Web Identity Token: {aws_web_identity_token} | Role Name: {aws_role_name} | Session Name: {aws_session_name}"
|
||||
)
|
||||
|
||||
if aws_sts_endpoint is None:
|
||||
sts_endpoint = f"https://sts.{aws_region_name}.amazonaws.com"
|
||||
else:
|
||||
sts_endpoint = aws_sts_endpoint
|
||||
|
||||
iam_creds_cache_key = json.dumps(
|
||||
{
|
||||
"aws_web_identity_token": aws_web_identity_token,
|
||||
"aws_role_name": aws_role_name,
|
||||
"aws_session_name": aws_session_name,
|
||||
"aws_region_name": aws_region_name,
|
||||
"aws_sts_endpoint": sts_endpoint,
|
||||
}
|
||||
)
|
||||
|
||||
iam_creds_dict = iam_cache.get_cache(iam_creds_cache_key)
|
||||
if iam_creds_dict is None:
|
||||
oidc_token = get_secret(aws_web_identity_token)
|
||||
|
||||
if oidc_token is None:
|
||||
raise BedrockError(
|
||||
message="OIDC token could not be retrieved from secret manager.",
|
||||
status_code=401,
|
||||
)
|
||||
|
||||
sts_client = boto3.client(
|
||||
"sts",
|
||||
region_name=aws_region_name,
|
||||
endpoint_url=sts_endpoint,
|
||||
)
|
||||
|
||||
# https://docs.aws.amazon.com/STS/latest/APIReference/API_AssumeRoleWithWebIdentity.html
|
||||
# https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sts/client/assume_role_with_web_identity.html
|
||||
sts_response = sts_client.assume_role_with_web_identity(
|
||||
RoleArn=aws_role_name,
|
||||
RoleSessionName=aws_session_name,
|
||||
WebIdentityToken=oidc_token,
|
||||
DurationSeconds=3600,
|
||||
)
|
||||
|
||||
iam_creds_dict = {
|
||||
"aws_access_key_id": sts_response["Credentials"]["AccessKeyId"],
|
||||
"aws_secret_access_key": sts_response["Credentials"][
|
||||
"SecretAccessKey"
|
||||
],
|
||||
"aws_session_token": sts_response["Credentials"]["SessionToken"],
|
||||
"region_name": aws_region_name,
|
||||
}
|
||||
|
||||
iam_cache.set_cache(
|
||||
key=iam_creds_cache_key,
|
||||
value=json.dumps(iam_creds_dict),
|
||||
ttl=3600 - 60,
|
||||
)
|
||||
|
||||
session = boto3.Session(**iam_creds_dict)
|
||||
|
||||
iam_creds = session.get_credentials()
|
||||
|
||||
return iam_creds
|
||||
elif aws_role_name is not None and aws_session_name is not None:
|
||||
sts_client = boto3.client(
|
||||
"sts",
|
||||
aws_access_key_id=aws_access_key_id, # [OPTIONAL]
|
||||
aws_secret_access_key=aws_secret_access_key, # [OPTIONAL]
|
||||
)
|
||||
|
||||
sts_response = sts_client.assume_role(
|
||||
RoleArn=aws_role_name, RoleSessionName=aws_session_name
|
||||
)
|
||||
|
||||
# Extract the credentials from the response and convert to Session Credentials
|
||||
sts_credentials = sts_response["Credentials"]
|
||||
from botocore.credentials import Credentials
|
||||
|
||||
credentials = Credentials(
|
||||
access_key=sts_credentials["AccessKeyId"],
|
||||
secret_key=sts_credentials["SecretAccessKey"],
|
||||
token=sts_credentials["SessionToken"],
|
||||
)
|
||||
return credentials
|
||||
elif aws_profile_name is not None: ### CHECK SESSION ###
|
||||
# uses auth values from AWS profile usually stored in ~/.aws/credentials
|
||||
client = boto3.Session(profile_name=aws_profile_name)
|
||||
|
||||
return client.get_credentials()
|
||||
elif (
|
||||
aws_access_key_id is not None
|
||||
and aws_secret_access_key is not None
|
||||
and aws_session_token is not None
|
||||
): ### CHECK FOR AWS SESSION TOKEN ###
|
||||
from botocore.credentials import Credentials
|
||||
|
||||
credentials = Credentials(
|
||||
access_key=aws_access_key_id,
|
||||
secret_key=aws_secret_access_key,
|
||||
token=aws_session_token,
|
||||
)
|
||||
return credentials
|
||||
else:
|
||||
session = boto3.Session(
|
||||
aws_access_key_id=aws_access_key_id,
|
||||
aws_secret_access_key=aws_secret_access_key,
|
||||
region_name=aws_region_name,
|
||||
)
|
||||
|
||||
return session.get_credentials()
|
||||
|
||||
async def async_streaming(
|
||||
self,
|
||||
model: str,
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -95,7 +95,6 @@ from .llms import (
|
|||
palm,
|
||||
petals,
|
||||
replicate,
|
||||
sagemaker,
|
||||
together_ai,
|
||||
triton,
|
||||
vertex_ai,
|
||||
|
|
@ -120,6 +119,7 @@ from .llms.prompt_templates.factory import (
|
|||
prompt_factory,
|
||||
stringify_json_tool_call_content,
|
||||
)
|
||||
from .llms.sagemaker import SagemakerLLM
|
||||
from .llms.text_completion_codestral import CodestralTextCompletion
|
||||
from .llms.triton import TritonChatCompletion
|
||||
from .llms.vertex_ai_partner import VertexAIPartnerModels
|
||||
|
|
@ -166,6 +166,7 @@ bedrock_converse_chat_completion = BedrockConverseLLM()
|
|||
vertex_chat_completion = VertexLLM()
|
||||
vertex_partner_models_chat_completion = VertexAIPartnerModels()
|
||||
watsonxai = IBMWatsonXAI()
|
||||
sagemaker_llm = SagemakerLLM()
|
||||
####### COMPLETION ENDPOINTS ################
|
||||
|
||||
|
||||
|
|
@ -2216,7 +2217,7 @@ def completion(
|
|||
response = model_response
|
||||
elif custom_llm_provider == "sagemaker":
|
||||
# boto3 reads keys from .env
|
||||
model_response = sagemaker.completion(
|
||||
model_response = sagemaker_llm.completion(
|
||||
model=model,
|
||||
messages=messages,
|
||||
model_response=model_response,
|
||||
|
|
@ -2230,26 +2231,13 @@ def completion(
|
|||
logging_obj=logging,
|
||||
acompletion=acompletion,
|
||||
)
|
||||
if (
|
||||
"stream" in optional_params and optional_params["stream"] == True
|
||||
): ## [BETA]
|
||||
print_verbose(f"ENTERS SAGEMAKER CUSTOMSTREAMWRAPPER")
|
||||
from .llms.sagemaker import TokenIterator
|
||||
|
||||
tokenIterator = TokenIterator(model_response, acompletion=acompletion)
|
||||
response = CustomStreamWrapper(
|
||||
completion_stream=tokenIterator,
|
||||
model=model,
|
||||
custom_llm_provider="sagemaker",
|
||||
logging_obj=logging,
|
||||
)
|
||||
if optional_params.get("stream", False):
|
||||
## LOGGING
|
||||
logging.post_call(
|
||||
input=messages,
|
||||
api_key=None,
|
||||
original_response=response,
|
||||
original_response=model_response,
|
||||
)
|
||||
return response
|
||||
|
||||
## RESPONSE OBJECT
|
||||
response = model_response
|
||||
|
|
@ -3529,7 +3517,7 @@ def embedding(
|
|||
model_response=EmbeddingResponse(),
|
||||
)
|
||||
elif custom_llm_provider == "sagemaker":
|
||||
response = sagemaker.embedding(
|
||||
response = sagemaker_llm.embedding(
|
||||
model=model,
|
||||
input=input,
|
||||
encoding=encoding,
|
||||
|
|
|
|||
File diff suppressed because one or more lines are too long
|
|
@ -1 +0,0 @@
|
|||
(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[185],{87421:function(e,n,t){Promise.resolve().then(t.t.bind(t,99646,23)),Promise.resolve().then(t.t.bind(t,63385,23))},63385:function(){},99646:function(e){e.exports={style:{fontFamily:"'__Inter_86ef86', '__Inter_Fallback_86ef86'",fontStyle:"normal"},className:"__className_86ef86"}}},function(e){e.O(0,[971,69,744],function(){return e(e.s=87421)}),_N_E=e.O()}]);
|
||||
File diff suppressed because one or more lines are too long
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -3,4 +3,12 @@ model_list:
|
|||
litellm_params:
|
||||
model: "gpt-4"
|
||||
model_info:
|
||||
my_custom_key: "my_custom_value"
|
||||
my_custom_key: "my_custom_value"
|
||||
|
||||
litellm_settings:
|
||||
success_callback: ["s3"]
|
||||
s3_callback_params:
|
||||
s3_bucket_name: mytestbucketlitellm # AWS Bucket Name for S3
|
||||
s3_region_name: us-west-2 # AWS Region Name for S3
|
||||
s3_aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID # us os.environ/<variable name> to pass environment variables. This is AWS Access Key ID for S3
|
||||
s3_aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY # AWS Secret Access Key for S3
|
||||
|
|
|
|||
|
|
@ -5,10 +5,10 @@ import sys
|
|||
import uuid
|
||||
from dataclasses import fields
|
||||
from datetime import datetime
|
||||
from typing import TYPE_CHECKING, Any, Dict, List, Literal, Optional, TypedDict, Union
|
||||
from typing import TYPE_CHECKING, Any, Dict, List, Literal, Optional, Union
|
||||
|
||||
from pydantic import BaseModel, ConfigDict, Extra, Field, Json, model_validator
|
||||
from typing_extensions import Annotated
|
||||
from typing_extensions import Annotated, TypedDict
|
||||
|
||||
from litellm.types.router import UpdateRouterConfig
|
||||
from litellm.types.utils import ProviderField
|
||||
|
|
@ -1082,6 +1082,20 @@ class DynamoDBArgs(LiteLLMBase):
|
|||
assume_role_aws_session_name: Optional[str] = None
|
||||
|
||||
|
||||
class PassThroughGenericEndpoint(LiteLLMBase):
|
||||
path: str = Field(description="The route to be added to the LiteLLM Proxy Server.")
|
||||
target: str = Field(
|
||||
description="The URL to which requests for this path should be forwarded."
|
||||
)
|
||||
headers: dict = Field(
|
||||
description="Key-value pairs of headers to be forwarded with the request. You can set any key value pair here and it will be forwarded to your target endpoint"
|
||||
)
|
||||
|
||||
|
||||
class PassThroughEndpointResponse(LiteLLMBase):
|
||||
endpoints: List[PassThroughGenericEndpoint]
|
||||
|
||||
|
||||
class ConfigFieldUpdate(LiteLLMBase):
|
||||
field_name: str
|
||||
field_value: Any
|
||||
|
|
@ -1093,6 +1107,14 @@ class ConfigFieldDelete(LiteLLMBase):
|
|||
field_name: str
|
||||
|
||||
|
||||
class FieldDetail(BaseModel):
|
||||
field_name: str
|
||||
field_type: str
|
||||
field_description: str
|
||||
field_default_value: Any = None
|
||||
stored_in_db: Optional[bool]
|
||||
|
||||
|
||||
class ConfigList(LiteLLMBase):
|
||||
field_name: str
|
||||
field_type: str
|
||||
|
|
@ -1101,6 +1123,9 @@ class ConfigList(LiteLLMBase):
|
|||
stored_in_db: Optional[bool]
|
||||
field_default_value: Any
|
||||
premium_field: bool = False
|
||||
nested_fields: Optional[List[FieldDetail]] = (
|
||||
None # For nested dictionary or Pydantic fields
|
||||
)
|
||||
|
||||
|
||||
class ConfigGeneralSettings(LiteLLMBase):
|
||||
|
|
@ -1203,6 +1228,10 @@ class ConfigGeneralSettings(LiteLLMBase):
|
|||
default=False,
|
||||
description="Public model hub for users to see what models they have access to, supported openai params, etc.",
|
||||
)
|
||||
pass_through_endpoints: Optional[List[PassThroughGenericEndpoint]] = Field(
|
||||
default=None,
|
||||
description="Set-up pass-through endpoints for provider-specific endpoints. Docs - https://docs.litellm.ai/docs/proxy/pass_through",
|
||||
)
|
||||
|
||||
|
||||
class ConfigYAML(LiteLLMBase):
|
||||
|
|
@ -1761,3 +1790,9 @@ class VirtualKeyEvent(LiteLLMBase):
|
|||
created_by_user_role: str
|
||||
created_by_key_alias: Optional[str]
|
||||
request_kwargs: dict
|
||||
|
||||
|
||||
class CreatePassThroughEndpoint(LiteLLMBase):
|
||||
path: str
|
||||
target: str
|
||||
headers: dict
|
||||
|
|
|
|||
|
|
@ -1,27 +1,26 @@
|
|||
import tempfile
|
||||
|
||||
import boto3
|
||||
import yaml
|
||||
|
||||
from litellm._logging import verbose_proxy_logger
|
||||
|
||||
|
||||
def get_file_contents_from_s3(bucket_name, object_key):
|
||||
# v0 rely on boto3 for authentication - allowing boto3 to handle IAM credentials etc
|
||||
from botocore.config import Config
|
||||
from botocore.credentials import Credentials
|
||||
|
||||
from litellm.main import bedrock_converse_chat_completion
|
||||
|
||||
credentials: Credentials = bedrock_converse_chat_completion.get_credentials()
|
||||
s3_client = boto3.client(
|
||||
"s3",
|
||||
aws_access_key_id=credentials.access_key,
|
||||
aws_secret_access_key=credentials.secret_key,
|
||||
aws_session_token=credentials.token, # Optional, if using temporary credentials
|
||||
)
|
||||
|
||||
try:
|
||||
# v0 rely on boto3 for authentication - allowing boto3 to handle IAM credentials etc
|
||||
import tempfile
|
||||
|
||||
import boto3
|
||||
from botocore.config import Config
|
||||
from botocore.credentials import Credentials
|
||||
|
||||
from litellm.main import bedrock_converse_chat_completion
|
||||
|
||||
credentials: Credentials = bedrock_converse_chat_completion.get_credentials()
|
||||
s3_client = boto3.client(
|
||||
"s3",
|
||||
aws_access_key_id=credentials.access_key,
|
||||
aws_secret_access_key=credentials.secret_key,
|
||||
aws_session_token=credentials.token, # Optional, if using temporary credentials
|
||||
)
|
||||
verbose_proxy_logger.debug(
|
||||
f"Retrieving {object_key} from S3 bucket: {bucket_name}"
|
||||
)
|
||||
|
|
@ -43,6 +42,10 @@ def get_file_contents_from_s3(bucket_name, object_key):
|
|||
config = yaml.safe_load(yaml_file)
|
||||
|
||||
return config
|
||||
except ImportError:
|
||||
# this is most likely if a user is not using the litellm docker container
|
||||
verbose_proxy_logger.error(f"ImportError: {str(e)}")
|
||||
pass
|
||||
except Exception as e:
|
||||
verbose_proxy_logger.error(f"Error retrieving file contents: {str(e)}")
|
||||
return None
|
||||
|
|
|
|||
|
|
@ -0,0 +1,47 @@
|
|||
"""
|
||||
What is this?
|
||||
|
||||
CRUD endpoints for managing pass-through endpoints
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import traceback
|
||||
from datetime import datetime, timedelta, timezone
|
||||
from typing import List, Optional
|
||||
|
||||
import fastapi
|
||||
import httpx
|
||||
from fastapi import (
|
||||
APIRouter,
|
||||
Depends,
|
||||
File,
|
||||
Form,
|
||||
Header,
|
||||
HTTPException,
|
||||
Request,
|
||||
Response,
|
||||
UploadFile,
|
||||
status,
|
||||
)
|
||||
|
||||
import litellm
|
||||
from litellm._logging import verbose_proxy_logger
|
||||
from litellm.batches.main import FileObject
|
||||
from litellm.proxy._types import *
|
||||
from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.get(
|
||||
"/config/pass_through_endpoints/settings",
|
||||
dependencies=[Depends(user_api_key_auth)],
|
||||
tags=["pass-through-endpoints"],
|
||||
summary="Create pass-through endpoints for provider specific endpoints - https://docs.litellm.ai/docs/proxy/pass_through",
|
||||
)
|
||||
async def create_fine_tuning_job(
|
||||
request: Request,
|
||||
fastapi_response: Response,
|
||||
user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
|
||||
):
|
||||
pass
|
||||
|
|
@ -126,14 +126,19 @@ async def add_litellm_data_to_request(
|
|||
|
||||
safe_add_api_version_from_query_params(data, request)
|
||||
|
||||
_headers = dict(request.headers)
|
||||
|
||||
# Include original request and headers in the data
|
||||
data["proxy_server_request"] = {
|
||||
"url": str(request.url),
|
||||
"method": request.method,
|
||||
"headers": dict(request.headers),
|
||||
"headers": _headers,
|
||||
"body": copy.copy(data), # use copy instead of deepcopy
|
||||
}
|
||||
|
||||
## Forward any LLM API Provider specific headers in extra_headers
|
||||
add_provider_specific_headers_to_request(data=data, headers=_headers)
|
||||
|
||||
## Cache Controls
|
||||
headers = request.headers
|
||||
verbose_proxy_logger.debug("Request Headers: %s", headers)
|
||||
|
|
@ -306,6 +311,31 @@ async def add_litellm_data_to_request(
|
|||
return data
|
||||
|
||||
|
||||
def add_provider_specific_headers_to_request(
|
||||
data: dict,
|
||||
headers: dict,
|
||||
):
|
||||
ANTHROPIC_API_HEADERS = [
|
||||
"anthropic-version",
|
||||
"anthropic-beta",
|
||||
]
|
||||
|
||||
extra_headers = data.get("extra_headers", {}) or {}
|
||||
|
||||
# boolean to indicate if a header was added
|
||||
added_header = False
|
||||
for header in ANTHROPIC_API_HEADERS:
|
||||
if header in headers:
|
||||
header_value = headers[header]
|
||||
extra_headers.update({header: header_value})
|
||||
added_header = True
|
||||
|
||||
if added_header is True:
|
||||
data["extra_headers"] = extra_headers
|
||||
|
||||
return
|
||||
|
||||
|
||||
def _add_otel_traceparent_to_data(data: dict, request: Request):
|
||||
from litellm.proxy.proxy_server import open_telemetry_logger
|
||||
|
||||
|
|
|
|||
1
litellm/proxy/out/404.html
Normal file
1
litellm/proxy/out/404.html
Normal file
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
|
|
@ -0,0 +1 @@
|
|||
(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[185],{11837:function(n,e,t){Promise.resolve().then(t.t.bind(t,99646,23)),Promise.resolve().then(t.t.bind(t,63385,23))},63385:function(){},99646:function(n){n.exports={style:{fontFamily:"'__Inter_12bbc4', '__Inter_Fallback_12bbc4'",fontStyle:"normal"},className:"__className_12bbc4"}}},function(n){n.O(0,[971,69,744],function(){return n(n.s=11837)}),_N_E=n.O()}]);
|
||||
File diff suppressed because one or more lines are too long
|
|
@ -1 +1 @@
|
|||
(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[461],{61994:function(e,s,t){Promise.resolve().then(t.bind(t,667))},667:function(e,s,t){"use strict";t.r(s),t.d(s,{default:function(){return g}});var l=t(57437),n=t(2265),a=t(47907),i=t(2179),r=t(18190),o=t(13810),c=t(10384),u=t(46453),d=t(71801),m=t(52273),h=t(42440),x=t(30953),f=t(777),p=t(37963),j=t(60620),_=t(1861);function g(){let[e]=j.Z.useForm(),s=(0,a.useSearchParams)();!function(e){console.log("COOKIES",document.cookie);let s=document.cookie.split("; ").find(s=>s.startsWith(e+"="));s&&s.split("=")[1]}("token");let t=s.get("invitation_id"),[g,Z]=(0,n.useState)(null),[k,w]=(0,n.useState)(""),[S,b]=(0,n.useState)(""),[N,v]=(0,n.useState)(null),[y,E]=(0,n.useState)(""),[I,O]=(0,n.useState)("");return(0,n.useEffect)(()=>{t&&(0,f.W_)(t).then(e=>{let s=e.login_url;console.log("login_url:",s),E(s);let t=e.token,l=(0,p.o)(t);O(t),console.log("decoded:",l),Z(l.key),console.log("decoded user email:",l.user_email),b(l.user_email),v(l.user_id)})},[t]),(0,l.jsx)("div",{className:"mx-auto w-full max-w-md mt-10",children:(0,l.jsxs)(o.Z,{children:[(0,l.jsx)(h.Z,{className:"text-sm mb-5 text-center",children:"\uD83D\uDE85 LiteLLM"}),(0,l.jsx)(h.Z,{className:"text-xl",children:"Sign up"}),(0,l.jsx)(d.Z,{children:"Claim your user account to login to Admin UI."}),(0,l.jsx)(r.Z,{className:"mt-4",title:"SSO",icon:x.GH$,color:"sky",children:(0,l.jsxs)(u.Z,{numItems:2,className:"flex justify-between items-center",children:[(0,l.jsx)(c.Z,{children:"SSO is under the Enterprise Tirer."}),(0,l.jsx)(c.Z,{children:(0,l.jsx)(i.Z,{variant:"primary",className:"mb-2",children:(0,l.jsx)("a",{href:"https://forms.gle/W3U4PZpJGFHWtHyA9",target:"_blank",children:"Get Free Trial"})})})]})}),(0,l.jsxs)(j.Z,{className:"mt-10 mb-5 mx-auto",layout:"vertical",onFinish:e=>{console.log("in handle submit. accessToken:",g,"token:",I,"formValues:",e),g&&I&&(e.user_email=S,N&&t&&(0,f.m_)(g,t,N,e.password).then(e=>{var s;let t="/ui/";t+="?userID="+((null===(s=e.data)||void 0===s?void 0:s.user_id)||e.user_id),document.cookie="token="+I,console.log("redirecting to:",t),window.location.href=t}))},children:[(0,l.jsxs)(l.Fragment,{children:[(0,l.jsx)(j.Z.Item,{label:"Email Address",name:"user_email",children:(0,l.jsx)(m.Z,{type:"email",disabled:!0,value:S,defaultValue:S,className:"max-w-md"})}),(0,l.jsx)(j.Z.Item,{label:"Password",name:"password",rules:[{required:!0,message:"password required to sign up"}],help:"Create a password for your account",children:(0,l.jsx)(m.Z,{placeholder:"",type:"password",className:"max-w-md"})})]}),(0,l.jsx)("div",{className:"mt-10",children:(0,l.jsx)(_.ZP,{htmlType:"submit",children:"Sign Up"})})]})]})})}}},function(e){e.O(0,[665,505,684,777,971,69,744],function(){return e(e.s=61994)}),_N_E=e.O()}]);
|
||||
(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[461],{20723:function(e,s,t){Promise.resolve().then(t.bind(t,667))},667:function(e,s,t){"use strict";t.r(s),t.d(s,{default:function(){return g}});var l=t(57437),n=t(2265),a=t(47907),i=t(2179),r=t(18190),o=t(13810),c=t(10384),u=t(46453),d=t(71801),m=t(52273),h=t(42440),x=t(30953),f=t(777),p=t(37963),j=t(60620),_=t(1861);function g(){let[e]=j.Z.useForm(),s=(0,a.useSearchParams)();!function(e){console.log("COOKIES",document.cookie);let s=document.cookie.split("; ").find(s=>s.startsWith(e+"="));s&&s.split("=")[1]}("token");let t=s.get("invitation_id"),[g,Z]=(0,n.useState)(null),[k,w]=(0,n.useState)(""),[S,b]=(0,n.useState)(""),[N,v]=(0,n.useState)(null),[y,E]=(0,n.useState)(""),[I,O]=(0,n.useState)("");return(0,n.useEffect)(()=>{t&&(0,f.W_)(t).then(e=>{let s=e.login_url;console.log("login_url:",s),E(s);let t=e.token,l=(0,p.o)(t);O(t),console.log("decoded:",l),Z(l.key),console.log("decoded user email:",l.user_email),b(l.user_email),v(l.user_id)})},[t]),(0,l.jsx)("div",{className:"mx-auto w-full max-w-md mt-10",children:(0,l.jsxs)(o.Z,{children:[(0,l.jsx)(h.Z,{className:"text-sm mb-5 text-center",children:"\uD83D\uDE85 LiteLLM"}),(0,l.jsx)(h.Z,{className:"text-xl",children:"Sign up"}),(0,l.jsx)(d.Z,{children:"Claim your user account to login to Admin UI."}),(0,l.jsx)(r.Z,{className:"mt-4",title:"SSO",icon:x.GH$,color:"sky",children:(0,l.jsxs)(u.Z,{numItems:2,className:"flex justify-between items-center",children:[(0,l.jsx)(c.Z,{children:"SSO is under the Enterprise Tirer."}),(0,l.jsx)(c.Z,{children:(0,l.jsx)(i.Z,{variant:"primary",className:"mb-2",children:(0,l.jsx)("a",{href:"https://forms.gle/W3U4PZpJGFHWtHyA9",target:"_blank",children:"Get Free Trial"})})})]})}),(0,l.jsxs)(j.Z,{className:"mt-10 mb-5 mx-auto",layout:"vertical",onFinish:e=>{console.log("in handle submit. accessToken:",g,"token:",I,"formValues:",e),g&&I&&(e.user_email=S,N&&t&&(0,f.m_)(g,t,N,e.password).then(e=>{var s;let t="/ui/";t+="?userID="+((null===(s=e.data)||void 0===s?void 0:s.user_id)||e.user_id),document.cookie="token="+I,console.log("redirecting to:",t),window.location.href=t}))},children:[(0,l.jsxs)(l.Fragment,{children:[(0,l.jsx)(j.Z.Item,{label:"Email Address",name:"user_email",children:(0,l.jsx)(m.Z,{type:"email",disabled:!0,value:S,defaultValue:S,className:"max-w-md"})}),(0,l.jsx)(j.Z.Item,{label:"Password",name:"password",rules:[{required:!0,message:"password required to sign up"}],help:"Create a password for your account",children:(0,l.jsx)(m.Z,{placeholder:"",type:"password",className:"max-w-md"})})]}),(0,l.jsx)("div",{className:"mt-10",children:(0,l.jsx)(_.ZP,{htmlType:"submit",children:"Sign Up"})})]})]})})}}},function(e){e.O(0,[665,505,684,777,971,69,744],function(){return e(e.s=20723)}),_N_E=e.O()}]);
|
||||
File diff suppressed because one or more lines are too long
|
|
@ -1 +1 @@
|
|||
(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[744],{32028:function(e,n,t){Promise.resolve().then(t.t.bind(t,47690,23)),Promise.resolve().then(t.t.bind(t,48955,23)),Promise.resolve().then(t.t.bind(t,5613,23)),Promise.resolve().then(t.t.bind(t,11902,23)),Promise.resolve().then(t.t.bind(t,31778,23)),Promise.resolve().then(t.t.bind(t,77831,23))}},function(e){var n=function(n){return e(e.s=n)};e.O(0,[971,69],function(){return n(35317),n(32028)}),_N_E=e.O()}]);
|
||||
(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[744],{70377:function(e,n,t){Promise.resolve().then(t.t.bind(t,47690,23)),Promise.resolve().then(t.t.bind(t,48955,23)),Promise.resolve().then(t.t.bind(t,5613,23)),Promise.resolve().then(t.t.bind(t,11902,23)),Promise.resolve().then(t.t.bind(t,31778,23)),Promise.resolve().then(t.t.bind(t,77831,23))}},function(e){var n=function(n){return e(e.s=n)};e.O(0,[971,69],function(){return n(35317),n(70377)}),_N_E=e.O()}]);
|
||||
|
|
@ -1 +1 @@
|
|||
!function(){"use strict";var e,t,n,r,o,u,i,c,f,a={},l={};function d(e){var t=l[e];if(void 0!==t)return t.exports;var n=l[e]={id:e,loaded:!1,exports:{}},r=!0;try{a[e](n,n.exports,d),r=!1}finally{r&&delete l[e]}return n.loaded=!0,n.exports}d.m=a,e=[],d.O=function(t,n,r,o){if(n){o=o||0;for(var u=e.length;u>0&&e[u-1][2]>o;u--)e[u]=e[u-1];e[u]=[n,r,o];return}for(var i=1/0,u=0;u<e.length;u++){for(var n=e[u][0],r=e[u][1],o=e[u][2],c=!0,f=0;f<n.length;f++)i>=o&&Object.keys(d.O).every(function(e){return d.O[e](n[f])})?n.splice(f--,1):(c=!1,o<i&&(i=o));if(c){e.splice(u--,1);var a=r();void 0!==a&&(t=a)}}return t},d.n=function(e){var t=e&&e.__esModule?function(){return e.default}:function(){return e};return d.d(t,{a:t}),t},n=Object.getPrototypeOf?function(e){return Object.getPrototypeOf(e)}:function(e){return e.__proto__},d.t=function(e,r){if(1&r&&(e=this(e)),8&r||"object"==typeof e&&e&&(4&r&&e.__esModule||16&r&&"function"==typeof e.then))return e;var o=Object.create(null);d.r(o);var u={};t=t||[null,n({}),n([]),n(n)];for(var i=2&r&&e;"object"==typeof i&&!~t.indexOf(i);i=n(i))Object.getOwnPropertyNames(i).forEach(function(t){u[t]=function(){return e[t]}});return u.default=function(){return e},d.d(o,u),o},d.d=function(e,t){for(var n in t)d.o(t,n)&&!d.o(e,n)&&Object.defineProperty(e,n,{enumerable:!0,get:t[n]})},d.f={},d.e=function(e){return Promise.all(Object.keys(d.f).reduce(function(t,n){return d.f[n](e,t),t},[]))},d.u=function(e){},d.miniCssF=function(e){return"static/css/cd10067a0a3408b4.css"},d.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||Function("return this")()}catch(e){if("object"==typeof window)return window}}(),d.o=function(e,t){return Object.prototype.hasOwnProperty.call(e,t)},r={},o="_N_E:",d.l=function(e,t,n,u){if(r[e]){r[e].push(t);return}if(void 0!==n)for(var i,c,f=document.getElementsByTagName("script"),a=0;a<f.length;a++){var l=f[a];if(l.getAttribute("src")==e||l.getAttribute("data-webpack")==o+n){i=l;break}}i||(c=!0,(i=document.createElement("script")).charset="utf-8",i.timeout=120,d.nc&&i.setAttribute("nonce",d.nc),i.setAttribute("data-webpack",o+n),i.src=d.tu(e)),r[e]=[t];var s=function(t,n){i.onerror=i.onload=null,clearTimeout(p);var o=r[e];if(delete r[e],i.parentNode&&i.parentNode.removeChild(i),o&&o.forEach(function(e){return e(n)}),t)return t(n)},p=setTimeout(s.bind(null,void 0,{type:"timeout",target:i}),12e4);i.onerror=s.bind(null,i.onerror),i.onload=s.bind(null,i.onload),c&&document.head.appendChild(i)},d.r=function(e){"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},d.nmd=function(e){return e.paths=[],e.children||(e.children=[]),e},d.tt=function(){return void 0===u&&(u={createScriptURL:function(e){return e}},"undefined"!=typeof trustedTypes&&trustedTypes.createPolicy&&(u=trustedTypes.createPolicy("nextjs#bundler",u))),u},d.tu=function(e){return d.tt().createScriptURL(e)},d.p="/ui/_next/",i={272:0},d.f.j=function(e,t){var n=d.o(i,e)?i[e]:void 0;if(0!==n){if(n)t.push(n[2]);else if(272!=e){var r=new Promise(function(t,r){n=i[e]=[t,r]});t.push(n[2]=r);var o=d.p+d.u(e),u=Error();d.l(o,function(t){if(d.o(i,e)&&(0!==(n=i[e])&&(i[e]=void 0),n)){var r=t&&("load"===t.type?"missing":t.type),o=t&&t.target&&t.target.src;u.message="Loading chunk "+e+" failed.\n("+r+": "+o+")",u.name="ChunkLoadError",u.type=r,u.request=o,n[1](u)}},"chunk-"+e,e)}else i[e]=0}},d.O.j=function(e){return 0===i[e]},c=function(e,t){var n,r,o=t[0],u=t[1],c=t[2],f=0;if(o.some(function(e){return 0!==i[e]})){for(n in u)d.o(u,n)&&(d.m[n]=u[n]);if(c)var a=c(d)}for(e&&e(t);f<o.length;f++)r=o[f],d.o(i,r)&&i[r]&&i[r][0](),i[r]=0;return d.O(a)},(f=self.webpackChunk_N_E=self.webpackChunk_N_E||[]).forEach(c.bind(null,0)),f.push=c.bind(null,f.push.bind(f))}();
|
||||
!function(){"use strict";var e,t,n,r,o,u,i,c,f,a={},l={};function d(e){var t=l[e];if(void 0!==t)return t.exports;var n=l[e]={id:e,loaded:!1,exports:{}},r=!0;try{a[e](n,n.exports,d),r=!1}finally{r&&delete l[e]}return n.loaded=!0,n.exports}d.m=a,e=[],d.O=function(t,n,r,o){if(n){o=o||0;for(var u=e.length;u>0&&e[u-1][2]>o;u--)e[u]=e[u-1];e[u]=[n,r,o];return}for(var i=1/0,u=0;u<e.length;u++){for(var n=e[u][0],r=e[u][1],o=e[u][2],c=!0,f=0;f<n.length;f++)i>=o&&Object.keys(d.O).every(function(e){return d.O[e](n[f])})?n.splice(f--,1):(c=!1,o<i&&(i=o));if(c){e.splice(u--,1);var a=r();void 0!==a&&(t=a)}}return t},d.n=function(e){var t=e&&e.__esModule?function(){return e.default}:function(){return e};return d.d(t,{a:t}),t},n=Object.getPrototypeOf?function(e){return Object.getPrototypeOf(e)}:function(e){return e.__proto__},d.t=function(e,r){if(1&r&&(e=this(e)),8&r||"object"==typeof e&&e&&(4&r&&e.__esModule||16&r&&"function"==typeof e.then))return e;var o=Object.create(null);d.r(o);var u={};t=t||[null,n({}),n([]),n(n)];for(var i=2&r&&e;"object"==typeof i&&!~t.indexOf(i);i=n(i))Object.getOwnPropertyNames(i).forEach(function(t){u[t]=function(){return e[t]}});return u.default=function(){return e},d.d(o,u),o},d.d=function(e,t){for(var n in t)d.o(t,n)&&!d.o(e,n)&&Object.defineProperty(e,n,{enumerable:!0,get:t[n]})},d.f={},d.e=function(e){return Promise.all(Object.keys(d.f).reduce(function(t,n){return d.f[n](e,t),t},[]))},d.u=function(e){},d.miniCssF=function(e){return"static/css/051d7321f11572d4.css"},d.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||Function("return this")()}catch(e){if("object"==typeof window)return window}}(),d.o=function(e,t){return Object.prototype.hasOwnProperty.call(e,t)},r={},o="_N_E:",d.l=function(e,t,n,u){if(r[e]){r[e].push(t);return}if(void 0!==n)for(var i,c,f=document.getElementsByTagName("script"),a=0;a<f.length;a++){var l=f[a];if(l.getAttribute("src")==e||l.getAttribute("data-webpack")==o+n){i=l;break}}i||(c=!0,(i=document.createElement("script")).charset="utf-8",i.timeout=120,d.nc&&i.setAttribute("nonce",d.nc),i.setAttribute("data-webpack",o+n),i.src=d.tu(e)),r[e]=[t];var s=function(t,n){i.onerror=i.onload=null,clearTimeout(p);var o=r[e];if(delete r[e],i.parentNode&&i.parentNode.removeChild(i),o&&o.forEach(function(e){return e(n)}),t)return t(n)},p=setTimeout(s.bind(null,void 0,{type:"timeout",target:i}),12e4);i.onerror=s.bind(null,i.onerror),i.onload=s.bind(null,i.onload),c&&document.head.appendChild(i)},d.r=function(e){"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},d.nmd=function(e){return e.paths=[],e.children||(e.children=[]),e},d.tt=function(){return void 0===u&&(u={createScriptURL:function(e){return e}},"undefined"!=typeof trustedTypes&&trustedTypes.createPolicy&&(u=trustedTypes.createPolicy("nextjs#bundler",u))),u},d.tu=function(e){return d.tt().createScriptURL(e)},d.p="/ui/_next/",i={272:0},d.f.j=function(e,t){var n=d.o(i,e)?i[e]:void 0;if(0!==n){if(n)t.push(n[2]);else if(272!=e){var r=new Promise(function(t,r){n=i[e]=[t,r]});t.push(n[2]=r);var o=d.p+d.u(e),u=Error();d.l(o,function(t){if(d.o(i,e)&&(0!==(n=i[e])&&(i[e]=void 0),n)){var r=t&&("load"===t.type?"missing":t.type),o=t&&t.target&&t.target.src;u.message="Loading chunk "+e+" failed.\n("+r+": "+o+")",u.name="ChunkLoadError",u.type=r,u.request=o,n[1](u)}},"chunk-"+e,e)}else i[e]=0}},d.O.j=function(e){return 0===i[e]},c=function(e,t){var n,r,o=t[0],u=t[1],c=t[2],f=0;if(o.some(function(e){return 0!==i[e]})){for(n in u)d.o(u,n)&&(d.m[n]=u[n]);if(c)var a=c(d)}for(e&&e(t);f<o.length;f++)r=o[f],d.o(i,r)&&i[r]&&i[r][0](),i[r]=0;return d.O(a)},(f=self.webpackChunk_N_E=self.webpackChunk_N_E||[]).forEach(c.bind(null,0)),f.push=c.bind(null,f.push.bind(f))}();
|
||||
|
|
@ -1,4 +1,4 @@
|
|||
@font-face{font-family:__Inter_86ef86;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/55c55f0601d81cf3-s.woff2) format("woff2");unicode-range:u+0460-052f,u+1c80-1c88,u+20b4,u+2de0-2dff,u+a640-a69f,u+fe2e-fe2f}@font-face{font-family:__Inter_86ef86;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/26a46d62cd723877-s.woff2) format("woff2");unicode-range:u+0301,u+0400-045f,u+0490-0491,u+04b0-04b1,u+2116}@font-face{font-family:__Inter_86ef86;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/97e0cb1ae144a2a9-s.woff2) format("woff2");unicode-range:u+1f??}@font-face{font-family:__Inter_86ef86;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/581909926a08bbc8-s.woff2) format("woff2");unicode-range:u+0370-0377,u+037a-037f,u+0384-038a,u+038c,u+038e-03a1,u+03a3-03ff}@font-face{font-family:__Inter_86ef86;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/df0a9ae256c0569c-s.woff2) format("woff2");unicode-range:u+0102-0103,u+0110-0111,u+0128-0129,u+0168-0169,u+01a0-01a1,u+01af-01b0,u+0300-0301,u+0303-0304,u+0308-0309,u+0323,u+0329,u+1ea0-1ef9,u+20ab}@font-face{font-family:__Inter_86ef86;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/6d93bde91c0c2823-s.woff2) format("woff2");unicode-range:u+0100-02af,u+0304,u+0308,u+0329,u+1e00-1e9f,u+1ef2-1eff,u+2020,u+20a0-20ab,u+20ad-20c0,u+2113,u+2c60-2c7f,u+a720-a7ff}@font-face{font-family:__Inter_86ef86;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/a34f9d1faa5f3315-s.p.woff2) format("woff2");unicode-range:u+00??,u+0131,u+0152-0153,u+02bb-02bc,u+02c6,u+02da,u+02dc,u+0304,u+0308,u+0329,u+2000-206f,u+2074,u+20ac,u+2122,u+2191,u+2193,u+2212,u+2215,u+feff,u+fffd}@font-face{font-family:__Inter_Fallback_86ef86;src:local("Arial");ascent-override:90.20%;descent-override:22.48%;line-gap-override:0.00%;size-adjust:107.40%}.__className_86ef86{font-family:__Inter_86ef86,__Inter_Fallback_86ef86;font-style:normal}
|
||||
@font-face{font-family:__Inter_12bbc4;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/ec159349637c90ad-s.woff2) format("woff2");unicode-range:u+0460-052f,u+1c80-1c88,u+20b4,u+2de0-2dff,u+a640-a69f,u+fe2e-fe2f}@font-face{font-family:__Inter_12bbc4;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/513657b02c5c193f-s.woff2) format("woff2");unicode-range:u+0301,u+0400-045f,u+0490-0491,u+04b0-04b1,u+2116}@font-face{font-family:__Inter_12bbc4;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/fd4db3eb5472fc27-s.woff2) format("woff2");unicode-range:u+1f??}@font-face{font-family:__Inter_12bbc4;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/51ed15f9841b9f9d-s.woff2) format("woff2");unicode-range:u+0370-0377,u+037a-037f,u+0384-038a,u+038c,u+038e-03a1,u+03a3-03ff}@font-face{font-family:__Inter_12bbc4;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/05a31a2ca4975f99-s.woff2) format("woff2");unicode-range:u+0102-0103,u+0110-0111,u+0128-0129,u+0168-0169,u+01a0-01a1,u+01af-01b0,u+0300-0301,u+0303-0304,u+0308-0309,u+0323,u+0329,u+1ea0-1ef9,u+20ab}@font-face{font-family:__Inter_12bbc4;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/d6b16ce4a6175f26-s.woff2) format("woff2");unicode-range:u+0100-02af,u+0304,u+0308,u+0329,u+1e00-1e9f,u+1ef2-1eff,u+2020,u+20a0-20ab,u+20ad-20c0,u+2113,u+2c60-2c7f,u+a720-a7ff}@font-face{font-family:__Inter_12bbc4;font-style:normal;font-weight:100 900;font-display:swap;src:url(/ui/_next/static/media/c9a5bc6a7c948fb0-s.p.woff2) format("woff2");unicode-range:u+00??,u+0131,u+0152-0153,u+02bb-02bc,u+02c6,u+02da,u+02dc,u+0304,u+0308,u+0329,u+2000-206f,u+2074,u+20ac,u+2122,u+2191,u+2193,u+2212,u+2215,u+feff,u+fffd}@font-face{font-family:__Inter_Fallback_12bbc4;src:local("Arial");ascent-override:90.20%;descent-override:22.48%;line-gap-override:0.00%;size-adjust:107.40%}.__className_12bbc4{font-family:__Inter_12bbc4,__Inter_Fallback_12bbc4;font-style:normal}
|
||||
|
||||
/*
|
||||
! tailwindcss v3.4.1 | MIT License | https://tailwindcss.com
|
||||
BIN
litellm/proxy/out/_next/static/media/05a31a2ca4975f99-s.woff2
Normal file
BIN
litellm/proxy/out/_next/static/media/05a31a2ca4975f99-s.woff2
Normal file
Binary file not shown.
BIN
litellm/proxy/out/_next/static/media/513657b02c5c193f-s.woff2
Normal file
BIN
litellm/proxy/out/_next/static/media/513657b02c5c193f-s.woff2
Normal file
Binary file not shown.
BIN
litellm/proxy/out/_next/static/media/51ed15f9841b9f9d-s.woff2
Normal file
BIN
litellm/proxy/out/_next/static/media/51ed15f9841b9f9d-s.woff2
Normal file
Binary file not shown.
BIN
litellm/proxy/out/_next/static/media/c9a5bc6a7c948fb0-s.p.woff2
Normal file
BIN
litellm/proxy/out/_next/static/media/c9a5bc6a7c948fb0-s.p.woff2
Normal file
Binary file not shown.
BIN
litellm/proxy/out/_next/static/media/d6b16ce4a6175f26-s.woff2
Normal file
BIN
litellm/proxy/out/_next/static/media/d6b16ce4a6175f26-s.woff2
Normal file
Binary file not shown.
BIN
litellm/proxy/out/_next/static/media/ec159349637c90ad-s.woff2
Normal file
BIN
litellm/proxy/out/_next/static/media/ec159349637c90ad-s.woff2
Normal file
Binary file not shown.
BIN
litellm/proxy/out/_next/static/media/fd4db3eb5472fc27-s.woff2
Normal file
BIN
litellm/proxy/out/_next/static/media/fd4db3eb5472fc27-s.woff2
Normal file
Binary file not shown.
|
Before Width: | Height: | Size: 15 KiB After Width: | Height: | Size: 15 KiB |
|
|
@ -1 +1 @@
|
|||
<!DOCTYPE html><html id="__next_error__"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="script" fetchPriority="low" href="/ui/_next/static/chunks/webpack-193a7eac80c8baba.js" crossorigin=""/><script src="/ui/_next/static/chunks/fd9d1056-f593049e31b05aeb.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/69-8316d07d1f41e39f.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/main-app-9b4fb13a7db53edf.js" async="" crossorigin=""></script><title>LiteLLM Dashboard</title><meta name="description" content="LiteLLM Proxy Admin UI"/><link rel="icon" href="/ui/favicon.ico" type="image/x-icon" sizes="16x16"/><meta name="next-size-adjust"/><script src="/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js" crossorigin="" noModule=""></script></head><body><script src="/ui/_next/static/chunks/webpack-193a7eac80c8baba.js" crossorigin="" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0]);self.__next_f.push([2,null])</script><script>self.__next_f.push([1,"1:HL[\"/ui/_next/static/media/a34f9d1faa5f3315-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n2:HL[\"/ui/_next/static/css/cd10067a0a3408b4.css\",\"style\",{\"crossOrigin\":\"\"}]\n0:\"$L3\"\n"])</script><script>self.__next_f.push([1,"4:I[47690,[],\"\"]\n6:I[77831,[],\"\"]\n7:I[48951,[\"665\",\"static/chunks/3014691f-b24e8254c7593934.js\",\"936\",\"static/chunks/2f6dbc85-cac2949a76539886.js\",\"505\",\"static/chunks/505-5ff3c318fddfa35c.js\",\"131\",\"static/chunks/131-cb6bfe24e23e121b.js\",\"684\",\"static/chunks/684-16b194c83a169f6d.js\",\"759\",\"static/chunks/759-c0083d8a782d300e.js\",\"777\",\"static/chunks/777-0a0bacbc160c02d3.js\",\"931\",\"static/chunks/app/page-913f3589403bc802.js\"],\"\"]\n8:I[5613,[],\"\"]\n9:I[31778,[],\"\"]\nb:I[48955,[],\"\"]\nc:[]\n"])</script><script>self.__next_f.push([1,"3:[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/ui/_next/static/css/cd10067a0a3408b4.css\",\"precedence\":\"next\",\"crossOrigin\":\"\"}]],[\"$\",\"$L4\",null,{\"buildId\":\"dWa6RZpZ5Z2Qhqv0Hff_m\",\"assetPrefix\":\"/ui\",\"initialCanonicalUrl\":\"/\",\"initialTree\":[\"\",{\"children\":[\"__PAGE__\",{}]},\"$undefined\",\"$undefined\",true],\"initialSeedData\":[\"\",{\"children\":[\"__PAGE__\",{},[\"$L5\",[\"$\",\"$L6\",null,{\"propsForComponent\":{\"params\":{}},\"Component\":\"$7\",\"isStaticGeneration\":true}],null]]},[null,[\"$\",\"html\",null,{\"lang\":\"en\",\"children\":[\"$\",\"body\",null,{\"className\":\"__className_86ef86\",\"children\":[\"$\",\"$L8\",null,{\"parallelRouterKey\":\"children\",\"segmentPath\":[\"children\"],\"loading\":\"$undefined\",\"loadingStyles\":\"$undefined\",\"loadingScripts\":\"$undefined\",\"hasLoading\":false,\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L9\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"title\",null,{\"children\":\"404: This page could not be found.\"}],[\"$\",\"div\",null,{\"style\":{\"fontFamily\":\"system-ui,\\\"Segoe UI\\\",Roboto,Helvetica,Arial,sans-serif,\\\"Apple Color Emoji\\\",\\\"Segoe UI Emoji\\\"\",\"height\":\"100vh\",\"textAlign\":\"center\",\"display\":\"flex\",\"flexDirection\":\"column\",\"alignItems\":\"center\",\"justifyContent\":\"center\"},\"children\":[\"$\",\"div\",null,{\"children\":[[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}\"}}],[\"$\",\"h1\",null,{\"className\":\"next-error-h1\",\"style\":{\"display\":\"inline-block\",\"margin\":\"0 20px 0 0\",\"padding\":\"0 23px 0 0\",\"fontSize\":24,\"fontWeight\":500,\"verticalAlign\":\"top\",\"lineHeight\":\"49px\"},\"children\":\"404\"}],[\"$\",\"div\",null,{\"style\":{\"display\":\"inline-block\"},\"children\":[\"$\",\"h2\",null,{\"style\":{\"fontSize\":14,\"fontWeight\":400,\"lineHeight\":\"49px\",\"margin\":0},\"children\":\"This page could not be found.\"}]}]]}]}]],\"notFoundStyles\":[],\"styles\":null}]}]}],null]],\"initialHead\":[false,\"$La\"],\"globalErrorComponent\":\"$b\",\"missingSlots\":\"$Wc\"}]]\n"])</script><script>self.__next_f.push([1,"a:[[\"$\",\"meta\",\"0\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"1\",{\"charSet\":\"utf-8\"}],[\"$\",\"title\",\"2\",{\"children\":\"LiteLLM Dashboard\"}],[\"$\",\"meta\",\"3\",{\"name\":\"description\",\"content\":\"LiteLLM Proxy Admin UI\"}],[\"$\",\"link\",\"4\",{\"rel\":\"icon\",\"href\":\"/ui/favicon.ico\",\"type\":\"image/x-icon\",\"sizes\":\"16x16\"}],[\"$\",\"meta\",\"5\",{\"name\":\"next-size-adjust\"}]]\n5:null\n"])</script><script>self.__next_f.push([1,""])</script></body></html>
|
||||
<!DOCTYPE html><html id="__next_error__"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="script" fetchPriority="low" href="/ui/_next/static/chunks/webpack-2d07f7d2618f9dfc.js" crossorigin=""/><script src="/ui/_next/static/chunks/fd9d1056-f593049e31b05aeb.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/69-8316d07d1f41e39f.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/main-app-096338c8e1915716.js" async="" crossorigin=""></script><title>LiteLLM Dashboard</title><meta name="description" content="LiteLLM Proxy Admin UI"/><link rel="icon" href="/ui/favicon.ico" type="image/x-icon" sizes="16x16"/><meta name="next-size-adjust"/><script src="/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js" crossorigin="" noModule=""></script></head><body><script src="/ui/_next/static/chunks/webpack-2d07f7d2618f9dfc.js" crossorigin="" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0]);self.__next_f.push([2,null])</script><script>self.__next_f.push([1,"1:HL[\"/ui/_next/static/media/c9a5bc6a7c948fb0-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n2:HL[\"/ui/_next/static/css/051d7321f11572d4.css\",\"style\",{\"crossOrigin\":\"\"}]\n0:\"$L3\"\n"])</script><script>self.__next_f.push([1,"4:I[47690,[],\"\"]\n6:I[77831,[],\"\"]\n7:I[26520,[\"665\",\"static/chunks/3014691f-b24e8254c7593934.js\",\"936\",\"static/chunks/2f6dbc85-cac2949a76539886.js\",\"505\",\"static/chunks/505-5ff3c318fddfa35c.js\",\"131\",\"static/chunks/131-cb6bfe24e23e121b.js\",\"684\",\"static/chunks/684-16b194c83a169f6d.js\",\"605\",\"static/chunks/605-8e4b96f972af8eaf.js\",\"777\",\"static/chunks/777-50d836152fad178b.js\",\"931\",\"static/chunks/app/page-5b7e51de07f1b89a.js\"],\"\"]\n8:I[5613,[],\"\"]\n9:I[31778,[],\"\"]\nb:I[48955,[],\"\"]\nc:[]\n"])</script><script>self.__next_f.push([1,"3:[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/ui/_next/static/css/051d7321f11572d4.css\",\"precedence\":\"next\",\"crossOrigin\":\"\"}]],[\"$\",\"$L4\",null,{\"buildId\":\"bNZcj3BOVnvWu7auSxFn-\",\"assetPrefix\":\"/ui\",\"initialCanonicalUrl\":\"/\",\"initialTree\":[\"\",{\"children\":[\"__PAGE__\",{}]},\"$undefined\",\"$undefined\",true],\"initialSeedData\":[\"\",{\"children\":[\"__PAGE__\",{},[\"$L5\",[\"$\",\"$L6\",null,{\"propsForComponent\":{\"params\":{}},\"Component\":\"$7\",\"isStaticGeneration\":true}],null]]},[null,[\"$\",\"html\",null,{\"lang\":\"en\",\"children\":[\"$\",\"body\",null,{\"className\":\"__className_12bbc4\",\"children\":[\"$\",\"$L8\",null,{\"parallelRouterKey\":\"children\",\"segmentPath\":[\"children\"],\"loading\":\"$undefined\",\"loadingStyles\":\"$undefined\",\"loadingScripts\":\"$undefined\",\"hasLoading\":false,\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L9\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"title\",null,{\"children\":\"404: This page could not be found.\"}],[\"$\",\"div\",null,{\"style\":{\"fontFamily\":\"system-ui,\\\"Segoe UI\\\",Roboto,Helvetica,Arial,sans-serif,\\\"Apple Color Emoji\\\",\\\"Segoe UI Emoji\\\"\",\"height\":\"100vh\",\"textAlign\":\"center\",\"display\":\"flex\",\"flexDirection\":\"column\",\"alignItems\":\"center\",\"justifyContent\":\"center\"},\"children\":[\"$\",\"div\",null,{\"children\":[[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}\"}}],[\"$\",\"h1\",null,{\"className\":\"next-error-h1\",\"style\":{\"display\":\"inline-block\",\"margin\":\"0 20px 0 0\",\"padding\":\"0 23px 0 0\",\"fontSize\":24,\"fontWeight\":500,\"verticalAlign\":\"top\",\"lineHeight\":\"49px\"},\"children\":\"404\"}],[\"$\",\"div\",null,{\"style\":{\"display\":\"inline-block\"},\"children\":[\"$\",\"h2\",null,{\"style\":{\"fontSize\":14,\"fontWeight\":400,\"lineHeight\":\"49px\",\"margin\":0},\"children\":\"This page could not be found.\"}]}]]}]}]],\"notFoundStyles\":[],\"styles\":null}]}]}],null]],\"initialHead\":[false,\"$La\"],\"globalErrorComponent\":\"$b\",\"missingSlots\":\"$Wc\"}]]\n"])</script><script>self.__next_f.push([1,"a:[[\"$\",\"meta\",\"0\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"1\",{\"charSet\":\"utf-8\"}],[\"$\",\"title\",\"2\",{\"children\":\"LiteLLM Dashboard\"}],[\"$\",\"meta\",\"3\",{\"name\":\"description\",\"content\":\"LiteLLM Proxy Admin UI\"}],[\"$\",\"link\",\"4\",{\"rel\":\"icon\",\"href\":\"/ui/favicon.ico\",\"type\":\"image/x-icon\",\"sizes\":\"16x16\"}],[\"$\",\"meta\",\"5\",{\"name\":\"next-size-adjust\"}]]\n5:null\n"])</script><script>self.__next_f.push([1,""])</script></body></html>
|
||||
|
|
@ -1,7 +1,7 @@
|
|||
2:I[77831,[],""]
|
||||
3:I[48951,["665","static/chunks/3014691f-b24e8254c7593934.js","936","static/chunks/2f6dbc85-cac2949a76539886.js","505","static/chunks/505-5ff3c318fddfa35c.js","131","static/chunks/131-cb6bfe24e23e121b.js","684","static/chunks/684-16b194c83a169f6d.js","759","static/chunks/759-c0083d8a782d300e.js","777","static/chunks/777-0a0bacbc160c02d3.js","931","static/chunks/app/page-913f3589403bc802.js"],""]
|
||||
3:I[26520,["665","static/chunks/3014691f-b24e8254c7593934.js","936","static/chunks/2f6dbc85-cac2949a76539886.js","505","static/chunks/505-5ff3c318fddfa35c.js","131","static/chunks/131-cb6bfe24e23e121b.js","684","static/chunks/684-16b194c83a169f6d.js","605","static/chunks/605-8e4b96f972af8eaf.js","777","static/chunks/777-50d836152fad178b.js","931","static/chunks/app/page-5b7e51de07f1b89a.js"],""]
|
||||
4:I[5613,[],""]
|
||||
5:I[31778,[],""]
|
||||
0:["dWa6RZpZ5Z2Qhqv0Hff_m",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_86ef86","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/cd10067a0a3408b4.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
|
||||
0:["bNZcj3BOVnvWu7auSxFn-",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_12bbc4","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/051d7321f11572d4.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
|
||||
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/ui/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","meta","5",{"name":"next-size-adjust"}]]
|
||||
1:null
|
||||
1
litellm/proxy/out/model_hub.html
Normal file
1
litellm/proxy/out/model_hub.html
Normal file
File diff suppressed because one or more lines are too long
|
|
@ -1,7 +1,7 @@
|
|||
2:I[77831,[],""]
|
||||
3:I[87494,["505","static/chunks/505-5ff3c318fddfa35c.js","131","static/chunks/131-cb6bfe24e23e121b.js","777","static/chunks/777-0a0bacbc160c02d3.js","418","static/chunks/app/model_hub/page-370c82f0dada594a.js"],""]
|
||||
3:I[87494,["505","static/chunks/505-5ff3c318fddfa35c.js","131","static/chunks/131-cb6bfe24e23e121b.js","777","static/chunks/777-50d836152fad178b.js","418","static/chunks/app/model_hub/page-39740ed413adc0ec.js"],""]
|
||||
4:I[5613,[],""]
|
||||
5:I[31778,[],""]
|
||||
0:["dWa6RZpZ5Z2Qhqv0Hff_m",[[["",{"children":["model_hub",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub","children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined","styles":null}]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_86ef86","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/cd10067a0a3408b4.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
|
||||
0:["bNZcj3BOVnvWu7auSxFn-",[[["",{"children":["model_hub",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub","children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined","styles":null}]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_12bbc4","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/051d7321f11572d4.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
|
||||
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/ui/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","meta","5",{"name":"next-size-adjust"}]]
|
||||
1:null
|
||||
|
Before Width: | Height: | Size: 1.3 KiB After Width: | Height: | Size: 1.3 KiB |
1
litellm/proxy/out/onboarding.html
Normal file
1
litellm/proxy/out/onboarding.html
Normal file
File diff suppressed because one or more lines are too long
|
|
@ -1,7 +1,7 @@
|
|||
2:I[77831,[],""]
|
||||
3:I[667,["665","static/chunks/3014691f-b24e8254c7593934.js","505","static/chunks/505-5ff3c318fddfa35c.js","684","static/chunks/684-16b194c83a169f6d.js","777","static/chunks/777-0a0bacbc160c02d3.js","461","static/chunks/app/onboarding/page-a71b2c4c6be5c272.js"],""]
|
||||
3:I[667,["665","static/chunks/3014691f-b24e8254c7593934.js","505","static/chunks/505-5ff3c318fddfa35c.js","684","static/chunks/684-16b194c83a169f6d.js","777","static/chunks/777-50d836152fad178b.js","461","static/chunks/app/onboarding/page-cd0662400289603c.js"],""]
|
||||
4:I[5613,[],""]
|
||||
5:I[31778,[],""]
|
||||
0:["dWa6RZpZ5Z2Qhqv0Hff_m",[[["",{"children":["onboarding",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["onboarding",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","onboarding","children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined","styles":null}]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_86ef86","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/cd10067a0a3408b4.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
|
||||
0:["bNZcj3BOVnvWu7auSxFn-",[[["",{"children":["onboarding",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["onboarding",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","onboarding","children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined","styles":null}]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_12bbc4","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/051d7321f11572d4.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
|
||||
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/ui/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","meta","5",{"name":"next-size-adjust"}]]
|
||||
1:null
|
||||
|
Before Width: | Height: | Size: 629 B After Width: | Height: | Size: 629 B |
|
|
@ -20,9 +20,18 @@ from fastapi.responses import StreamingResponse
|
|||
import litellm
|
||||
from litellm._logging import verbose_proxy_logger
|
||||
from litellm.integrations.custom_logger import CustomLogger
|
||||
from litellm.proxy._types import ProxyException, UserAPIKeyAuth
|
||||
from litellm.proxy._types import (
|
||||
ConfigFieldInfo,
|
||||
ConfigFieldUpdate,
|
||||
PassThroughEndpointResponse,
|
||||
PassThroughGenericEndpoint,
|
||||
ProxyException,
|
||||
UserAPIKeyAuth,
|
||||
)
|
||||
from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
async def set_env_variables_in_header(custom_headers: dict):
|
||||
"""
|
||||
|
|
@ -476,3 +485,188 @@ async def initialize_pass_through_endpoints(pass_through_endpoints: list):
|
|||
)
|
||||
|
||||
verbose_proxy_logger.debug("Added new pass through endpoint: %s", _path)
|
||||
|
||||
|
||||
@router.get(
|
||||
"/config/pass_through_endpoint",
|
||||
tags=["Internal User management"],
|
||||
dependencies=[Depends(user_api_key_auth)],
|
||||
response_model=PassThroughEndpointResponse,
|
||||
)
|
||||
async def get_pass_through_endpoints(
|
||||
endpoint_id: Optional[str] = None,
|
||||
user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
|
||||
):
|
||||
"""
|
||||
GET configured pass through endpoint.
|
||||
|
||||
If no endpoint_id given, return all configured endpoints.
|
||||
"""
|
||||
from litellm.proxy.proxy_server import get_config_general_settings
|
||||
|
||||
## Get existing pass-through endpoint field value
|
||||
try:
|
||||
response: ConfigFieldInfo = await get_config_general_settings(
|
||||
field_name="pass_through_endpoints", user_api_key_dict=user_api_key_dict
|
||||
)
|
||||
except Exception:
|
||||
return PassThroughEndpointResponse(endpoints=[])
|
||||
|
||||
pass_through_endpoint_data: Optional[List] = response.field_value
|
||||
if pass_through_endpoint_data is None:
|
||||
return PassThroughEndpointResponse(endpoints=[])
|
||||
|
||||
returned_endpoints = []
|
||||
if endpoint_id is None:
|
||||
for endpoint in pass_through_endpoint_data:
|
||||
if isinstance(endpoint, dict):
|
||||
returned_endpoints.append(PassThroughGenericEndpoint(**endpoint))
|
||||
elif isinstance(endpoint, PassThroughGenericEndpoint):
|
||||
returned_endpoints.append(endpoint)
|
||||
elif endpoint_id is not None:
|
||||
for endpoint in pass_through_endpoint_data:
|
||||
_endpoint: Optional[PassThroughGenericEndpoint] = None
|
||||
if isinstance(endpoint, dict):
|
||||
_endpoint = PassThroughGenericEndpoint(**endpoint)
|
||||
elif isinstance(endpoint, PassThroughGenericEndpoint):
|
||||
_endpoint = endpoint
|
||||
|
||||
if _endpoint is not None and _endpoint.path == endpoint_id:
|
||||
returned_endpoints.append(_endpoint)
|
||||
|
||||
return PassThroughEndpointResponse(endpoints=returned_endpoints)
|
||||
|
||||
|
||||
@router.post(
|
||||
"/config/pass_through_endpoint/{endpoint_id}",
|
||||
tags=["Internal User management"],
|
||||
dependencies=[Depends(user_api_key_auth)],
|
||||
)
|
||||
async def update_pass_through_endpoints(request: Request, endpoint_id: str):
|
||||
"""
|
||||
Update a pass-through endpoint
|
||||
"""
|
||||
pass
|
||||
|
||||
|
||||
@router.post(
|
||||
"/config/pass_through_endpoint",
|
||||
tags=["Internal User management"],
|
||||
dependencies=[Depends(user_api_key_auth)],
|
||||
)
|
||||
async def create_pass_through_endpoints(
|
||||
data: PassThroughGenericEndpoint,
|
||||
user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
|
||||
):
|
||||
"""
|
||||
Create new pass-through endpoint
|
||||
"""
|
||||
from litellm.proxy.proxy_server import (
|
||||
get_config_general_settings,
|
||||
update_config_general_settings,
|
||||
)
|
||||
|
||||
## Get existing pass-through endpoint field value
|
||||
|
||||
try:
|
||||
response: ConfigFieldInfo = await get_config_general_settings(
|
||||
field_name="pass_through_endpoints", user_api_key_dict=user_api_key_dict
|
||||
)
|
||||
except Exception:
|
||||
response = ConfigFieldInfo(
|
||||
field_name="pass_through_endpoints", field_value=None
|
||||
)
|
||||
|
||||
## Update field with new endpoint
|
||||
data_dict = data.model_dump()
|
||||
if response.field_value is None:
|
||||
response.field_value = [data_dict]
|
||||
elif isinstance(response.field_value, List):
|
||||
response.field_value.append(data_dict)
|
||||
|
||||
## Update db
|
||||
updated_data = ConfigFieldUpdate(
|
||||
field_name="pass_through_endpoints",
|
||||
field_value=response.field_value,
|
||||
config_type="general_settings",
|
||||
)
|
||||
await update_config_general_settings(
|
||||
data=updated_data, user_api_key_dict=user_api_key_dict
|
||||
)
|
||||
|
||||
|
||||
@router.delete(
|
||||
"/config/pass_through_endpoint",
|
||||
tags=["Internal User management"],
|
||||
dependencies=[Depends(user_api_key_auth)],
|
||||
response_model=PassThroughEndpointResponse,
|
||||
)
|
||||
async def delete_pass_through_endpoints(
|
||||
endpoint_id: str,
|
||||
user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth),
|
||||
):
|
||||
"""
|
||||
Delete a pass-through endpoint
|
||||
|
||||
Returns - the deleted endpoint
|
||||
"""
|
||||
from litellm.proxy.proxy_server import (
|
||||
get_config_general_settings,
|
||||
update_config_general_settings,
|
||||
)
|
||||
|
||||
## Get existing pass-through endpoint field value
|
||||
|
||||
try:
|
||||
response: ConfigFieldInfo = await get_config_general_settings(
|
||||
field_name="pass_through_endpoints", user_api_key_dict=user_api_key_dict
|
||||
)
|
||||
except Exception:
|
||||
response = ConfigFieldInfo(
|
||||
field_name="pass_through_endpoints", field_value=None
|
||||
)
|
||||
|
||||
## Update field by removing endpoint
|
||||
pass_through_endpoint_data: Optional[List] = response.field_value
|
||||
response_obj: Optional[PassThroughGenericEndpoint] = None
|
||||
if response.field_value is None or pass_through_endpoint_data is None:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail={"error": "There are no pass-through endpoints setup."},
|
||||
)
|
||||
elif isinstance(response.field_value, List):
|
||||
invalid_idx: Optional[int] = None
|
||||
for idx, endpoint in enumerate(pass_through_endpoint_data):
|
||||
_endpoint: Optional[PassThroughGenericEndpoint] = None
|
||||
if isinstance(endpoint, dict):
|
||||
_endpoint = PassThroughGenericEndpoint(**endpoint)
|
||||
elif isinstance(endpoint, PassThroughGenericEndpoint):
|
||||
_endpoint = endpoint
|
||||
|
||||
if _endpoint is not None and _endpoint.path == endpoint_id:
|
||||
invalid_idx = idx
|
||||
response_obj = _endpoint
|
||||
|
||||
if invalid_idx is not None:
|
||||
pass_through_endpoint_data.pop(invalid_idx)
|
||||
|
||||
## Update db
|
||||
updated_data = ConfigFieldUpdate(
|
||||
field_name="pass_through_endpoints",
|
||||
field_value=pass_through_endpoint_data,
|
||||
config_type="general_settings",
|
||||
)
|
||||
await update_config_general_settings(
|
||||
data=updated_data, user_api_key_dict=user_api_key_dict
|
||||
)
|
||||
|
||||
if response_obj is None:
|
||||
raise HTTPException(
|
||||
status_code=400,
|
||||
detail={
|
||||
"error": "Endpoint={} was not found in pass-through endpoint list.".format(
|
||||
endpoint_id
|
||||
)
|
||||
},
|
||||
)
|
||||
return PassThroughEndpointResponse(endpoints=[response_obj])
|
||||
|
|
|
|||
|
|
@ -19,6 +19,9 @@ model_list:
|
|||
litellm_params:
|
||||
model: mistral/mistral-small-latest
|
||||
api_key: "os.environ/MISTRAL_API_KEY"
|
||||
- model_name: bedrock-anthropic
|
||||
litellm_params:
|
||||
model: bedrock/anthropic.claude-3-sonnet-20240229-v1:0
|
||||
- model_name: gemini-1.5-pro-001
|
||||
litellm_params:
|
||||
model: vertex_ai_beta/gemini-1.5-pro-001
|
||||
|
|
@ -40,3 +43,6 @@ general_settings:
|
|||
litellm_settings:
|
||||
fallbacks: [{"gemini-1.5-pro-001": ["gpt-4o"]}]
|
||||
callbacks: ["gcs_bucket"]
|
||||
success_callback: ["langfuse"]
|
||||
langfuse_default_tags: ["cache_hit", "cache_key", "user_api_key_alias", "user_api_key_team_alias"]
|
||||
cache: True
|
||||
|
|
|
|||
|
|
@ -13,7 +13,15 @@ import traceback
|
|||
import uuid
|
||||
import warnings
|
||||
from datetime import datetime, timedelta
|
||||
from typing import TYPE_CHECKING, Any, List, Optional
|
||||
from typing import (
|
||||
TYPE_CHECKING,
|
||||
Any,
|
||||
List,
|
||||
Optional,
|
||||
get_args,
|
||||
get_origin,
|
||||
get_type_hints,
|
||||
)
|
||||
|
||||
import requests
|
||||
|
||||
|
|
@ -187,6 +195,11 @@ from litellm.proxy.openai_files_endpoints.files_endpoints import set_files_confi
|
|||
from litellm.proxy.pass_through_endpoints.pass_through_endpoints import (
|
||||
initialize_pass_through_endpoints,
|
||||
)
|
||||
from litellm.proxy.pass_through_endpoints.pass_through_endpoints import (
|
||||
router as pass_through_router,
|
||||
)
|
||||
from litellm.proxy.route_llm_request import route_request
|
||||
|
||||
from litellm.proxy.secret_managers.aws_secret_manager import (
|
||||
load_aws_kms,
|
||||
load_aws_secret_manager,
|
||||
|
|
@ -549,6 +562,37 @@ async def check_request_disconnection(request: Request, llm_api_call_task):
|
|||
)
|
||||
|
||||
|
||||
def _resolve_typed_dict_type(typ):
|
||||
"""Resolve the actual TypedDict class from a potentially wrapped type."""
|
||||
from typing_extensions import _TypedDictMeta # type: ignore
|
||||
|
||||
origin = get_origin(typ)
|
||||
if origin is Union: # Check if it's a Union (like Optional)
|
||||
for arg in get_args(typ):
|
||||
if isinstance(arg, _TypedDictMeta):
|
||||
return arg
|
||||
elif isinstance(typ, type) and isinstance(typ, dict):
|
||||
return typ
|
||||
return None
|
||||
|
||||
|
||||
def _resolve_pydantic_type(typ) -> List:
|
||||
"""Resolve the actual TypedDict class from a potentially wrapped type."""
|
||||
origin = get_origin(typ)
|
||||
typs = []
|
||||
if origin is Union: # Check if it's a Union (like Optional)
|
||||
for arg in get_args(typ):
|
||||
if (
|
||||
arg is not None
|
||||
and not isinstance(arg, type(None))
|
||||
and "NoneType" not in str(arg)
|
||||
):
|
||||
typs.append(arg)
|
||||
elif isinstance(typ, type) and isinstance(typ, BaseModel):
|
||||
return [typ]
|
||||
return typs
|
||||
|
||||
|
||||
def prisma_setup(database_url: Optional[str]):
|
||||
global prisma_client, proxy_logging_obj, user_api_key_cache
|
||||
|
||||
|
|
@ -2191,6 +2235,15 @@ class ProxyConfig:
|
|||
alerting_args=general_settings["alerting_args"],
|
||||
)
|
||||
|
||||
## PASS-THROUGH ENDPOINTS ##
|
||||
if "pass_through_endpoints" in _general_settings:
|
||||
general_settings["pass_through_endpoints"] = _general_settings[
|
||||
"pass_through_endpoints"
|
||||
]
|
||||
await initialize_pass_through_endpoints(
|
||||
pass_through_endpoints=general_settings["pass_through_endpoints"]
|
||||
)
|
||||
|
||||
async def add_deployment(
|
||||
self,
|
||||
prisma_client: PrismaClient,
|
||||
|
|
@ -3006,68 +3059,13 @@ async def chat_completion(
|
|||
|
||||
### ROUTE THE REQUEST ###
|
||||
# Do not change this - it should be a constant time fetch - ALWAYS
|
||||
router_model_names = llm_router.model_names if llm_router is not None else []
|
||||
# skip router if user passed their key
|
||||
if "api_key" in data:
|
||||
tasks.append(litellm.acompletion(**data))
|
||||
elif "," in data["model"] and llm_router is not None:
|
||||
if (
|
||||
data.get("fastest_response", None) is not None
|
||||
and data["fastest_response"] == True
|
||||
):
|
||||
tasks.append(llm_router.abatch_completion_fastest_response(**data))
|
||||
else:
|
||||
_models_csv_string = data.pop("model")
|
||||
_models = [model.strip() for model in _models_csv_string.split(",")]
|
||||
tasks.append(llm_router.abatch_completion(models=_models, **data))
|
||||
elif "user_config" in data:
|
||||
# initialize a new router instance. make request using this Router
|
||||
router_config = data.pop("user_config")
|
||||
user_router = litellm.Router(**router_config)
|
||||
tasks.append(user_router.acompletion(**data))
|
||||
elif (
|
||||
llm_router is not None and data["model"] in router_model_names
|
||||
): # model in router model list
|
||||
tasks.append(llm_router.acompletion(**data))
|
||||
elif (
|
||||
llm_router is not None and data["model"] in llm_router.get_model_ids()
|
||||
): # model in router model list
|
||||
tasks.append(llm_router.acompletion(**data))
|
||||
elif (
|
||||
llm_router is not None
|
||||
and llm_router.model_group_alias is not None
|
||||
and data["model"] in llm_router.model_group_alias
|
||||
): # model set in model_group_alias
|
||||
tasks.append(llm_router.acompletion(**data))
|
||||
elif (
|
||||
llm_router is not None and data["model"] in llm_router.deployment_names
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
tasks.append(llm_router.acompletion(**data, specific_deployment=True))
|
||||
elif (
|
||||
llm_router is not None
|
||||
and data["model"] not in router_model_names
|
||||
and llm_router.router_general_settings.pass_through_all_models is True
|
||||
):
|
||||
tasks.append(litellm.acompletion(**data))
|
||||
elif (
|
||||
llm_router is not None
|
||||
and data["model"] not in router_model_names
|
||||
and (
|
||||
llm_router.default_deployment is not None
|
||||
or len(llm_router.provider_default_deployments) > 0
|
||||
)
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
tasks.append(llm_router.acompletion(**data))
|
||||
elif user_model is not None: # `litellm --model <your-model-name>`
|
||||
tasks.append(litellm.acompletion(**data))
|
||||
else:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"error": "chat_completion: Invalid model name passed in model="
|
||||
+ data.get("model", "")
|
||||
},
|
||||
)
|
||||
llm_call = await route_request(
|
||||
data=data,
|
||||
route_type="acompletion",
|
||||
llm_router=llm_router,
|
||||
user_model=user_model,
|
||||
)
|
||||
tasks.append(llm_call)
|
||||
|
||||
# wait for call to end
|
||||
llm_responses = asyncio.gather(
|
||||
|
|
@ -3290,58 +3288,15 @@ async def completion(
|
|||
)
|
||||
|
||||
### ROUTE THE REQUESTs ###
|
||||
router_model_names = llm_router.model_names if llm_router is not None else []
|
||||
# skip router if user passed their key
|
||||
if "api_key" in data:
|
||||
llm_response = asyncio.create_task(litellm.atext_completion(**data))
|
||||
elif (
|
||||
llm_router is not None and data["model"] in router_model_names
|
||||
): # model in router model list
|
||||
llm_response = asyncio.create_task(llm_router.atext_completion(**data))
|
||||
elif (
|
||||
llm_router is not None
|
||||
and llm_router.model_group_alias is not None
|
||||
and data["model"] in llm_router.model_group_alias
|
||||
): # model set in model_group_alias
|
||||
llm_response = asyncio.create_task(llm_router.atext_completion(**data))
|
||||
elif (
|
||||
llm_router is not None and data["model"] in llm_router.deployment_names
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
llm_response = asyncio.create_task(
|
||||
llm_router.atext_completion(**data, specific_deployment=True)
|
||||
)
|
||||
elif (
|
||||
llm_router is not None and data["model"] in llm_router.get_model_ids()
|
||||
): # model in router model list
|
||||
llm_response = asyncio.create_task(llm_router.atext_completion(**data))
|
||||
elif (
|
||||
llm_router is not None
|
||||
and data["model"] not in router_model_names
|
||||
and llm_router.router_general_settings.pass_through_all_models is True
|
||||
):
|
||||
llm_response = asyncio.create_task(litellm.atext_completion(**data))
|
||||
elif (
|
||||
llm_router is not None
|
||||
and data["model"] not in router_model_names
|
||||
and (
|
||||
llm_router.default_deployment is not None
|
||||
or len(llm_router.provider_default_deployments) > 0
|
||||
)
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
llm_response = asyncio.create_task(llm_router.atext_completion(**data))
|
||||
elif user_model is not None: # `litellm --model <your-model-name>`
|
||||
llm_response = asyncio.create_task(litellm.atext_completion(**data))
|
||||
else:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"error": "completion: Invalid model name passed in model="
|
||||
+ data.get("model", "")
|
||||
},
|
||||
)
|
||||
llm_call = await route_request(
|
||||
data=data,
|
||||
route_type="atext_completion",
|
||||
llm_router=llm_router,
|
||||
user_model=user_model,
|
||||
)
|
||||
|
||||
# Await the llm_response task
|
||||
response = await llm_response
|
||||
response = await llm_call
|
||||
|
||||
hidden_params = getattr(response, "_hidden_params", {}) or {}
|
||||
model_id = hidden_params.get("model_id", None) or ""
|
||||
|
|
@ -3555,59 +3510,13 @@ async def embeddings(
|
|||
)
|
||||
|
||||
## ROUTE TO CORRECT ENDPOINT ##
|
||||
# skip router if user passed their key
|
||||
if "api_key" in data:
|
||||
tasks.append(litellm.aembedding(**data))
|
||||
elif "user_config" in data:
|
||||
# initialize a new router instance. make request using this Router
|
||||
router_config = data.pop("user_config")
|
||||
user_router = litellm.Router(**router_config)
|
||||
tasks.append(user_router.aembedding(**data))
|
||||
elif (
|
||||
llm_router is not None and data["model"] in router_model_names
|
||||
): # model in router model list
|
||||
tasks.append(llm_router.aembedding(**data))
|
||||
elif (
|
||||
llm_router is not None
|
||||
and llm_router.model_group_alias is not None
|
||||
and data["model"] in llm_router.model_group_alias
|
||||
): # model set in model_group_alias
|
||||
tasks.append(
|
||||
llm_router.aembedding(**data)
|
||||
) # ensure this goes the llm_router, router will do the correct alias mapping
|
||||
elif (
|
||||
llm_router is not None and data["model"] in llm_router.deployment_names
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
tasks.append(llm_router.aembedding(**data, specific_deployment=True))
|
||||
elif (
|
||||
llm_router is not None and data["model"] in llm_router.get_model_ids()
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
tasks.append(llm_router.aembedding(**data))
|
||||
elif (
|
||||
llm_router is not None
|
||||
and data["model"] not in router_model_names
|
||||
and llm_router.router_general_settings.pass_through_all_models is True
|
||||
):
|
||||
tasks.append(litellm.aembedding(**data))
|
||||
elif (
|
||||
llm_router is not None
|
||||
and data["model"] not in router_model_names
|
||||
and (
|
||||
llm_router.default_deployment is not None
|
||||
or len(llm_router.provider_default_deployments) > 0
|
||||
)
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
tasks.append(llm_router.aembedding(**data))
|
||||
elif user_model is not None: # `litellm --model <your-model-name>`
|
||||
tasks.append(litellm.aembedding(**data))
|
||||
else:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"error": "embeddings: Invalid model name passed in model="
|
||||
+ data.get("model", "")
|
||||
},
|
||||
)
|
||||
llm_call = await route_request(
|
||||
data=data,
|
||||
route_type="aembedding",
|
||||
llm_router=llm_router,
|
||||
user_model=user_model,
|
||||
)
|
||||
tasks.append(llm_call)
|
||||
|
||||
# wait for call to end
|
||||
llm_responses = asyncio.gather(
|
||||
|
|
@ -3738,46 +3647,13 @@ async def image_generation(
|
|||
)
|
||||
|
||||
## ROUTE TO CORRECT ENDPOINT ##
|
||||
# skip router if user passed their key
|
||||
if "api_key" in data:
|
||||
response = await litellm.aimage_generation(**data)
|
||||
elif (
|
||||
llm_router is not None and data["model"] in router_model_names
|
||||
): # model in router model list
|
||||
response = await llm_router.aimage_generation(**data)
|
||||
elif (
|
||||
llm_router is not None and data["model"] in llm_router.deployment_names
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
response = await llm_router.aimage_generation(
|
||||
**data, specific_deployment=True
|
||||
)
|
||||
elif (
|
||||
llm_router is not None
|
||||
and llm_router.model_group_alias is not None
|
||||
and data["model"] in llm_router.model_group_alias
|
||||
): # model set in model_group_alias
|
||||
response = await llm_router.aimage_generation(
|
||||
**data
|
||||
) # ensure this goes the llm_router, router will do the correct alias mapping
|
||||
elif (
|
||||
llm_router is not None
|
||||
and data["model"] not in router_model_names
|
||||
and (
|
||||
llm_router.default_deployment is not None
|
||||
or len(llm_router.provider_default_deployments) > 0
|
||||
)
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
response = await llm_router.aimage_generation(**data)
|
||||
elif user_model is not None: # `litellm --model <your-model-name>`
|
||||
response = await litellm.aimage_generation(**data)
|
||||
else:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"error": "image_generation: Invalid model name passed in model="
|
||||
+ data.get("model", "")
|
||||
},
|
||||
)
|
||||
llm_call = await route_request(
|
||||
data=data,
|
||||
route_type="aimage_generation",
|
||||
llm_router=llm_router,
|
||||
user_model=user_model,
|
||||
)
|
||||
response = await llm_call
|
||||
|
||||
### ALERTING ###
|
||||
asyncio.create_task(
|
||||
|
|
@ -3885,44 +3761,13 @@ async def audio_speech(
|
|||
)
|
||||
|
||||
## ROUTE TO CORRECT ENDPOINT ##
|
||||
# skip router if user passed their key
|
||||
if "api_key" in data:
|
||||
response = await litellm.aspeech(**data)
|
||||
elif (
|
||||
llm_router is not None and data["model"] in router_model_names
|
||||
): # model in router model list
|
||||
response = await llm_router.aspeech(**data)
|
||||
elif (
|
||||
llm_router is not None and data["model"] in llm_router.deployment_names
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
response = await llm_router.aspeech(**data, specific_deployment=True)
|
||||
elif (
|
||||
llm_router is not None
|
||||
and llm_router.model_group_alias is not None
|
||||
and data["model"] in llm_router.model_group_alias
|
||||
): # model set in model_group_alias
|
||||
response = await llm_router.aspeech(
|
||||
**data
|
||||
) # ensure this goes the llm_router, router will do the correct alias mapping
|
||||
elif (
|
||||
llm_router is not None
|
||||
and data["model"] not in router_model_names
|
||||
and (
|
||||
llm_router.default_deployment is not None
|
||||
or len(llm_router.provider_default_deployments) > 0
|
||||
)
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
response = await llm_router.aspeech(**data)
|
||||
elif user_model is not None: # `litellm --model <your-model-name>`
|
||||
response = await litellm.aspeech(**data)
|
||||
else:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"error": "audio_speech: Invalid model name passed in model="
|
||||
+ data.get("model", "")
|
||||
},
|
||||
)
|
||||
llm_call = await route_request(
|
||||
data=data,
|
||||
route_type="aspeech",
|
||||
llm_router=llm_router,
|
||||
user_model=user_model,
|
||||
)
|
||||
response = await llm_call
|
||||
|
||||
### ALERTING ###
|
||||
asyncio.create_task(
|
||||
|
|
@ -4055,47 +3900,13 @@ async def audio_transcriptions(
|
|||
)
|
||||
|
||||
## ROUTE TO CORRECT ENDPOINT ##
|
||||
# skip router if user passed their key
|
||||
if "api_key" in data:
|
||||
response = await litellm.atranscription(**data)
|
||||
elif (
|
||||
llm_router is not None and data["model"] in router_model_names
|
||||
): # model in router model list
|
||||
response = await llm_router.atranscription(**data)
|
||||
|
||||
elif (
|
||||
llm_router is not None and data["model"] in llm_router.deployment_names
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
response = await llm_router.atranscription(
|
||||
**data, specific_deployment=True
|
||||
)
|
||||
elif (
|
||||
llm_router is not None
|
||||
and llm_router.model_group_alias is not None
|
||||
and data["model"] in llm_router.model_group_alias
|
||||
): # model set in model_group_alias
|
||||
response = await llm_router.atranscription(
|
||||
**data
|
||||
) # ensure this goes the llm_router, router will do the correct alias mapping
|
||||
elif (
|
||||
llm_router is not None
|
||||
and data["model"] not in router_model_names
|
||||
and (
|
||||
llm_router.default_deployment is not None
|
||||
or len(llm_router.provider_default_deployments) > 0
|
||||
)
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
response = await llm_router.atranscription(**data)
|
||||
elif user_model is not None: # `litellm --model <your-model-name>`
|
||||
response = await litellm.atranscription(**data)
|
||||
else:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"error": "audio_transcriptions: Invalid model name passed in model="
|
||||
+ data.get("model", "")
|
||||
},
|
||||
)
|
||||
llm_call = await route_request(
|
||||
data=data,
|
||||
route_type="atranscription",
|
||||
llm_router=llm_router,
|
||||
user_model=user_model,
|
||||
)
|
||||
response = await llm_call
|
||||
except Exception as e:
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
finally:
|
||||
|
|
@ -5311,40 +5122,13 @@ async def moderations(
|
|||
start_time = time.time()
|
||||
|
||||
## ROUTE TO CORRECT ENDPOINT ##
|
||||
# skip router if user passed their key
|
||||
if "api_key" in data:
|
||||
response = await litellm.amoderation(**data)
|
||||
elif (
|
||||
llm_router is not None and data.get("model") in router_model_names
|
||||
): # model in router model list
|
||||
response = await llm_router.amoderation(**data)
|
||||
elif (
|
||||
llm_router is not None and data.get("model") in llm_router.deployment_names
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
response = await llm_router.amoderation(**data, specific_deployment=True)
|
||||
elif (
|
||||
llm_router is not None
|
||||
and llm_router.model_group_alias is not None
|
||||
and data.get("model") in llm_router.model_group_alias
|
||||
): # model set in model_group_alias
|
||||
response = await llm_router.amoderation(
|
||||
**data
|
||||
) # ensure this goes the llm_router, router will do the correct alias mapping
|
||||
elif (
|
||||
llm_router is not None
|
||||
and data.get("model") not in router_model_names
|
||||
and (
|
||||
llm_router.default_deployment is not None
|
||||
or len(llm_router.provider_default_deployments) > 0
|
||||
)
|
||||
): # model in router deployments, calling a specific deployment on the router
|
||||
response = await llm_router.amoderation(**data)
|
||||
elif user_model is not None: # `litellm --model <your-model-name>`
|
||||
response = await litellm.amoderation(**data)
|
||||
else:
|
||||
# /moderations does not need a "model" passed
|
||||
# see https://platform.openai.com/docs/api-reference/moderations
|
||||
response = await litellm.amoderation(**data)
|
||||
llm_call = await route_request(
|
||||
data=data,
|
||||
route_type="amoderation",
|
||||
llm_router=llm_router,
|
||||
user_model=user_model,
|
||||
)
|
||||
response = await llm_call
|
||||
|
||||
### ALERTING ###
|
||||
asyncio.create_task(
|
||||
|
|
@ -9430,6 +9214,7 @@ async def get_config_list(
|
|||
"global_max_parallel_requests": {"type": "Integer"},
|
||||
"max_request_size_mb": {"type": "Integer"},
|
||||
"max_response_size_mb": {"type": "Integer"},
|
||||
"pass_through_endpoints": {"type": "PydanticModel"},
|
||||
}
|
||||
|
||||
return_val = []
|
||||
|
|
@ -9437,21 +9222,79 @@ async def get_config_list(
|
|||
for field_name, field_info in ConfigGeneralSettings.model_fields.items():
|
||||
if field_name in allowed_args:
|
||||
|
||||
_stored_in_db = None
|
||||
if field_name in db_general_settings_dict:
|
||||
_stored_in_db = True
|
||||
elif field_name in general_settings:
|
||||
_stored_in_db = False
|
||||
## HANDLE TYPED DICT
|
||||
|
||||
_response_obj = ConfigList(
|
||||
field_name=field_name,
|
||||
field_type=allowed_args[field_name]["type"],
|
||||
field_description=field_info.description or "",
|
||||
field_value=general_settings.get(field_name, None),
|
||||
stored_in_db=_stored_in_db,
|
||||
field_default_value=field_info.default,
|
||||
)
|
||||
return_val.append(_response_obj)
|
||||
typed_dict_type = allowed_args[field_name]["type"]
|
||||
|
||||
if typed_dict_type == "PydanticModel":
|
||||
if field_name == "pass_through_endpoints":
|
||||
pydantic_class_list = [PassThroughGenericEndpoint]
|
||||
else:
|
||||
pydantic_class_list = []
|
||||
|
||||
for pydantic_class in pydantic_class_list:
|
||||
# Get type hints from the TypedDict to create FieldDetail objects
|
||||
nested_fields = [
|
||||
FieldDetail(
|
||||
field_name=sub_field,
|
||||
field_type=sub_field_type.__name__,
|
||||
field_description="", # Add custom logic if descriptions are available
|
||||
field_default_value=general_settings.get(sub_field, None),
|
||||
stored_in_db=None,
|
||||
)
|
||||
for sub_field, sub_field_type in pydantic_class.__annotations__.items()
|
||||
]
|
||||
|
||||
idx = 0
|
||||
for (
|
||||
sub_field,
|
||||
sub_field_info,
|
||||
) in pydantic_class.model_fields.items():
|
||||
if (
|
||||
hasattr(sub_field_info, "description")
|
||||
and sub_field_info.description is not None
|
||||
):
|
||||
nested_fields[idx].field_description = (
|
||||
sub_field_info.description
|
||||
)
|
||||
idx += 1
|
||||
|
||||
_stored_in_db = None
|
||||
if field_name in db_general_settings_dict:
|
||||
_stored_in_db = True
|
||||
elif field_name in general_settings:
|
||||
_stored_in_db = False
|
||||
|
||||
_response_obj = ConfigList(
|
||||
field_name=field_name,
|
||||
field_type=allowed_args[field_name]["type"],
|
||||
field_description=field_info.description or "",
|
||||
field_value=general_settings.get(field_name, None),
|
||||
stored_in_db=_stored_in_db,
|
||||
field_default_value=field_info.default,
|
||||
nested_fields=nested_fields,
|
||||
)
|
||||
return_val.append(_response_obj)
|
||||
|
||||
else:
|
||||
nested_fields = None
|
||||
|
||||
_stored_in_db = None
|
||||
if field_name in db_general_settings_dict:
|
||||
_stored_in_db = True
|
||||
elif field_name in general_settings:
|
||||
_stored_in_db = False
|
||||
|
||||
_response_obj = ConfigList(
|
||||
field_name=field_name,
|
||||
field_type=allowed_args[field_name]["type"],
|
||||
field_description=field_info.description or "",
|
||||
field_value=general_settings.get(field_name, None),
|
||||
stored_in_db=_stored_in_db,
|
||||
field_default_value=field_info.default,
|
||||
nested_fields=nested_fields,
|
||||
)
|
||||
return_val.append(_response_obj)
|
||||
|
||||
return return_val
|
||||
|
||||
|
|
@ -9865,6 +9708,7 @@ def cleanup_router_config_variables():
|
|||
app.include_router(router)
|
||||
app.include_router(fine_tuning_router)
|
||||
app.include_router(vertex_router)
|
||||
app.include_router(pass_through_router)
|
||||
app.include_router(health_router)
|
||||
app.include_router(key_management_router)
|
||||
app.include_router(internal_user_router)
|
||||
|
|
|
|||
117
litellm/proxy/route_llm_request.py
Normal file
117
litellm/proxy/route_llm_request.py
Normal file
|
|
@ -0,0 +1,117 @@
|
|||
from typing import TYPE_CHECKING, Any, Literal, Optional, Union
|
||||
|
||||
from fastapi import (
|
||||
Depends,
|
||||
FastAPI,
|
||||
File,
|
||||
Form,
|
||||
Header,
|
||||
HTTPException,
|
||||
Path,
|
||||
Request,
|
||||
Response,
|
||||
UploadFile,
|
||||
status,
|
||||
)
|
||||
|
||||
import litellm
|
||||
from litellm._logging import verbose_logger
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from litellm.router import Router as _Router
|
||||
|
||||
LitellmRouter = _Router
|
||||
else:
|
||||
LitellmRouter = Any
|
||||
|
||||
|
||||
ROUTE_ENDPOINT_MAPPING = {
|
||||
"acompletion": "/chat/completions",
|
||||
"atext_completion": "/completions",
|
||||
"aembedding": "/embeddings",
|
||||
"aimage_generation": "/image/generations",
|
||||
"aspeech": "/audio/speech",
|
||||
"atranscription": "/audio/transcriptions",
|
||||
"amoderation": "/moderations",
|
||||
}
|
||||
|
||||
|
||||
async def route_request(
|
||||
data: dict,
|
||||
llm_router: Optional[LitellmRouter],
|
||||
user_model: Optional[str],
|
||||
route_type: Literal[
|
||||
"acompletion",
|
||||
"atext_completion",
|
||||
"aembedding",
|
||||
"aimage_generation",
|
||||
"aspeech",
|
||||
"atranscription",
|
||||
"amoderation",
|
||||
],
|
||||
):
|
||||
"""
|
||||
Common helper to route the request
|
||||
|
||||
"""
|
||||
router_model_names = llm_router.model_names if llm_router is not None else []
|
||||
|
||||
if "api_key" in data:
|
||||
return getattr(litellm, f"{route_type}")(**data)
|
||||
|
||||
elif "user_config" in data:
|
||||
router_config = data.pop("user_config")
|
||||
user_router = litellm.Router(**router_config)
|
||||
return getattr(user_router, f"{route_type}")(**data)
|
||||
|
||||
elif (
|
||||
route_type == "acompletion"
|
||||
and data.get("model", "") is not None
|
||||
and "," in data.get("model", "")
|
||||
and llm_router is not None
|
||||
):
|
||||
if data.get("fastest_response", False):
|
||||
return llm_router.abatch_completion_fastest_response(**data)
|
||||
else:
|
||||
models = [model.strip() for model in data.pop("model").split(",")]
|
||||
return llm_router.abatch_completion(models=models, **data)
|
||||
|
||||
elif llm_router is not None:
|
||||
if (
|
||||
data["model"] in router_model_names
|
||||
or data["model"] in llm_router.get_model_ids()
|
||||
):
|
||||
return getattr(llm_router, f"{route_type}")(**data)
|
||||
|
||||
elif (
|
||||
llm_router.model_group_alias is not None
|
||||
and data["model"] in llm_router.model_group_alias
|
||||
):
|
||||
return getattr(llm_router, f"{route_type}")(**data)
|
||||
|
||||
elif data["model"] in llm_router.deployment_names:
|
||||
return getattr(llm_router, f"{route_type}")(
|
||||
**data, specific_deployment=True
|
||||
)
|
||||
|
||||
elif data["model"] not in router_model_names:
|
||||
if llm_router.router_general_settings.pass_through_all_models:
|
||||
return getattr(litellm, f"{route_type}")(**data)
|
||||
elif (
|
||||
llm_router.default_deployment is not None
|
||||
or len(llm_router.provider_default_deployments) > 0
|
||||
):
|
||||
return getattr(llm_router, f"{route_type}")(**data)
|
||||
|
||||
elif user_model is not None:
|
||||
return getattr(litellm, f"{route_type}")(**data)
|
||||
|
||||
# if no route found then it's a bad request
|
||||
route_name = ROUTE_ENDPOINT_MAPPING.get(route_type, route_type)
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"error": f"{route_name}: Invalid model name passed in model="
|
||||
+ data.get("model", "")
|
||||
},
|
||||
)
|
||||
37
litellm/proxy/tests/test_anthropic_context_caching.py
Normal file
37
litellm/proxy/tests/test_anthropic_context_caching.py
Normal file
|
|
@ -0,0 +1,37 @@
|
|||
import openai
|
||||
|
||||
client = openai.OpenAI(
|
||||
api_key="sk-1234", # litellm proxy api key
|
||||
base_url="http://0.0.0.0:4000", # litellm proxy base url
|
||||
)
|
||||
|
||||
|
||||
response = client.chat.completions.create(
|
||||
model="anthropic/claude-3-5-sonnet-20240620",
|
||||
messages=[
|
||||
{ # type: ignore
|
||||
"role": "system",
|
||||
"content": [
|
||||
{
|
||||
"type": "text",
|
||||
"text": "You are an AI assistant tasked with analyzing legal documents.",
|
||||
},
|
||||
{
|
||||
"type": "text",
|
||||
"text": "Here is the full text of a complex legal agreement" * 100,
|
||||
"cache_control": {"type": "ephemeral"},
|
||||
},
|
||||
],
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "what are the key terms and conditions in this agreement?",
|
||||
},
|
||||
],
|
||||
extra_headers={
|
||||
"anthropic-version": "2023-06-01",
|
||||
"anthropic-beta": "prompt-caching-2024-07-31",
|
||||
},
|
||||
)
|
||||
|
||||
print(response)
|
||||
|
|
@ -3337,108 +3337,6 @@ def test_customprompt_together_ai():
|
|||
# test_customprompt_together_ai()
|
||||
|
||||
|
||||
@pytest.mark.skip(reason="AWS Suspended Account")
|
||||
def test_completion_sagemaker():
|
||||
try:
|
||||
litellm.set_verbose = True
|
||||
print("testing sagemaker")
|
||||
response = completion(
|
||||
model="sagemaker/jumpstart-dft-hf-llm-mistral-7b-ins-20240329-150233",
|
||||
model_id="huggingface-llm-mistral-7b-instruct-20240329-150233",
|
||||
messages=messages,
|
||||
temperature=0.2,
|
||||
max_tokens=80,
|
||||
aws_region_name=os.getenv("AWS_REGION_NAME_2"),
|
||||
aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID_2"),
|
||||
aws_secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY_2"),
|
||||
input_cost_per_second=0.000420,
|
||||
)
|
||||
# Add any assertions here to check the response
|
||||
print(response)
|
||||
cost = completion_cost(completion_response=response)
|
||||
print("calculated cost", cost)
|
||||
assert (
|
||||
cost > 0.0 and cost < 1.0
|
||||
) # should never be > $1 for a single completion call
|
||||
except Exception as e:
|
||||
pytest.fail(f"Error occurred: {e}")
|
||||
|
||||
|
||||
# test_completion_sagemaker()
|
||||
|
||||
|
||||
@pytest.mark.skip(reason="AWS Suspended Account")
|
||||
@pytest.mark.asyncio
|
||||
async def test_acompletion_sagemaker():
|
||||
try:
|
||||
litellm.set_verbose = True
|
||||
print("testing sagemaker")
|
||||
response = await litellm.acompletion(
|
||||
model="sagemaker/jumpstart-dft-hf-llm-mistral-7b-ins-20240329-150233",
|
||||
model_id="huggingface-llm-mistral-7b-instruct-20240329-150233",
|
||||
messages=messages,
|
||||
temperature=0.2,
|
||||
max_tokens=80,
|
||||
aws_region_name=os.getenv("AWS_REGION_NAME_2"),
|
||||
aws_access_key_id=os.getenv("AWS_ACCESS_KEY_ID_2"),
|
||||
aws_secret_access_key=os.getenv("AWS_SECRET_ACCESS_KEY_2"),
|
||||
input_cost_per_second=0.000420,
|
||||
)
|
||||
# Add any assertions here to check the response
|
||||
print(response)
|
||||
cost = completion_cost(completion_response=response)
|
||||
print("calculated cost", cost)
|
||||
assert (
|
||||
cost > 0.0 and cost < 1.0
|
||||
) # should never be > $1 for a single completion call
|
||||
except Exception as e:
|
||||
pytest.fail(f"Error occurred: {e}")
|
||||
|
||||
|
||||
@pytest.mark.skip(reason="AWS Suspended Account")
|
||||
def test_completion_chat_sagemaker():
|
||||
try:
|
||||
messages = [{"role": "user", "content": "Hey, how's it going?"}]
|
||||
litellm.set_verbose = True
|
||||
response = completion(
|
||||
model="sagemaker/berri-benchmarking-Llama-2-70b-chat-hf-4",
|
||||
messages=messages,
|
||||
max_tokens=100,
|
||||
temperature=0.7,
|
||||
stream=True,
|
||||
)
|
||||
# Add any assertions here to check the response
|
||||
complete_response = ""
|
||||
for chunk in response:
|
||||
complete_response += chunk.choices[0].delta.content or ""
|
||||
print(f"complete_response: {complete_response}")
|
||||
assert len(complete_response) > 0
|
||||
except Exception as e:
|
||||
pytest.fail(f"Error occurred: {e}")
|
||||
|
||||
|
||||
# test_completion_chat_sagemaker()
|
||||
|
||||
|
||||
@pytest.mark.skip(reason="AWS Suspended Account")
|
||||
def test_completion_chat_sagemaker_mistral():
|
||||
try:
|
||||
messages = [{"role": "user", "content": "Hey, how's it going?"}]
|
||||
|
||||
response = completion(
|
||||
model="sagemaker/jumpstart-dft-hf-llm-mistral-7b-instruct",
|
||||
messages=messages,
|
||||
max_tokens=100,
|
||||
)
|
||||
# Add any assertions here to check the response
|
||||
print(response)
|
||||
except Exception as e:
|
||||
pytest.fail(f"An error occurred: {str(e)}")
|
||||
|
||||
|
||||
# test_completion_chat_sagemaker_mistral()
|
||||
|
||||
|
||||
def response_format_tests(response: litellm.ModelResponse):
|
||||
assert isinstance(response.id, str)
|
||||
assert response.id != ""
|
||||
|
|
|
|||
|
|
@ -1166,3 +1166,63 @@ def test_turn_off_message_logging():
|
|||
|
||||
time.sleep(2)
|
||||
assert len(customHandler.errors) == 0
|
||||
|
||||
|
||||
##### VALID JSON ######
|
||||
|
||||
|
||||
def test_standard_logging_payload():
|
||||
"""
|
||||
Ensure valid standard_logging_payload is passed for logging calls to s3
|
||||
|
||||
Motivation: provide a standard set of things that are logged to s3/gcs/future integrations across all llm calls
|
||||
"""
|
||||
from litellm.types.utils import StandardLoggingPayload
|
||||
|
||||
# sync completion
|
||||
customHandler = CompletionCustomHandler()
|
||||
litellm.callbacks = [customHandler]
|
||||
|
||||
with patch.object(
|
||||
customHandler, "log_success_event", new=MagicMock()
|
||||
) as mock_client:
|
||||
_ = litellm.completion(
|
||||
model="gpt-3.5-turbo",
|
||||
messages=[{"role": "user", "content": "Hey, how's it going?"}],
|
||||
mock_response="Going well!",
|
||||
)
|
||||
|
||||
time.sleep(2)
|
||||
mock_client.assert_called_once()
|
||||
|
||||
print(
|
||||
f"mock_client_post.call_args: {mock_client.call_args.kwargs['kwargs'].keys()}"
|
||||
)
|
||||
assert "standard_logging_object" in mock_client.call_args.kwargs["kwargs"]
|
||||
assert (
|
||||
mock_client.call_args.kwargs["kwargs"]["standard_logging_object"]
|
||||
is not None
|
||||
)
|
||||
|
||||
print(mock_client.call_args.kwargs["kwargs"]["standard_logging_object"])
|
||||
|
||||
keys_list = list(StandardLoggingPayload.__annotations__.keys())
|
||||
|
||||
for k in keys_list:
|
||||
assert (
|
||||
k in mock_client.call_args.kwargs["kwargs"]["standard_logging_object"]
|
||||
)
|
||||
|
||||
## json serializable
|
||||
json_str_payload = json.dumps(
|
||||
mock_client.call_args.kwargs["kwargs"]["standard_logging_object"]
|
||||
)
|
||||
json.loads(json_str_payload)
|
||||
|
||||
## response cost
|
||||
assert (
|
||||
mock_client.call_args.kwargs["kwargs"]["standard_logging_object"][
|
||||
"response_cost"
|
||||
]
|
||||
> 0
|
||||
)
|
||||
|
|
|
|||
|
|
@ -2,16 +2,19 @@
|
|||
# This tests setting provider specific configs across providers
|
||||
# There are 2 types of tests - changing config dynamically or by setting class variables
|
||||
|
||||
import sys, os
|
||||
import os
|
||||
import sys
|
||||
import traceback
|
||||
|
||||
import pytest
|
||||
|
||||
sys.path.insert(
|
||||
0, os.path.abspath("../..")
|
||||
) # Adds the parent directory to the system path
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
|
||||
import litellm
|
||||
from litellm import completion
|
||||
from litellm import RateLimitError
|
||||
from litellm import RateLimitError, completion
|
||||
|
||||
# Huggingface - Expensive to deploy models and keep them running. Maybe we can try doing this via baseten??
|
||||
# def hf_test_completion_tgi():
|
||||
|
|
@ -513,102 +516,165 @@ def sagemaker_test_completion():
|
|||
# sagemaker_test_completion()
|
||||
|
||||
|
||||
def test_sagemaker_default_region(mocker):
|
||||
def test_sagemaker_default_region():
|
||||
"""
|
||||
If no regions are specified in config or in environment, the default region is us-west-2
|
||||
"""
|
||||
mock_client = mocker.patch("boto3.client")
|
||||
try:
|
||||
mock_response = MagicMock()
|
||||
|
||||
def return_val():
|
||||
return {
|
||||
"generated_text": "This is a mock response from SageMaker.",
|
||||
"id": "cmpl-mockid",
|
||||
"object": "text_completion",
|
||||
"created": 1629800000,
|
||||
"model": "sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
"choices": [
|
||||
{
|
||||
"text": "This is a mock response from SageMaker.",
|
||||
"index": 0,
|
||||
"logprobs": None,
|
||||
"finish_reason": "length",
|
||||
}
|
||||
],
|
||||
"usage": {"prompt_tokens": 1, "completion_tokens": 8, "total_tokens": 9},
|
||||
}
|
||||
|
||||
mock_response.json = return_val
|
||||
mock_response.status_code = 200
|
||||
|
||||
with patch(
|
||||
"litellm.llms.custom_httpx.http_handler.HTTPHandler.post",
|
||||
return_value=mock_response,
|
||||
) as mock_post:
|
||||
response = litellm.completion(
|
||||
model="sagemaker/mock-endpoint",
|
||||
messages=[
|
||||
{
|
||||
"content": "Hello, world!",
|
||||
"role": "user"
|
||||
}
|
||||
]
|
||||
messages=[{"content": "Hello, world!", "role": "user"}],
|
||||
)
|
||||
except Exception:
|
||||
pass # expected serialization exception because AWS client was replaced with a Mock
|
||||
assert mock_client.call_args.kwargs["region_name"] == "us-west-2"
|
||||
mock_post.assert_called_once()
|
||||
_, kwargs = mock_post.call_args
|
||||
args_to_sagemaker = kwargs["json"]
|
||||
print("Arguments passed to sagemaker=", args_to_sagemaker)
|
||||
print("url=", kwargs["url"])
|
||||
|
||||
assert (
|
||||
kwargs["url"]
|
||||
== "https://runtime.sagemaker.us-west-2.amazonaws.com/endpoints/mock-endpoint/invocations"
|
||||
)
|
||||
|
||||
|
||||
# test_sagemaker_default_region()
|
||||
|
||||
|
||||
def test_sagemaker_environment_region(mocker):
|
||||
def test_sagemaker_environment_region():
|
||||
"""
|
||||
If a region is specified in the environment, use that region instead of us-west-2
|
||||
"""
|
||||
expected_region = "us-east-1"
|
||||
os.environ["AWS_REGION_NAME"] = expected_region
|
||||
mock_client = mocker.patch("boto3.client")
|
||||
try:
|
||||
mock_response = MagicMock()
|
||||
|
||||
def return_val():
|
||||
return {
|
||||
"generated_text": "This is a mock response from SageMaker.",
|
||||
"id": "cmpl-mockid",
|
||||
"object": "text_completion",
|
||||
"created": 1629800000,
|
||||
"model": "sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
"choices": [
|
||||
{
|
||||
"text": "This is a mock response from SageMaker.",
|
||||
"index": 0,
|
||||
"logprobs": None,
|
||||
"finish_reason": "length",
|
||||
}
|
||||
],
|
||||
"usage": {"prompt_tokens": 1, "completion_tokens": 8, "total_tokens": 9},
|
||||
}
|
||||
|
||||
mock_response.json = return_val
|
||||
mock_response.status_code = 200
|
||||
|
||||
with patch(
|
||||
"litellm.llms.custom_httpx.http_handler.HTTPHandler.post",
|
||||
return_value=mock_response,
|
||||
) as mock_post:
|
||||
response = litellm.completion(
|
||||
model="sagemaker/mock-endpoint",
|
||||
messages=[
|
||||
{
|
||||
"content": "Hello, world!",
|
||||
"role": "user"
|
||||
}
|
||||
]
|
||||
messages=[{"content": "Hello, world!", "role": "user"}],
|
||||
)
|
||||
except Exception:
|
||||
pass # expected serialization exception because AWS client was replaced with a Mock
|
||||
del os.environ["AWS_REGION_NAME"] # cleanup
|
||||
assert mock_client.call_args.kwargs["region_name"] == expected_region
|
||||
mock_post.assert_called_once()
|
||||
_, kwargs = mock_post.call_args
|
||||
args_to_sagemaker = kwargs["json"]
|
||||
print("Arguments passed to sagemaker=", args_to_sagemaker)
|
||||
print("url=", kwargs["url"])
|
||||
|
||||
assert (
|
||||
kwargs["url"]
|
||||
== f"https://runtime.sagemaker.{expected_region}.amazonaws.com/endpoints/mock-endpoint/invocations"
|
||||
)
|
||||
|
||||
del os.environ["AWS_REGION_NAME"] # cleanup
|
||||
|
||||
|
||||
# test_sagemaker_environment_region()
|
||||
|
||||
|
||||
def test_sagemaker_config_region(mocker):
|
||||
def test_sagemaker_config_region():
|
||||
"""
|
||||
If a region is specified as part of the optional parameters of the completion, including as
|
||||
part of the config file, then use that region instead of us-west-2
|
||||
"""
|
||||
expected_region = "us-east-1"
|
||||
mock_client = mocker.patch("boto3.client")
|
||||
try:
|
||||
response = litellm.completion(
|
||||
model="sagemaker/mock-endpoint",
|
||||
messages=[
|
||||
mock_response = MagicMock()
|
||||
|
||||
def return_val():
|
||||
return {
|
||||
"generated_text": "This is a mock response from SageMaker.",
|
||||
"id": "cmpl-mockid",
|
||||
"object": "text_completion",
|
||||
"created": 1629800000,
|
||||
"model": "sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
"choices": [
|
||||
{
|
||||
"content": "Hello, world!",
|
||||
"role": "user"
|
||||
"text": "This is a mock response from SageMaker.",
|
||||
"index": 0,
|
||||
"logprobs": None,
|
||||
"finish_reason": "length",
|
||||
}
|
||||
],
|
||||
"usage": {"prompt_tokens": 1, "completion_tokens": 8, "total_tokens": 9},
|
||||
}
|
||||
|
||||
mock_response.json = return_val
|
||||
mock_response.status_code = 200
|
||||
|
||||
with patch(
|
||||
"litellm.llms.custom_httpx.http_handler.HTTPHandler.post",
|
||||
return_value=mock_response,
|
||||
) as mock_post:
|
||||
|
||||
response = litellm.completion(
|
||||
model="sagemaker/mock-endpoint",
|
||||
messages=[{"content": "Hello, world!", "role": "user"}],
|
||||
aws_region_name=expected_region,
|
||||
)
|
||||
except Exception:
|
||||
pass # expected serialization exception because AWS client was replaced with a Mock
|
||||
assert mock_client.call_args.kwargs["region_name"] == expected_region
|
||||
|
||||
mock_post.assert_called_once()
|
||||
_, kwargs = mock_post.call_args
|
||||
args_to_sagemaker = kwargs["json"]
|
||||
print("Arguments passed to sagemaker=", args_to_sagemaker)
|
||||
print("url=", kwargs["url"])
|
||||
|
||||
assert (
|
||||
kwargs["url"]
|
||||
== f"https://runtime.sagemaker.{expected_region}.amazonaws.com/endpoints/mock-endpoint/invocations"
|
||||
)
|
||||
|
||||
|
||||
# test_sagemaker_config_region()
|
||||
|
||||
|
||||
def test_sagemaker_config_and_environment_region(mocker):
|
||||
"""
|
||||
If both the environment and config file specify a region, the environment region is expected
|
||||
"""
|
||||
expected_region = "us-east-1"
|
||||
unexpected_region = "us-east-2"
|
||||
os.environ["AWS_REGION_NAME"] = expected_region
|
||||
mock_client = mocker.patch("boto3.client")
|
||||
try:
|
||||
response = litellm.completion(
|
||||
model="sagemaker/mock-endpoint",
|
||||
messages=[
|
||||
{
|
||||
"content": "Hello, world!",
|
||||
"role": "user"
|
||||
}
|
||||
],
|
||||
aws_region_name=unexpected_region,
|
||||
)
|
||||
except Exception:
|
||||
pass # expected serialization exception because AWS client was replaced with a Mock
|
||||
del os.environ["AWS_REGION_NAME"] # cleanup
|
||||
assert mock_client.call_args.kwargs["region_name"] == expected_region
|
||||
|
||||
# test_sagemaker_config_and_environment_region()
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -229,8 +229,9 @@ def test_chat_completion_exception_any_model(client):
|
|||
)
|
||||
assert isinstance(openai_exception, openai.BadRequestError)
|
||||
_error_message = openai_exception.message
|
||||
assert "chat_completion: Invalid model name passed in model=Lite-GPT-12" in str(
|
||||
_error_message
|
||||
assert (
|
||||
"/chat/completions: Invalid model name passed in model=Lite-GPT-12"
|
||||
in str(_error_message)
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
|
|
@ -259,7 +260,7 @@ def test_embedding_exception_any_model(client):
|
|||
print("Exception raised=", openai_exception)
|
||||
assert isinstance(openai_exception, openai.BadRequestError)
|
||||
_error_message = openai_exception.message
|
||||
assert "embeddings: Invalid model name passed in model=Lite-GPT-12" in str(
|
||||
assert "/embeddings: Invalid model name passed in model=Lite-GPT-12" in str(
|
||||
_error_message
|
||||
)
|
||||
|
||||
|
|
|
|||
316
litellm/tests/test_sagemaker.py
Normal file
316
litellm/tests/test_sagemaker.py
Normal file
|
|
@ -0,0 +1,316 @@
|
|||
import json
|
||||
import os
|
||||
import sys
|
||||
import traceback
|
||||
|
||||
from dotenv import load_dotenv
|
||||
|
||||
load_dotenv()
|
||||
import io
|
||||
import os
|
||||
|
||||
sys.path.insert(
|
||||
0, os.path.abspath("../..")
|
||||
) # Adds the parent directory to the system path
|
||||
|
||||
import os
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
import litellm
|
||||
from litellm import RateLimitError, Timeout, completion, completion_cost, embedding
|
||||
from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
|
||||
from litellm.llms.prompt_templates.factory import anthropic_messages_pt
|
||||
|
||||
# litellm.num_retries =3
|
||||
litellm.cache = None
|
||||
litellm.success_callback = []
|
||||
user_message = "Write a short poem about the sky"
|
||||
messages = [{"content": user_message, "role": "user"}]
|
||||
import logging
|
||||
|
||||
from litellm._logging import verbose_logger
|
||||
|
||||
|
||||
def logger_fn(user_model_dict):
|
||||
print(f"user_model_dict: {user_model_dict}")
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def reset_callbacks():
|
||||
print("\npytest fixture - resetting callbacks")
|
||||
litellm.success_callback = []
|
||||
litellm._async_success_callback = []
|
||||
litellm.failure_callback = []
|
||||
litellm.callbacks = []
|
||||
|
||||
|
||||
@pytest.mark.asyncio()
|
||||
@pytest.mark.parametrize("sync_mode", [True, False])
|
||||
async def test_completion_sagemaker(sync_mode):
|
||||
try:
|
||||
litellm.set_verbose = True
|
||||
verbose_logger.setLevel(logging.DEBUG)
|
||||
print("testing sagemaker")
|
||||
if sync_mode is True:
|
||||
response = litellm.completion(
|
||||
model="sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
messages=[
|
||||
{"role": "user", "content": "hi"},
|
||||
],
|
||||
temperature=0.2,
|
||||
max_tokens=80,
|
||||
input_cost_per_second=0.000420,
|
||||
)
|
||||
else:
|
||||
response = await litellm.acompletion(
|
||||
model="sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
messages=[
|
||||
{"role": "user", "content": "hi"},
|
||||
],
|
||||
temperature=0.2,
|
||||
max_tokens=80,
|
||||
input_cost_per_second=0.000420,
|
||||
)
|
||||
# Add any assertions here to check the response
|
||||
print(response)
|
||||
cost = completion_cost(completion_response=response)
|
||||
print("calculated cost", cost)
|
||||
assert (
|
||||
cost > 0.0 and cost < 1.0
|
||||
) # should never be > $1 for a single completion call
|
||||
except Exception as e:
|
||||
pytest.fail(f"Error occurred: {e}")
|
||||
|
||||
|
||||
@pytest.mark.asyncio()
|
||||
@pytest.mark.parametrize("sync_mode", [False, True])
|
||||
async def test_completion_sagemaker_stream(sync_mode):
|
||||
try:
|
||||
litellm.set_verbose = False
|
||||
print("testing sagemaker")
|
||||
verbose_logger.setLevel(logging.DEBUG)
|
||||
full_text = ""
|
||||
if sync_mode is True:
|
||||
response = litellm.completion(
|
||||
model="sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
messages=[
|
||||
{"role": "user", "content": "hi - what is ur name"},
|
||||
],
|
||||
temperature=0.2,
|
||||
stream=True,
|
||||
max_tokens=80,
|
||||
input_cost_per_second=0.000420,
|
||||
)
|
||||
|
||||
for chunk in response:
|
||||
print(chunk)
|
||||
full_text += chunk.choices[0].delta.content or ""
|
||||
|
||||
print("SYNC RESPONSE full text", full_text)
|
||||
else:
|
||||
response = await litellm.acompletion(
|
||||
model="sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
messages=[
|
||||
{"role": "user", "content": "hi - what is ur name"},
|
||||
],
|
||||
stream=True,
|
||||
temperature=0.2,
|
||||
max_tokens=80,
|
||||
input_cost_per_second=0.000420,
|
||||
)
|
||||
|
||||
print("streaming response")
|
||||
|
||||
async for chunk in response:
|
||||
print(chunk)
|
||||
full_text += chunk.choices[0].delta.content or ""
|
||||
|
||||
print("ASYNC RESPONSE full text", full_text)
|
||||
|
||||
except Exception as e:
|
||||
pytest.fail(f"Error occurred: {e}")
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_acompletion_sagemaker_non_stream():
|
||||
mock_response = AsyncMock()
|
||||
|
||||
def return_val():
|
||||
return {
|
||||
"generated_text": "This is a mock response from SageMaker.",
|
||||
"id": "cmpl-mockid",
|
||||
"object": "text_completion",
|
||||
"created": 1629800000,
|
||||
"model": "sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
"choices": [
|
||||
{
|
||||
"text": "This is a mock response from SageMaker.",
|
||||
"index": 0,
|
||||
"logprobs": None,
|
||||
"finish_reason": "length",
|
||||
}
|
||||
],
|
||||
"usage": {"prompt_tokens": 1, "completion_tokens": 8, "total_tokens": 9},
|
||||
}
|
||||
|
||||
mock_response.json = return_val
|
||||
mock_response.status_code = 200
|
||||
|
||||
expected_payload = {
|
||||
"inputs": "hi",
|
||||
"parameters": {"temperature": 0.2, "max_new_tokens": 80},
|
||||
}
|
||||
|
||||
with patch(
|
||||
"litellm.llms.custom_httpx.http_handler.AsyncHTTPHandler.post",
|
||||
return_value=mock_response,
|
||||
) as mock_post:
|
||||
# Act: Call the litellm.acompletion function
|
||||
response = await litellm.acompletion(
|
||||
model="sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
messages=[
|
||||
{"role": "user", "content": "hi"},
|
||||
],
|
||||
temperature=0.2,
|
||||
max_tokens=80,
|
||||
input_cost_per_second=0.000420,
|
||||
)
|
||||
|
||||
# Print what was called on the mock
|
||||
print("call args=", mock_post.call_args)
|
||||
|
||||
# Assert
|
||||
mock_post.assert_called_once()
|
||||
_, kwargs = mock_post.call_args
|
||||
args_to_sagemaker = kwargs["json"]
|
||||
print("Arguments passed to sagemaker=", args_to_sagemaker)
|
||||
assert args_to_sagemaker == expected_payload
|
||||
assert (
|
||||
kwargs["url"]
|
||||
== "https://runtime.sagemaker.us-west-2.amazonaws.com/endpoints/jumpstart-dft-hf-textgeneration1-mp-20240815-185614/invocations"
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_completion_sagemaker_non_stream():
|
||||
mock_response = MagicMock()
|
||||
|
||||
def return_val():
|
||||
return {
|
||||
"generated_text": "This is a mock response from SageMaker.",
|
||||
"id": "cmpl-mockid",
|
||||
"object": "text_completion",
|
||||
"created": 1629800000,
|
||||
"model": "sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
"choices": [
|
||||
{
|
||||
"text": "This is a mock response from SageMaker.",
|
||||
"index": 0,
|
||||
"logprobs": None,
|
||||
"finish_reason": "length",
|
||||
}
|
||||
],
|
||||
"usage": {"prompt_tokens": 1, "completion_tokens": 8, "total_tokens": 9},
|
||||
}
|
||||
|
||||
mock_response.json = return_val
|
||||
mock_response.status_code = 200
|
||||
|
||||
expected_payload = {
|
||||
"inputs": "hi",
|
||||
"parameters": {"temperature": 0.2, "max_new_tokens": 80},
|
||||
}
|
||||
|
||||
with patch(
|
||||
"litellm.llms.custom_httpx.http_handler.HTTPHandler.post",
|
||||
return_value=mock_response,
|
||||
) as mock_post:
|
||||
# Act: Call the litellm.acompletion function
|
||||
response = litellm.completion(
|
||||
model="sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
messages=[
|
||||
{"role": "user", "content": "hi"},
|
||||
],
|
||||
temperature=0.2,
|
||||
max_tokens=80,
|
||||
input_cost_per_second=0.000420,
|
||||
)
|
||||
|
||||
# Print what was called on the mock
|
||||
print("call args=", mock_post.call_args)
|
||||
|
||||
# Assert
|
||||
mock_post.assert_called_once()
|
||||
_, kwargs = mock_post.call_args
|
||||
args_to_sagemaker = kwargs["json"]
|
||||
print("Arguments passed to sagemaker=", args_to_sagemaker)
|
||||
assert args_to_sagemaker == expected_payload
|
||||
assert (
|
||||
kwargs["url"]
|
||||
== "https://runtime.sagemaker.us-west-2.amazonaws.com/endpoints/jumpstart-dft-hf-textgeneration1-mp-20240815-185614/invocations"
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_completion_sagemaker_non_stream_with_aws_params():
|
||||
mock_response = MagicMock()
|
||||
|
||||
def return_val():
|
||||
return {
|
||||
"generated_text": "This is a mock response from SageMaker.",
|
||||
"id": "cmpl-mockid",
|
||||
"object": "text_completion",
|
||||
"created": 1629800000,
|
||||
"model": "sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
"choices": [
|
||||
{
|
||||
"text": "This is a mock response from SageMaker.",
|
||||
"index": 0,
|
||||
"logprobs": None,
|
||||
"finish_reason": "length",
|
||||
}
|
||||
],
|
||||
"usage": {"prompt_tokens": 1, "completion_tokens": 8, "total_tokens": 9},
|
||||
}
|
||||
|
||||
mock_response.json = return_val
|
||||
mock_response.status_code = 200
|
||||
|
||||
expected_payload = {
|
||||
"inputs": "hi",
|
||||
"parameters": {"temperature": 0.2, "max_new_tokens": 80},
|
||||
}
|
||||
|
||||
with patch(
|
||||
"litellm.llms.custom_httpx.http_handler.HTTPHandler.post",
|
||||
return_value=mock_response,
|
||||
) as mock_post:
|
||||
# Act: Call the litellm.acompletion function
|
||||
response = litellm.completion(
|
||||
model="sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614",
|
||||
messages=[
|
||||
{"role": "user", "content": "hi"},
|
||||
],
|
||||
temperature=0.2,
|
||||
max_tokens=80,
|
||||
input_cost_per_second=0.000420,
|
||||
aws_access_key_id="gm",
|
||||
aws_secret_access_key="s",
|
||||
aws_region_name="us-west-5",
|
||||
)
|
||||
|
||||
# Print what was called on the mock
|
||||
print("call args=", mock_post.call_args)
|
||||
|
||||
# Assert
|
||||
mock_post.assert_called_once()
|
||||
_, kwargs = mock_post.call_args
|
||||
args_to_sagemaker = kwargs["json"]
|
||||
print("Arguments passed to sagemaker=", args_to_sagemaker)
|
||||
assert args_to_sagemaker == expected_payload
|
||||
assert (
|
||||
kwargs["url"]
|
||||
== "https://runtime.sagemaker.us-west-5.amazonaws.com/endpoints/jumpstart-dft-hf-textgeneration1-mp-20240815-185614/invocations"
|
||||
)
|
||||
|
|
@ -1683,6 +1683,7 @@ def test_completion_bedrock_mistral_stream():
|
|||
pytest.fail(f"Error occurred: {e}")
|
||||
|
||||
|
||||
@pytest.mark.skip(reason="stopped using TokenIterator")
|
||||
def test_sagemaker_weird_response():
|
||||
"""
|
||||
When the stream ends, flush any remaining holding chunks.
|
||||
|
|
|
|||
|
|
@ -80,7 +80,7 @@ class ModelInfo(TypedDict, total=False):
|
|||
supports_assistant_prefill: Optional[bool]
|
||||
|
||||
|
||||
class GenericStreamingChunk(TypedDict):
|
||||
class GenericStreamingChunk(TypedDict, total=False):
|
||||
text: Required[str]
|
||||
tool_use: Optional[ChatCompletionToolCallChunk]
|
||||
is_finished: Required[bool]
|
||||
|
|
@ -1166,3 +1166,53 @@ class AdapterCompletionStreamWrapper:
|
|||
raise StopIteration
|
||||
except StopIteration:
|
||||
raise StopAsyncIteration
|
||||
|
||||
|
||||
class StandardLoggingMetadata(TypedDict):
|
||||
"""
|
||||
Specific metadata k,v pairs logged to integration for easier cost tracking
|
||||
"""
|
||||
|
||||
user_api_key_hash: Optional[str] # hash of the litellm virtual key used
|
||||
user_api_key_alias: Optional[str]
|
||||
user_api_key_team_id: Optional[str]
|
||||
user_api_key_user_id: Optional[str]
|
||||
user_api_key_team_alias: Optional[str]
|
||||
spend_logs_metadata: Optional[
|
||||
dict
|
||||
] # special param to log k,v pairs to spendlogs for a call
|
||||
requester_ip_address: Optional[str]
|
||||
|
||||
|
||||
class StandardLoggingHiddenParams(TypedDict):
|
||||
model_id: Optional[str]
|
||||
cache_key: Optional[str]
|
||||
api_base: Optional[str]
|
||||
response_cost: Optional[str]
|
||||
additional_headers: Optional[dict]
|
||||
|
||||
|
||||
class StandardLoggingPayload(TypedDict):
|
||||
id: str
|
||||
call_type: str
|
||||
response_cost: float
|
||||
total_tokens: int
|
||||
prompt_tokens: int
|
||||
completion_tokens: int
|
||||
startTime: float
|
||||
endTime: float
|
||||
completionStartTime: float
|
||||
model: str
|
||||
model_id: Optional[str]
|
||||
model_group: Optional[str]
|
||||
api_base: str
|
||||
metadata: StandardLoggingMetadata
|
||||
cache_hit: Optional[bool]
|
||||
cache_key: Optional[str]
|
||||
request_tags: list
|
||||
end_user: Optional[str]
|
||||
requester_ip_address: Optional[str]
|
||||
messages: Optional[Union[str, list, dict]]
|
||||
response: Optional[Union[str, list, dict]]
|
||||
model_parameters: dict
|
||||
hidden_params: StandardLoggingHiddenParams
|
||||
|
|
|
|||
|
|
@ -9848,11 +9848,28 @@ class CustomStreamWrapper:
|
|||
completion_obj["tool_calls"] = [response_obj["tool_use"]]
|
||||
|
||||
elif self.custom_llm_provider == "sagemaker":
|
||||
print_verbose(f"ENTERS SAGEMAKER STREAMING for chunk {chunk}")
|
||||
response_obj = self.handle_sagemaker_stream(chunk)
|
||||
from litellm.types.llms.bedrock import GenericStreamingChunk
|
||||
|
||||
if self.received_finish_reason is not None:
|
||||
raise StopIteration
|
||||
response_obj: GenericStreamingChunk = chunk
|
||||
completion_obj["content"] = response_obj["text"]
|
||||
if response_obj["is_finished"]:
|
||||
self.received_finish_reason = response_obj["finish_reason"]
|
||||
|
||||
if (
|
||||
self.stream_options
|
||||
and self.stream_options.get("include_usage", False) is True
|
||||
and response_obj["usage"] is not None
|
||||
):
|
||||
model_response.usage = litellm.Usage(
|
||||
prompt_tokens=response_obj["usage"]["inputTokens"],
|
||||
completion_tokens=response_obj["usage"]["outputTokens"],
|
||||
total_tokens=response_obj["usage"]["totalTokens"],
|
||||
)
|
||||
|
||||
if "tool_use" in response_obj and response_obj["tool_use"] is not None:
|
||||
completion_obj["tool_calls"] = [response_obj["tool_use"]]
|
||||
elif self.custom_llm_provider == "petals":
|
||||
if len(self.completion_stream) == 0:
|
||||
if self.received_finish_reason is not None:
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
[tool.poetry]
|
||||
name = "litellm"
|
||||
version = "1.43.13"
|
||||
version = "1.43.16"
|
||||
description = "Library to easily interface with LLM API providers"
|
||||
authors = ["BerriAI"]
|
||||
license = "MIT"
|
||||
|
|
@ -91,7 +91,7 @@ requires = ["poetry-core", "wheel"]
|
|||
build-backend = "poetry.core.masonry.api"
|
||||
|
||||
[tool.commitizen]
|
||||
version = "1.43.13"
|
||||
version = "1.43.16"
|
||||
version_files = [
|
||||
"pyproject.toml:^version"
|
||||
]
|
||||
|
|
|
|||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
|
|
@ -1 +0,0 @@
|
|||
(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[185],{87421:function(e,n,t){Promise.resolve().then(t.t.bind(t,99646,23)),Promise.resolve().then(t.t.bind(t,63385,23))},63385:function(){},99646:function(e){e.exports={style:{fontFamily:"'__Inter_86ef86', '__Inter_Fallback_86ef86'",fontStyle:"normal"},className:"__className_86ef86"}}},function(e){e.O(0,[971,69,744],function(){return e(e.s=87421)}),_N_E=e.O()}]);
|
||||
|
|
@ -1 +0,0 @@
|
|||
(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[461],{61994:function(e,s,t){Promise.resolve().then(t.bind(t,667))},667:function(e,s,t){"use strict";t.r(s),t.d(s,{default:function(){return g}});var l=t(57437),n=t(2265),a=t(47907),i=t(2179),r=t(18190),o=t(13810),c=t(10384),u=t(46453),d=t(71801),m=t(52273),h=t(42440),x=t(30953),f=t(777),p=t(37963),j=t(60620),_=t(1861);function g(){let[e]=j.Z.useForm(),s=(0,a.useSearchParams)();!function(e){console.log("COOKIES",document.cookie);let s=document.cookie.split("; ").find(s=>s.startsWith(e+"="));s&&s.split("=")[1]}("token");let t=s.get("invitation_id"),[g,Z]=(0,n.useState)(null),[k,w]=(0,n.useState)(""),[S,b]=(0,n.useState)(""),[N,v]=(0,n.useState)(null),[y,E]=(0,n.useState)(""),[I,O]=(0,n.useState)("");return(0,n.useEffect)(()=>{t&&(0,f.W_)(t).then(e=>{let s=e.login_url;console.log("login_url:",s),E(s);let t=e.token,l=(0,p.o)(t);O(t),console.log("decoded:",l),Z(l.key),console.log("decoded user email:",l.user_email),b(l.user_email),v(l.user_id)})},[t]),(0,l.jsx)("div",{className:"mx-auto w-full max-w-md mt-10",children:(0,l.jsxs)(o.Z,{children:[(0,l.jsx)(h.Z,{className:"text-sm mb-5 text-center",children:"\uD83D\uDE85 LiteLLM"}),(0,l.jsx)(h.Z,{className:"text-xl",children:"Sign up"}),(0,l.jsx)(d.Z,{children:"Claim your user account to login to Admin UI."}),(0,l.jsx)(r.Z,{className:"mt-4",title:"SSO",icon:x.GH$,color:"sky",children:(0,l.jsxs)(u.Z,{numItems:2,className:"flex justify-between items-center",children:[(0,l.jsx)(c.Z,{children:"SSO is under the Enterprise Tirer."}),(0,l.jsx)(c.Z,{children:(0,l.jsx)(i.Z,{variant:"primary",className:"mb-2",children:(0,l.jsx)("a",{href:"https://forms.gle/W3U4PZpJGFHWtHyA9",target:"_blank",children:"Get Free Trial"})})})]})}),(0,l.jsxs)(j.Z,{className:"mt-10 mb-5 mx-auto",layout:"vertical",onFinish:e=>{console.log("in handle submit. accessToken:",g,"token:",I,"formValues:",e),g&&I&&(e.user_email=S,N&&t&&(0,f.m_)(g,t,N,e.password).then(e=>{var s;let t="/ui/";t+="?userID="+((null===(s=e.data)||void 0===s?void 0:s.user_id)||e.user_id),document.cookie="token="+I,console.log("redirecting to:",t),window.location.href=t}))},children:[(0,l.jsxs)(l.Fragment,{children:[(0,l.jsx)(j.Z.Item,{label:"Email Address",name:"user_email",children:(0,l.jsx)(m.Z,{type:"email",disabled:!0,value:S,defaultValue:S,className:"max-w-md"})}),(0,l.jsx)(j.Z.Item,{label:"Password",name:"password",rules:[{required:!0,message:"password required to sign up"}],help:"Create a password for your account",children:(0,l.jsx)(m.Z,{placeholder:"",type:"password",className:"max-w-md"})})]}),(0,l.jsx)("div",{className:"mt-10",children:(0,l.jsx)(_.ZP,{htmlType:"submit",children:"Sign Up"})})]})]})})}}},function(e){e.O(0,[665,505,684,777,971,69,744],function(){return e(e.s=61994)}),_N_E=e.O()}]);
|
||||
File diff suppressed because one or more lines are too long
|
|
@ -1 +0,0 @@
|
|||
(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[744],{32028:function(e,n,t){Promise.resolve().then(t.t.bind(t,47690,23)),Promise.resolve().then(t.t.bind(t,48955,23)),Promise.resolve().then(t.t.bind(t,5613,23)),Promise.resolve().then(t.t.bind(t,11902,23)),Promise.resolve().then(t.t.bind(t,31778,23)),Promise.resolve().then(t.t.bind(t,77831,23))}},function(e){var n=function(n){return e(e.s=n)};e.O(0,[971,69],function(){return n(35317),n(32028)}),_N_E=e.O()}]);
|
||||
|
|
@ -1 +0,0 @@
|
|||
!function(){"use strict";var e,t,n,r,o,u,i,c,f,a={},l={};function d(e){var t=l[e];if(void 0!==t)return t.exports;var n=l[e]={id:e,loaded:!1,exports:{}},r=!0;try{a[e](n,n.exports,d),r=!1}finally{r&&delete l[e]}return n.loaded=!0,n.exports}d.m=a,e=[],d.O=function(t,n,r,o){if(n){o=o||0;for(var u=e.length;u>0&&e[u-1][2]>o;u--)e[u]=e[u-1];e[u]=[n,r,o];return}for(var i=1/0,u=0;u<e.length;u++){for(var n=e[u][0],r=e[u][1],o=e[u][2],c=!0,f=0;f<n.length;f++)i>=o&&Object.keys(d.O).every(function(e){return d.O[e](n[f])})?n.splice(f--,1):(c=!1,o<i&&(i=o));if(c){e.splice(u--,1);var a=r();void 0!==a&&(t=a)}}return t},d.n=function(e){var t=e&&e.__esModule?function(){return e.default}:function(){return e};return d.d(t,{a:t}),t},n=Object.getPrototypeOf?function(e){return Object.getPrototypeOf(e)}:function(e){return e.__proto__},d.t=function(e,r){if(1&r&&(e=this(e)),8&r||"object"==typeof e&&e&&(4&r&&e.__esModule||16&r&&"function"==typeof e.then))return e;var o=Object.create(null);d.r(o);var u={};t=t||[null,n({}),n([]),n(n)];for(var i=2&r&&e;"object"==typeof i&&!~t.indexOf(i);i=n(i))Object.getOwnPropertyNames(i).forEach(function(t){u[t]=function(){return e[t]}});return u.default=function(){return e},d.d(o,u),o},d.d=function(e,t){for(var n in t)d.o(t,n)&&!d.o(e,n)&&Object.defineProperty(e,n,{enumerable:!0,get:t[n]})},d.f={},d.e=function(e){return Promise.all(Object.keys(d.f).reduce(function(t,n){return d.f[n](e,t),t},[]))},d.u=function(e){},d.miniCssF=function(e){return"static/css/cd10067a0a3408b4.css"},d.g=function(){if("object"==typeof globalThis)return globalThis;try{return this||Function("return this")()}catch(e){if("object"==typeof window)return window}}(),d.o=function(e,t){return Object.prototype.hasOwnProperty.call(e,t)},r={},o="_N_E:",d.l=function(e,t,n,u){if(r[e]){r[e].push(t);return}if(void 0!==n)for(var i,c,f=document.getElementsByTagName("script"),a=0;a<f.length;a++){var l=f[a];if(l.getAttribute("src")==e||l.getAttribute("data-webpack")==o+n){i=l;break}}i||(c=!0,(i=document.createElement("script")).charset="utf-8",i.timeout=120,d.nc&&i.setAttribute("nonce",d.nc),i.setAttribute("data-webpack",o+n),i.src=d.tu(e)),r[e]=[t];var s=function(t,n){i.onerror=i.onload=null,clearTimeout(p);var o=r[e];if(delete r[e],i.parentNode&&i.parentNode.removeChild(i),o&&o.forEach(function(e){return e(n)}),t)return t(n)},p=setTimeout(s.bind(null,void 0,{type:"timeout",target:i}),12e4);i.onerror=s.bind(null,i.onerror),i.onload=s.bind(null,i.onload),c&&document.head.appendChild(i)},d.r=function(e){"undefined"!=typeof Symbol&&Symbol.toStringTag&&Object.defineProperty(e,Symbol.toStringTag,{value:"Module"}),Object.defineProperty(e,"__esModule",{value:!0})},d.nmd=function(e){return e.paths=[],e.children||(e.children=[]),e},d.tt=function(){return void 0===u&&(u={createScriptURL:function(e){return e}},"undefined"!=typeof trustedTypes&&trustedTypes.createPolicy&&(u=trustedTypes.createPolicy("nextjs#bundler",u))),u},d.tu=function(e){return d.tt().createScriptURL(e)},d.p="/ui/_next/",i={272:0},d.f.j=function(e,t){var n=d.o(i,e)?i[e]:void 0;if(0!==n){if(n)t.push(n[2]);else if(272!=e){var r=new Promise(function(t,r){n=i[e]=[t,r]});t.push(n[2]=r);var o=d.p+d.u(e),u=Error();d.l(o,function(t){if(d.o(i,e)&&(0!==(n=i[e])&&(i[e]=void 0),n)){var r=t&&("load"===t.type?"missing":t.type),o=t&&t.target&&t.target.src;u.message="Loading chunk "+e+" failed.\n("+r+": "+o+")",u.name="ChunkLoadError",u.type=r,u.request=o,n[1](u)}},"chunk-"+e,e)}else i[e]=0}},d.O.j=function(e){return 0===i[e]},c=function(e,t){var n,r,o=t[0],u=t[1],c=t[2],f=0;if(o.some(function(e){return 0!==i[e]})){for(n in u)d.o(u,n)&&(d.m[n]=u[n]);if(c)var a=c(d)}for(e&&e(t);f<o.length;f++)r=o[f],d.o(i,r)&&i[r]&&i[r][0](),i[r]=0;return d.O(a)},(f=self.webpackChunk_N_E=self.webpackChunk_N_E||[]).forEach(c.bind(null,0)),f.push=c.bind(null,f.push.bind(f))}();
|
||||
File diff suppressed because one or more lines are too long
|
|
@ -1 +0,0 @@
|
|||
self.__BUILD_MANIFEST={__rewrites:{afterFiles:[],beforeFiles:[],fallback:[]},"/_error":["static/chunks/pages/_error-d6107f1aac0c574c.js"],sortedPages:["/_app","/_error"]},self.__BUILD_MANIFEST_CB&&self.__BUILD_MANIFEST_CB();
|
||||
|
|
@ -1 +0,0 @@
|
|||
self.__SSG_MANIFEST=new Set([]);self.__SSG_MANIFEST_CB&&self.__SSG_MANIFEST_CB()
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
|
@ -1 +1 @@
|
|||
<!DOCTYPE html><html id="__next_error__"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="script" fetchPriority="low" href="/ui/_next/static/chunks/webpack-193a7eac80c8baba.js" crossorigin=""/><script src="/ui/_next/static/chunks/fd9d1056-f593049e31b05aeb.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/69-8316d07d1f41e39f.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/main-app-9b4fb13a7db53edf.js" async="" crossorigin=""></script><title>LiteLLM Dashboard</title><meta name="description" content="LiteLLM Proxy Admin UI"/><link rel="icon" href="/ui/favicon.ico" type="image/x-icon" sizes="16x16"/><meta name="next-size-adjust"/><script src="/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js" crossorigin="" noModule=""></script></head><body><script src="/ui/_next/static/chunks/webpack-193a7eac80c8baba.js" crossorigin="" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0]);self.__next_f.push([2,null])</script><script>self.__next_f.push([1,"1:HL[\"/ui/_next/static/media/a34f9d1faa5f3315-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n2:HL[\"/ui/_next/static/css/cd10067a0a3408b4.css\",\"style\",{\"crossOrigin\":\"\"}]\n0:\"$L3\"\n"])</script><script>self.__next_f.push([1,"4:I[47690,[],\"\"]\n6:I[77831,[],\"\"]\n7:I[48951,[\"665\",\"static/chunks/3014691f-b24e8254c7593934.js\",\"936\",\"static/chunks/2f6dbc85-cac2949a76539886.js\",\"505\",\"static/chunks/505-5ff3c318fddfa35c.js\",\"131\",\"static/chunks/131-cb6bfe24e23e121b.js\",\"684\",\"static/chunks/684-16b194c83a169f6d.js\",\"759\",\"static/chunks/759-c0083d8a782d300e.js\",\"777\",\"static/chunks/777-0a0bacbc160c02d3.js\",\"931\",\"static/chunks/app/page-913f3589403bc802.js\"],\"\"]\n8:I[5613,[],\"\"]\n9:I[31778,[],\"\"]\nb:I[48955,[],\"\"]\nc:[]\n"])</script><script>self.__next_f.push([1,"3:[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/ui/_next/static/css/cd10067a0a3408b4.css\",\"precedence\":\"next\",\"crossOrigin\":\"\"}]],[\"$\",\"$L4\",null,{\"buildId\":\"dWa6RZpZ5Z2Qhqv0Hff_m\",\"assetPrefix\":\"/ui\",\"initialCanonicalUrl\":\"/\",\"initialTree\":[\"\",{\"children\":[\"__PAGE__\",{}]},\"$undefined\",\"$undefined\",true],\"initialSeedData\":[\"\",{\"children\":[\"__PAGE__\",{},[\"$L5\",[\"$\",\"$L6\",null,{\"propsForComponent\":{\"params\":{}},\"Component\":\"$7\",\"isStaticGeneration\":true}],null]]},[null,[\"$\",\"html\",null,{\"lang\":\"en\",\"children\":[\"$\",\"body\",null,{\"className\":\"__className_86ef86\",\"children\":[\"$\",\"$L8\",null,{\"parallelRouterKey\":\"children\",\"segmentPath\":[\"children\"],\"loading\":\"$undefined\",\"loadingStyles\":\"$undefined\",\"loadingScripts\":\"$undefined\",\"hasLoading\":false,\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L9\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"title\",null,{\"children\":\"404: This page could not be found.\"}],[\"$\",\"div\",null,{\"style\":{\"fontFamily\":\"system-ui,\\\"Segoe UI\\\",Roboto,Helvetica,Arial,sans-serif,\\\"Apple Color Emoji\\\",\\\"Segoe UI Emoji\\\"\",\"height\":\"100vh\",\"textAlign\":\"center\",\"display\":\"flex\",\"flexDirection\":\"column\",\"alignItems\":\"center\",\"justifyContent\":\"center\"},\"children\":[\"$\",\"div\",null,{\"children\":[[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}\"}}],[\"$\",\"h1\",null,{\"className\":\"next-error-h1\",\"style\":{\"display\":\"inline-block\",\"margin\":\"0 20px 0 0\",\"padding\":\"0 23px 0 0\",\"fontSize\":24,\"fontWeight\":500,\"verticalAlign\":\"top\",\"lineHeight\":\"49px\"},\"children\":\"404\"}],[\"$\",\"div\",null,{\"style\":{\"display\":\"inline-block\"},\"children\":[\"$\",\"h2\",null,{\"style\":{\"fontSize\":14,\"fontWeight\":400,\"lineHeight\":\"49px\",\"margin\":0},\"children\":\"This page could not be found.\"}]}]]}]}]],\"notFoundStyles\":[],\"styles\":null}]}]}],null]],\"initialHead\":[false,\"$La\"],\"globalErrorComponent\":\"$b\",\"missingSlots\":\"$Wc\"}]]\n"])</script><script>self.__next_f.push([1,"a:[[\"$\",\"meta\",\"0\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"1\",{\"charSet\":\"utf-8\"}],[\"$\",\"title\",\"2\",{\"children\":\"LiteLLM Dashboard\"}],[\"$\",\"meta\",\"3\",{\"name\":\"description\",\"content\":\"LiteLLM Proxy Admin UI\"}],[\"$\",\"link\",\"4\",{\"rel\":\"icon\",\"href\":\"/ui/favicon.ico\",\"type\":\"image/x-icon\",\"sizes\":\"16x16\"}],[\"$\",\"meta\",\"5\",{\"name\":\"next-size-adjust\"}]]\n5:null\n"])</script><script>self.__next_f.push([1,""])</script></body></html>
|
||||
<!DOCTYPE html><html id="__next_error__"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="preload" as="script" fetchPriority="low" href="/ui/_next/static/chunks/webpack-2d07f7d2618f9dfc.js" crossorigin=""/><script src="/ui/_next/static/chunks/fd9d1056-f593049e31b05aeb.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/69-8316d07d1f41e39f.js" async="" crossorigin=""></script><script src="/ui/_next/static/chunks/main-app-096338c8e1915716.js" async="" crossorigin=""></script><title>LiteLLM Dashboard</title><meta name="description" content="LiteLLM Proxy Admin UI"/><link rel="icon" href="/ui/favicon.ico" type="image/x-icon" sizes="16x16"/><meta name="next-size-adjust"/><script src="/ui/_next/static/chunks/polyfills-c67a75d1b6f99dc8.js" crossorigin="" noModule=""></script></head><body><script src="/ui/_next/static/chunks/webpack-2d07f7d2618f9dfc.js" crossorigin="" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0]);self.__next_f.push([2,null])</script><script>self.__next_f.push([1,"1:HL[\"/ui/_next/static/media/c9a5bc6a7c948fb0-s.p.woff2\",\"font\",{\"crossOrigin\":\"\",\"type\":\"font/woff2\"}]\n2:HL[\"/ui/_next/static/css/051d7321f11572d4.css\",\"style\",{\"crossOrigin\":\"\"}]\n0:\"$L3\"\n"])</script><script>self.__next_f.push([1,"4:I[47690,[],\"\"]\n6:I[77831,[],\"\"]\n7:I[26520,[\"665\",\"static/chunks/3014691f-b24e8254c7593934.js\",\"936\",\"static/chunks/2f6dbc85-cac2949a76539886.js\",\"505\",\"static/chunks/505-5ff3c318fddfa35c.js\",\"131\",\"static/chunks/131-cb6bfe24e23e121b.js\",\"684\",\"static/chunks/684-16b194c83a169f6d.js\",\"605\",\"static/chunks/605-8e4b96f972af8eaf.js\",\"777\",\"static/chunks/777-50d836152fad178b.js\",\"931\",\"static/chunks/app/page-5b7e51de07f1b89a.js\"],\"\"]\n8:I[5613,[],\"\"]\n9:I[31778,[],\"\"]\nb:I[48955,[],\"\"]\nc:[]\n"])</script><script>self.__next_f.push([1,"3:[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/ui/_next/static/css/051d7321f11572d4.css\",\"precedence\":\"next\",\"crossOrigin\":\"\"}]],[\"$\",\"$L4\",null,{\"buildId\":\"bNZcj3BOVnvWu7auSxFn-\",\"assetPrefix\":\"/ui\",\"initialCanonicalUrl\":\"/\",\"initialTree\":[\"\",{\"children\":[\"__PAGE__\",{}]},\"$undefined\",\"$undefined\",true],\"initialSeedData\":[\"\",{\"children\":[\"__PAGE__\",{},[\"$L5\",[\"$\",\"$L6\",null,{\"propsForComponent\":{\"params\":{}},\"Component\":\"$7\",\"isStaticGeneration\":true}],null]]},[null,[\"$\",\"html\",null,{\"lang\":\"en\",\"children\":[\"$\",\"body\",null,{\"className\":\"__className_12bbc4\",\"children\":[\"$\",\"$L8\",null,{\"parallelRouterKey\":\"children\",\"segmentPath\":[\"children\"],\"loading\":\"$undefined\",\"loadingStyles\":\"$undefined\",\"loadingScripts\":\"$undefined\",\"hasLoading\":false,\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L9\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"title\",null,{\"children\":\"404: This page could not be found.\"}],[\"$\",\"div\",null,{\"style\":{\"fontFamily\":\"system-ui,\\\"Segoe UI\\\",Roboto,Helvetica,Arial,sans-serif,\\\"Apple Color Emoji\\\",\\\"Segoe UI Emoji\\\"\",\"height\":\"100vh\",\"textAlign\":\"center\",\"display\":\"flex\",\"flexDirection\":\"column\",\"alignItems\":\"center\",\"justifyContent\":\"center\"},\"children\":[\"$\",\"div\",null,{\"children\":[[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}\"}}],[\"$\",\"h1\",null,{\"className\":\"next-error-h1\",\"style\":{\"display\":\"inline-block\",\"margin\":\"0 20px 0 0\",\"padding\":\"0 23px 0 0\",\"fontSize\":24,\"fontWeight\":500,\"verticalAlign\":\"top\",\"lineHeight\":\"49px\"},\"children\":\"404\"}],[\"$\",\"div\",null,{\"style\":{\"display\":\"inline-block\"},\"children\":[\"$\",\"h2\",null,{\"style\":{\"fontSize\":14,\"fontWeight\":400,\"lineHeight\":\"49px\",\"margin\":0},\"children\":\"This page could not be found.\"}]}]]}]}]],\"notFoundStyles\":[],\"styles\":null}]}]}],null]],\"initialHead\":[false,\"$La\"],\"globalErrorComponent\":\"$b\",\"missingSlots\":\"$Wc\"}]]\n"])</script><script>self.__next_f.push([1,"a:[[\"$\",\"meta\",\"0\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"1\",{\"charSet\":\"utf-8\"}],[\"$\",\"title\",\"2\",{\"children\":\"LiteLLM Dashboard\"}],[\"$\",\"meta\",\"3\",{\"name\":\"description\",\"content\":\"LiteLLM Proxy Admin UI\"}],[\"$\",\"link\",\"4\",{\"rel\":\"icon\",\"href\":\"/ui/favicon.ico\",\"type\":\"image/x-icon\",\"sizes\":\"16x16\"}],[\"$\",\"meta\",\"5\",{\"name\":\"next-size-adjust\"}]]\n5:null\n"])</script><script>self.__next_f.push([1,""])</script></body></html>
|
||||
|
|
@ -1,7 +1,7 @@
|
|||
2:I[77831,[],""]
|
||||
3:I[48951,["665","static/chunks/3014691f-b24e8254c7593934.js","936","static/chunks/2f6dbc85-cac2949a76539886.js","505","static/chunks/505-5ff3c318fddfa35c.js","131","static/chunks/131-cb6bfe24e23e121b.js","684","static/chunks/684-16b194c83a169f6d.js","759","static/chunks/759-c0083d8a782d300e.js","777","static/chunks/777-0a0bacbc160c02d3.js","931","static/chunks/app/page-913f3589403bc802.js"],""]
|
||||
3:I[26520,["665","static/chunks/3014691f-b24e8254c7593934.js","936","static/chunks/2f6dbc85-cac2949a76539886.js","505","static/chunks/505-5ff3c318fddfa35c.js","131","static/chunks/131-cb6bfe24e23e121b.js","684","static/chunks/684-16b194c83a169f6d.js","605","static/chunks/605-8e4b96f972af8eaf.js","777","static/chunks/777-50d836152fad178b.js","931","static/chunks/app/page-5b7e51de07f1b89a.js"],""]
|
||||
4:I[5613,[],""]
|
||||
5:I[31778,[],""]
|
||||
0:["dWa6RZpZ5Z2Qhqv0Hff_m",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_86ef86","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/cd10067a0a3408b4.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
|
||||
0:["bNZcj3BOVnvWu7auSxFn-",[[["",{"children":["__PAGE__",{}]},"$undefined","$undefined",true],["",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_12bbc4","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/051d7321f11572d4.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
|
||||
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/ui/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","meta","5",{"name":"next-size-adjust"}]]
|
||||
1:null
|
||||
|
|
|
|||
File diff suppressed because one or more lines are too long
|
|
@ -1,7 +1,7 @@
|
|||
2:I[77831,[],""]
|
||||
3:I[87494,["505","static/chunks/505-5ff3c318fddfa35c.js","131","static/chunks/131-cb6bfe24e23e121b.js","777","static/chunks/777-0a0bacbc160c02d3.js","418","static/chunks/app/model_hub/page-370c82f0dada594a.js"],""]
|
||||
3:I[87494,["505","static/chunks/505-5ff3c318fddfa35c.js","131","static/chunks/131-cb6bfe24e23e121b.js","777","static/chunks/777-50d836152fad178b.js","418","static/chunks/app/model_hub/page-39740ed413adc0ec.js"],""]
|
||||
4:I[5613,[],""]
|
||||
5:I[31778,[],""]
|
||||
0:["dWa6RZpZ5Z2Qhqv0Hff_m",[[["",{"children":["model_hub",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub","children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined","styles":null}]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_86ef86","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/cd10067a0a3408b4.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
|
||||
0:["bNZcj3BOVnvWu7auSxFn-",[[["",{"children":["model_hub",{"children":["__PAGE__",{}]}]},"$undefined","$undefined",true],["",{"children":["model_hub",{"children":["__PAGE__",{},["$L1",["$","$L2",null,{"propsForComponent":{"params":{}},"Component":"$3","isStaticGeneration":true}],null]]},["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children","model_hub","children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":"$undefined","notFoundStyles":"$undefined","styles":null}]]},[null,["$","html",null,{"lang":"en","children":["$","body",null,{"className":"__className_12bbc4","children":["$","$L4",null,{"parallelRouterKey":"children","segmentPath":["children"],"loading":"$undefined","loadingStyles":"$undefined","loadingScripts":"$undefined","hasLoading":false,"error":"$undefined","errorStyles":"$undefined","errorScripts":"$undefined","template":["$","$L5",null,{}],"templateStyles":"$undefined","templateScripts":"$undefined","notFound":[["$","title",null,{"children":"404: This page could not be found."}],["$","div",null,{"style":{"fontFamily":"system-ui,\"Segoe UI\",Roboto,Helvetica,Arial,sans-serif,\"Apple Color Emoji\",\"Segoe UI Emoji\"","height":"100vh","textAlign":"center","display":"flex","flexDirection":"column","alignItems":"center","justifyContent":"center"},"children":["$","div",null,{"children":[["$","style",null,{"dangerouslySetInnerHTML":{"__html":"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}"}}],["$","h1",null,{"className":"next-error-h1","style":{"display":"inline-block","margin":"0 20px 0 0","padding":"0 23px 0 0","fontSize":24,"fontWeight":500,"verticalAlign":"top","lineHeight":"49px"},"children":"404"}],["$","div",null,{"style":{"display":"inline-block"},"children":["$","h2",null,{"style":{"fontSize":14,"fontWeight":400,"lineHeight":"49px","margin":0},"children":"This page could not be found."}]}]]}]}]],"notFoundStyles":[],"styles":null}]}]}],null]],[[["$","link","0",{"rel":"stylesheet","href":"/ui/_next/static/css/051d7321f11572d4.css","precedence":"next","crossOrigin":""}]],"$L6"]]]]
|
||||
6:[["$","meta","0",{"name":"viewport","content":"width=device-width, initial-scale=1"}],["$","meta","1",{"charSet":"utf-8"}],["$","title","2",{"children":"LiteLLM Dashboard"}],["$","meta","3",{"name":"description","content":"LiteLLM Proxy Admin UI"}],["$","link","4",{"rel":"icon","href":"/ui/favicon.ico","type":"image/x-icon","sizes":"16x16"}],["$","meta","5",{"name":"next-size-adjust"}]]
|
||||
1:null
|
||||
|
|
|
|||
File diff suppressed because one or more lines are too long
Some files were not shown because too many files have changed in this diff Show more
Loading…
Add table
Reference in a new issue