scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-14 09:03:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 353

Merge 208209cd94 into aeede53112

Browse source
This commit is contained in:
drvt69talati 2026-11-06 15:51:18 -05:00 • committed by GitHub
commit d13f76db53
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 161 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/llms/openai_like/dynamic_config.py
View file

@ -99,7 +99,7 @@ def create_config_class(provider: SimpleProviderConfig):
resolved_base = provider.base_url
# Resolve API key
resolved_key: Final = api_key or get_secret_str(provider.api_key_env)
resolved_key: Final = api_key or get_secret_str(provider.api_key_env) or provider.default_api_key
return resolved_base, resolved_key

4
litellm/llms/openai_like/json_loader.py
View file

@ -25,6 +25,10 @@ class SimpleProviderConfig:
self.base_url = data["base_url"]
self.api_key_env: str = data["api_key_env"]
self.api_base_env: str | None = data.get("api_base_env")
# A local server that needs no key still has to be sent one: the OpenAI
# client refuses a request without it. Used only when neither the call
# nor api_key_env supplies a key, as LM Studio's "fake-api-key" is.
self.default_api_key: str | None = data.get("default_api_key")
self.base_class = data.get("base_class", "openai_gpt")
self.param_mappings = data.get("param_mappings", {})
self.constraints = data.get("constraints", {})

13
litellm/llms/openai_like/providers.json
View file

@ -283,6 +283,19 @@
"/v1/responses"
]
},
"llamay": {
"base_url": "http://localhost:11435/v1",
"api_key_env": "LLAMAY_API_KEY",
"api_base_env": "LLAMAY_API_BASE",
"default_api_key": "fake-api-key",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"provider_info": {
"supports_function_calling": true
}
},
"kyma": {
"base_url": "https://kymaapi.com/v1",
"api_key_env": "KYMA_API_KEY",

26
litellm/provider_endpoints_support_backup.json
View file

@ -59,6 +59,32 @@
"generateContent": true
}
},
"llamay": {
"display_name": "llamay (`llamay`)",
"url": "https://docs.litellm.ai/docs/providers/llamay",
"endpoints": {
"chat_completions": true,
"responses": true,
"text_completion": false,
"embeddings": false,
"image_generations": false,
"image_edits": false,
"audio_transcriptions": false,
"audio_speech": false,
"rerank": false,
"ocr": false,
"search": false,
"moderations": false,
"realtime": false,
"video_generations": false,
"batches": false,
"messages": true,
"interactions": false,
"systemone": false,
"a2a": false,
"generateContent": false
}
},
"a2a": {
"display_name": "A2A (Agent-to-Agent) (`a2a`)",
"url": "https://docs.litellm.ai/docs/providers/a2a",

28
litellm/proxy/public_endpoints/provider_create_fields.json
View file

@ -3483,6 +3483,34 @@
],
"default_model_placeholder": "refuseless/glm-5.3-abliterated"
},
{
"provider": "LLAMAY",
"provider_display_name": "llamay",
"litellm_provider": "llamay",
"credential_fields": [
{
"key": "api_base",
"label": "API Base",
"placeholder": "http://localhost:11435/v1",
"tooltip": "Optional. Leave blank for a llamay server on this machine.",
"required": false,
"field_type": "text",
"options": null,
"default_value": null
},
{
"key": "api_key",
"label": "API Key",
"placeholder": null,
"tooltip": "Only needed when the server was started with LLAMAY_API_KEY.",
"required": false,
"field_type": "password",
"options": null,
"default_value": null
}
],
"default_model_placeholder": "llamay/qwen2.5:0.5b"
},
{
"provider": "REPLICATE",
"provider_display_name": "Replicate",

1
litellm/types/utils.py
View file

@ -4612,6 +4612,7 @@ GenericBudgetConfigType = dict[str, BudgetConfig]
class LlmProviders(str, Enum):
REFUSELESS = "refuseless"
LLAMAY = "llamay"
OPENAI = "openai"
CHATGPT = "chatgpt"
OPENAI_LIKE = "openai_like" # embedding only

26
provider_endpoints_support.json
View file

@ -59,6 +59,32 @@
"generateContent": true
}
},
"llamay": {
"display_name": "llamay (`llamay`)",
"url": "https://docs.litellm.ai/docs/providers/llamay",
"endpoints": {
"chat_completions": true,
"responses": true,
"text_completion": false,
"embeddings": false,
"image_generations": false,
"image_edits": false,
"audio_transcriptions": false,
"audio_speech": false,
"rerank": false,
"ocr": false,
"search": false,
"moderations": false,
"realtime": false,
"video_generations": false,
"batches": false,
"messages": true,
"interactions": false,
"systemone": false,
"a2a": false,
"generateContent": false
}
},
"a2a": {
"display_name": "A2A (Agent-to-Agent) (`a2a`)",
"url": "https://docs.litellm.ai/docs/providers/a2a",

62
tests/unit/llms/openai_like/test_llamay_provider.py Normal file
View file

@ -0,0 +1,62 @@
import json
from typing import Final
import pytest
import respx
import litellm
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
def test_llamay_needs_no_key_on_this_machine(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.delenv("LLAMAY_API_KEY", raising=False)
monkeypatch.delenv("LLAMAY_API_BASE", raising=False)
assert get_llm_provider(model="llamay/qwen2.5:0.5b") == (
"qwen2.5:0.5b",
"llamay",
"fake-api-key",
"http://localhost:11435/v1",
)
def test_llamay_reads_a_key_and_base_from_the_environment(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("LLAMAY_API_KEY", "fake-environment-key")
monkeypatch.setenv("LLAMAY_API_BASE", "http://gpu-box:11435/v1")
assert get_llm_provider(model="llamay/hf.co/bartowski/Qwen2.5-Coder-1.5B-Instruct-GGUF:Q4_K_M") == (
"hf.co/bartowski/Qwen2.5-Coder-1.5B-Instruct-GGUF:Q4_K_M",
"llamay",
"fake-environment-key",
"http://gpu-box:11435/v1",
)
def test_an_explicit_key_and_base_win(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("LLAMAY_API_KEY", "fake-environment-key")
assert get_llm_provider(
model="llamay/qwen2.5:0.5b", api_key="fake-explicit-key", api_base="http://other:11435/v1"
) == ("qwen2.5:0.5b", "llamay", "fake-explicit-key", "http://other:11435/v1")
def test_llamay_chat_reaches_the_local_server(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.delenv("LLAMAY_API_KEY", raising=False)
monkeypatch.delenv("LLAMAY_API_BASE", raising=False)
with respx.mock() as upstream:
route: Final = upstream.post("http://localhost:11435/v1/chat/completions").respond(
200,
json={
"id": "chatcmpl-test",
"object": "chat.completion",
"created": 1,
"model": "qwen2.5:0.5b",
"choices": [
{"index": 0, "message": {"role": "assistant", "content": "hello"}, "finish_reason": "stop"}
],
"usage": {"prompt_tokens": 10, "completion_tokens": 1, "total_tokens": 11},
},
)
response: Final = litellm.completion(
model="llamay/qwen2.5:0.5b", messages=[{"role": "user", "content": "Say hello"}]
)
body: Final = json.loads(route.calls.last.request.content)
assert body["model"] == "qwen2.5:0.5b"
assert response.choices[0].message.content == "hello"