Merge pull request #3331 from BerriAI/litellm_common_auth_params

feat(utils.py): unify common auth params across azure/vertex_ai/bedrock/watsonx

docs/my-website/docs/set_keys.md

@@ -5,6 +5,9 @@ LiteLLM allows you to specify the following:
 * API Base
 * API Version
 * API Type
+* Project
+* Location
+* Token
 
 Useful Helper functions: 
 * [`check_valid_key()`](#check_valid_key)
@@ -43,6 +46,24 @@ os.environ['AZURE_API_TYPE'] = "azure" # [OPTIONAL]
 os.environ['OPENAI_API_BASE'] = "https://openai-gpt-4-test2-v-12.openai.azure.com/"
 ```
 
+### Setting Project, Location, Token
+
+For cloud providers:
+- Azure
+- Bedrock
+- GCP
+- Watson AI 
+
+you might need to set additional parameters. LiteLLM provides a common set of params, that we map across all providers. 
+
+|      | LiteLLM param | Watson       | Vertex AI    | Azure        | Bedrock      |
+|------|--------------|--------------|--------------|--------------|--------------|
+| Project | project | watsonx_project | vertex_project | n/a | n/a |
+| Region | region_name | watsonx_region_name | vertex_location | n/a | aws_region_name |
+| Token | token | watsonx_token or token | n/a | azure_ad_token | n/a |
+
+If you want, you can call them by their provider-specific params as well. 
+
 ## litellm variables
 
 ### litellm.api_key

litellm/__init__.py

@@ -59,6 +59,7 @@ max_tokens = 256  # OpenAI Defaults
 drop_params = False
 modify_params = False
 retry = True
+### AUTH ###
 api_key: Optional[str] = None
 openai_key: Optional[str] = None
 azure_key: Optional[str] = None
@@ -77,6 +78,10 @@ cloudflare_api_key: Optional[str] = None
 baseten_key: Optional[str] = None
 aleph_alpha_key: Optional[str] = None
 nlp_cloud_key: Optional[str] = None
+common_cloud_provider_auth_params: dict = {
+    "params": ["project", "region_name", "token"],
+    "providers": ["vertex_ai", "bedrock", "watsonx", "azure"],
+}
 use_client: bool = False
 ssl_verify: bool = True
 disable_streaming_logging: bool = False
@@ -655,6 +660,7 @@ from .llms.bedrock import (
     AmazonLlamaConfig,
     AmazonStabilityConfig,
     AmazonMistralConfig,
+    AmazonBedrockGlobalConfig,
 )
 from .llms.openai import OpenAIConfig, OpenAITextCompletionConfig
 from .llms.azure import AzureOpenAIConfig, AzureOpenAIError

litellm/llms/azure.py

@@ -96,6 +96,15 @@ class AzureOpenAIConfig(OpenAIConfig):
             top_p,
         )
 
+    def get_mapped_special_auth_params(self) -> dict:
+        return {"token": "azure_ad_token"}
+
+    def map_special_auth_params(self, non_default_params: dict, optional_params: dict):
+        for param, value in non_default_params.items():
+            if param == "token":
+                optional_params["azure_ad_token"] = value
+        return optional_params
+
 
 def select_azure_base_url_or_endpoint(azure_client_params: dict):
     # azure_client_params = {

litellm/llms/bedrock.py

@@ -29,6 +29,24 @@ class BedrockError(Exception):
         )  # Call the base class constructor with the parameters it needs
 
 
+class AmazonBedrockGlobalConfig:
+    def __init__(self):
+        pass
+
+    def get_mapped_special_auth_params(self) -> dict:
+        """
+        Mapping of common auth params across bedrock/vertex/azure/watsonx
+        """
+        return {"region_name": "aws_region_name"}
+
+    def map_special_auth_params(self, non_default_params: dict, optional_params: dict):
+        mapped_params = self.get_mapped_special_auth_params()
+        for param, value in non_default_params.items():
+            if param in mapped_params:
+                optional_params[mapped_params[param]] = value
+        return optional_params
+
+
 class AmazonTitanConfig:
     """
     Reference: https://us-west-2.console.aws.amazon.com/bedrock/home?region=us-west-2#/providers?model=titan-text-express-v1

litellm/llms/vertex_ai.py

@@ -184,6 +184,20 @@ class VertexAIConfig:
                 pass
         return optional_params
 
+    def get_mapped_special_auth_params(self) -> dict:
+        """
+        Common auth params across bedrock/vertex_ai/azure/watsonx
+        """
+        return {"project": "vertex_project", "region_name": "vertex_location"}
+
+    def map_special_auth_params(self, non_default_params: dict, optional_params: dict):
+        mapped_params = self.get_mapped_special_auth_params()
+
+        for param, value in non_default_params.items():
+            if param in mapped_params:
+                optional_params[mapped_params[param]] = value
+        return optional_params
+
 
 import asyncio
 

litellm/llms/watsonx.py

@@ -131,6 +131,24 @@ class IBMWatsonXAIConfig:
             "stream",  # equivalent to stream
         ]
 
+    def get_mapped_special_auth_params(self) -> dict:
+        """
+        Common auth params across bedrock/vertex_ai/azure/watsonx
+        """
+        return {
+            "project": "watsonx_project",
+            "region_name": "watsonx_region_name",
+            "token": "watsonx_token",
+        }
+
+    def map_special_auth_params(self, non_default_params: dict, optional_params: dict):
+        mapped_params = self.get_mapped_special_auth_params()
+
+        for param, value in non_default_params.items():
+            if param in mapped_params:
+                optional_params[mapped_params[param]] = value
+        return optional_params
+
 
 def convert_messages_to_prompt(model, messages, provider, custom_prompt_dict):
     # handle anthropic prompts and amazon titan prompts

litellm/tests/test_completion.py

@@ -2673,10 +2673,56 @@ def test_completion_watsonx():
         pytest.fail(f"Error occurred: {e}")
 
 
+@pytest.mark.parametrize(
+    "provider, model, project, region_name, token",
+    [
+        ("azure", "chatgpt-v-2", None, None, "test-token"),
+        ("vertex_ai", "anthropic-claude-3", "adroit-crow-1", "us-east1", None),
+        ("watsonx", "ibm/granite", "96946574", "dallas", "1234"),
+        ("bedrock", "anthropic.claude-3", None, "us-east-1", None),
+    ],
+)
+def test_unified_auth_params(provider, model, project, region_name, token):
+    """
+    Check if params = ["project", "region_name", "token"]
+    are correctly translated for = ["azure", "vertex_ai", "watsonx", "aws"]
+
+    tests get_optional_params
+    """
+    data = {
+        "project": project,
+        "region_name": region_name,
+        "token": token,
+        "custom_llm_provider": provider,
+        "model": model,
+    }
+
+    translated_optional_params = litellm.utils.get_optional_params(**data)
+
+    if provider == "azure":
+        special_auth_params = (
+            litellm.AzureOpenAIConfig().get_mapped_special_auth_params()
+        )
+    elif provider == "bedrock":
+        special_auth_params = (
+            litellm.AmazonBedrockGlobalConfig().get_mapped_special_auth_params()
+        )
+    elif provider == "vertex_ai":
+        special_auth_params = litellm.VertexAIConfig().get_mapped_special_auth_params()
+    elif provider == "watsonx":
+        special_auth_params = (
+            litellm.IBMWatsonXAIConfig().get_mapped_special_auth_params()
+        )
+
+    for param, value in special_auth_params.items():
+        assert param in data
+        assert value in translated_optional_params
+
+
 @pytest.mark.asyncio
 async def test_acompletion_watsonx():
     litellm.set_verbose = True
-    model_name = "watsonx/ibm/granite-13b-chat-v2"
+    model_name = "watsonx/deployment/" + os.getenv("WATSONX_DEPLOYMENT_ID")
     print("testing watsonx")
     try:
         response = await litellm.acompletion(

litellm/utils.py

@@ -4655,7 +4655,36 @@ def get_optional_params(
             k.startswith("vertex_") and custom_llm_provider != "vertex_ai"
         ):  # allow dynamically setting vertex ai init logic
             continue
+
         passed_params[k] = v
+
+    optional_params = {}
+
+    common_auth_dict = litellm.common_cloud_provider_auth_params
+    if custom_llm_provider in common_auth_dict["providers"]:
+        """
+        Check if params = ["project", "region_name", "token"]
+        and correctly translate for = ["azure", "vertex_ai", "watsonx", "aws"]
+        """
+        if custom_llm_provider == "azure":
+            optional_params = litellm.AzureOpenAIConfig().map_special_auth_params(
+                non_default_params=passed_params, optional_params=optional_params
+            )
+        elif custom_llm_provider == "bedrock":
+            optional_params = (
+                litellm.AmazonBedrockGlobalConfig().map_special_auth_params(
+                    non_default_params=passed_params, optional_params=optional_params
+                )
+            )
+        elif custom_llm_provider == "vertex_ai":
+            optional_params = litellm.VertexAIConfig().map_special_auth_params(
+                non_default_params=passed_params, optional_params=optional_params
+            )
+        elif custom_llm_provider == "watsonx":
+            optional_params = litellm.IBMWatsonXAIConfig().map_special_auth_params(
+                non_default_params=passed_params, optional_params=optional_params
+            )
+
     default_params = {
         "functions": None,
         "function_call": None,
@@ -4691,7 +4720,7 @@ def get_optional_params(
             and v != default_params[k]
         )
     }
-    optional_params = {}
+
     ## raise exception if function calling passed in for a provider that doesn't support it
     if (
         "functions" in non_default_params
@@ -10125,6 +10154,21 @@ class CustomStreamWrapper:
             elif self.custom_llm_provider == "watsonx":
                 response_obj = self.handle_watsonx_stream(chunk)
                 completion_obj["content"] = response_obj["text"]
+                print_verbose(f"completion obj content: {completion_obj['content']}")
+                if response_obj.get("prompt_tokens") is not None:
+                    prompt_token_count = getattr(
+                        model_response.usage, "prompt_tokens", 0
+                    )
+                    model_response.usage.prompt_tokens = (
+                        prompt_token_count + response_obj["prompt_tokens"]
+                    )
+                if response_obj.get("completion_tokens") is not None:
+                    model_response.usage.completion_tokens = response_obj[
+                        "completion_tokens"
+                    ]
+                model_response.usage.total_tokens = getattr(
+                    model_response.usage, "prompt_tokens", 0
+                ) + getattr(model_response.usage, "completion_tokens", 0)
                 if response_obj["is_finished"]:
                     self.received_finish_reason = response_obj["finish_reason"]
             elif self.custom_llm_provider == "text-completion-openai":