LiteLLM Minor Fixes & Improvements (09/24/2024) (#5880)

* LiteLLM Minor Fixes & Improvements (09/23/2024)  (#5842)

* feat(auth_utils.py): enable admin to allow client-side credentials to be passed

Makes it easier for devs to experiment with finetuned fireworks ai models

* feat(router.py): allow setting configurable_clientside_auth_params for a model

Closes https://github.com/BerriAI/litellm/issues/5843

* build(model_prices_and_context_window.json): fix anthropic claude-3-5-sonnet max output token limit

Fixes https://github.com/BerriAI/litellm/issues/5850

* fix(azure_ai/): support content list for azure ai

Fixes https://github.com/BerriAI/litellm/issues/4237

* fix(litellm_logging.py): always set saved_cache_cost

Set to 0 by default

* fix(fireworks_ai/cost_calculator.py): add fireworks ai default pricing

handles calling 405b+ size models

* fix(slack_alerting.py): fix error alerting for failed spend tracking

Fixes regression with slack alerting error monitoring

* fix(vertex_and_google_ai_studio_gemini.py): handle gemini no candidates in streaming chunk error

* docs(bedrock.md): add llama3-1 models

* test: fix tests

* fix(azure_ai/chat): fix transformation for azure ai calls

* feat(azure_ai/embed): Add azure ai embeddings support

Closes https://github.com/BerriAI/litellm/issues/5861

* fix(azure_ai/embed): enable async embedding

* feat(azure_ai/embed): support azure ai multimodal embeddings

* fix(azure_ai/embed): support async multi modal embeddings

* feat(together_ai/embed): support together ai embedding calls

* feat(rerank/main.py): log source documents for rerank endpoints to langfuse

improves rerank endpoint logging

* fix(langfuse.py): support logging `/audio/speech` input to langfuse

* test(test_embedding.py): fix test

* test(test_completion_cost.py): fix helper util

litellm/main.py

@@ -83,7 +83,7 @@ from .llms import (
 from .llms.AI21 import completion as ai21
 from .llms.anthropic.chat import AnthropicChatCompletion
 from .llms.anthropic.completion import AnthropicTextCompletion
-from .llms.azure_ai.chat.handler import AzureAIChatCompletion
+from .llms.azure_ai import AzureAIChatCompletion, AzureAIEmbedding
 from .llms.azure_text import AzureTextCompletion
 from .llms.AzureOpenAI.audio_transcriptions import AzureAudioTranscription
 from .llms.AzureOpenAI.azure import AzureChatCompletion, _check_dynamic_azure_params
@@ -168,6 +168,7 @@ openai_o1_chat_completions = OpenAIO1ChatCompletion()
 openai_audio_transcriptions = OpenAIAudioTranscription()
 databricks_chat_completions = DatabricksChatCompletion()
 azure_ai_chat_completions = AzureAIChatCompletion()
+azure_ai_embedding = AzureAIEmbedding()
 anthropic_chat_completions = AnthropicChatCompletion()
 anthropic_text_completions = AnthropicTextCompletion()
 azure_chat_completions = AzureChatCompletion()
@@ -3215,6 +3216,8 @@ async def aembedding(*args, **kwargs) -> EmbeddingResponse:
             or custom_llm_provider == "cohere"
             or custom_llm_provider == "huggingface"
             or custom_llm_provider == "bedrock"
+            or custom_llm_provider == "azure_ai"
+            or custom_llm_provider == "together_ai"
         ):  # currently implemented aiohttp calls for just azure and openai, soon all.
             # Await normally
             init_response = await loop.run_in_executor(None, func_with_context)
@@ -3385,6 +3388,9 @@ def embedding(
         api_base=api_base,
         api_key=api_key,
     )
+    if dynamic_api_key is not None:
+        api_key = dynamic_api_key
+
     optional_params = get_optional_params_embeddings(
         model=model,
         user=user,
@@ -3481,7 +3487,9 @@ def embedding(
                 aembedding=aembedding,
             )
         elif (
-            model in litellm.open_ai_embedding_models or custom_llm_provider == "openai"
+            model in litellm.open_ai_embedding_models
+            or custom_llm_provider == "openai"
+            or custom_llm_provider == "together_ai"
         ):
             api_base = (
                 api_base
@@ -3832,6 +3840,33 @@ def embedding(
                 model_response=EmbeddingResponse(),
                 aembedding=aembedding,
             )
+        elif custom_llm_provider == "azure_ai":
+            api_base = (
+                api_base  # for deepinfra/perplexity/anyscale/groq/friendliai we check in get_llm_provider and pass in the api base from there
+                or litellm.api_base
+                or get_secret("AZURE_AI_API_BASE")
+            )
+            # set API KEY
+            api_key = (
+                api_key
+                or litellm.api_key  # for deepinfra/perplexity/anyscale/friendliai we check in get_llm_provider and pass in the api key from there
+                or litellm.openai_key
+                or get_secret("AZURE_AI_API_KEY")
+            )
+
+            ## EMBEDDING CALL
+            response = azure_ai_embedding.embedding(
+                model=model,
+                input=input,
+                api_base=api_base,
+                api_key=api_key,
+                logging_obj=logging,
+                timeout=timeout,
+                model_response=EmbeddingResponse(),
+                optional_params=optional_params,
+                client=client,
+                aembedding=aembedding,
+            )
         else:
             args = locals()
             raise ValueError(f"No valid embedding model args passed in - {args}")
@@ -4901,7 +4936,11 @@ def speech(
     aspeech: Optional[bool] = None,
     **kwargs,
 ) -> HttpxBinaryResponseContent:
-
+    user = kwargs.get("user", None)
+    litellm_call_id: Optional[str] = kwargs.get("litellm_call_id", None)
+    proxy_server_request = kwargs.get("proxy_server_request", None)
+    model_info = kwargs.get("model_info", None)
+    metadata = kwargs.get("metadata", {})
     model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider(model=model, custom_llm_provider=custom_llm_provider, api_base=api_base)  # type: ignore
     tags = kwargs.pop("tags", [])
 
@@ -4918,6 +4957,21 @@ def speech(
         max_retries = litellm.num_retries or openai.DEFAULT_MAX_RETRIES
 
     logging_obj = kwargs.get("litellm_logging_obj", None)
+    logging_obj.update_environment_variables(
+        model=model,
+        user=user,
+        optional_params={},
+        litellm_params={
+            "litellm_call_id": litellm_call_id,
+            "proxy_server_request": proxy_server_request,
+            "model_info": model_info,
+            "metadata": metadata,
+            "preset_cache_key": None,
+            "stream_response": {},
+            **kwargs,
+        },
+        custom_llm_provider=custom_llm_provider,
+    )
     response: Optional[HttpxBinaryResponseContent] = None
     if custom_llm_provider == "openai":
         if voice is None or not (isinstance(voice, str)):