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/cost_calculator.py

@@ -28,6 +28,7 @@ from litellm.llms.databricks.cost_calculator import (
 from litellm.llms.fireworks_ai.cost_calculator import (
     cost_per_token as fireworks_ai_cost_per_token,
 )
+from litellm.llms.together_ai.cost_calculator import get_model_params_and_category
 from litellm.rerank_api.types import RerankResponse
 from litellm.types.llms.openai import HttpxBinaryResponseContent
 from litellm.types.router import SPECIAL_MODEL_INFO_PARAMS
@@ -395,48 +396,6 @@ def cost_per_token(
         )
 
 
-# Extract the number of billion parameters from the model name
-# only used for together_computer LLMs
-def get_model_params_and_category(model_name) -> str:
-    """
-    Helper function for calculating together ai pricing.
-
-    Returns
-    - str - model pricing category if mapped else received model name
-    """
-    import re
-
-    model_name = model_name.lower()
-    re_params_match = re.search(
-        r"(\d+b)", model_name
-    )  # catch all decimals like 3b, 70b, etc
-    category = None
-    if re_params_match is not None:
-        params_match = str(re_params_match.group(1))
-        params_match = params_match.replace("b", "")
-        if params_match is not None:
-            params_billion = float(params_match)
-        else:
-            return model_name
-        # Determine the category based on the number of parameters
-        if params_billion <= 4.0:
-            category = "together-ai-up-to-4b"
-        elif params_billion <= 8.0:
-            category = "together-ai-4.1b-8b"
-        elif params_billion <= 21.0:
-            category = "together-ai-8.1b-21b"
-        elif params_billion <= 41.0:
-            category = "together-ai-21.1b-41b"
-        elif params_billion <= 80.0:
-            category = "together-ai-41.1b-80b"
-        elif params_billion <= 110.0:
-            category = "together-ai-81.1b-110b"
-        if category is not None:
-            return category
-
-    return model_name
-
-
 def get_replicate_completion_pricing(completion_response: dict, total_time=0.0):
     # see https://replicate.com/pricing
     # for all litellm currently supported LLMs, almost all requests go to a100_80gb
@@ -477,7 +436,7 @@ def _select_model_name_for_cost_calc(
     if isinstance(completion_response, str):
         return return_model
 
-    elif return_model is None:
+    elif return_model is None and hasattr(completion_response, "get"):
         return_model = completion_response.get("model", "")  # type: ignore
     hidden_params = getattr(completion_response, "_hidden_params", None)
 
@@ -716,7 +675,9 @@ def completion_cost(
         ):
             # together ai prices based on size of llm
             # get_model_params_and_category takes a model name and returns the category of LLM size it is in model_prices_and_context_window.json
-            model = get_model_params_and_category(model)
+
+            model = get_model_params_and_category(model, call_type=CallTypes(call_type))
+
         # replicate llms are calculate based on time for request running
         # see https://replicate.com/pricing
         elif (