mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 03:04:13 +00:00
LiteLLM Minor Fixes & Improvements (10/28/2024) (#6475)
* fix(anthropic/chat/transformation.py): support anthropic disable_parallel_tool_use param Fixes https://github.com/BerriAI/litellm/issues/6456 * feat(anthropic/chat/transformation.py): support anthropic computer tool use Closes https://github.com/BerriAI/litellm/issues/6427 * fix(vertex_ai/common_utils.py): parse out '$schema' when calling vertex ai Fixes issue when trying to call vertex from vercel sdk * fix(main.py): add 'extra_headers' support for azure on all translation endpoints Fixes https://github.com/BerriAI/litellm/issues/6465 * fix: fix linting errors * fix(transformation.py): handle no beta headers for anthropic * test: cleanup test * fix: fix linting error * fix: fix linting errors * fix: fix linting errors * fix(transformation.py): handle dummy tool call * fix(main.py): fix linting error * fix(azure.py): pass required param * LiteLLM Minor Fixes & Improvements (10/24/2024) (#6441) * fix(azure.py): handle /openai/deployment in azure api base * fix(factory.py): fix faulty anthropic tool result translation check Fixes https://github.com/BerriAI/litellm/issues/6422 * fix(gpt_transformation.py): add support for parallel_tool_calls to azure Fixes https://github.com/BerriAI/litellm/issues/6440 * fix(factory.py): support anthropic prompt caching for tool results * fix(vertex_ai/common_utils): don't pop non-null required field Fixes https://github.com/BerriAI/litellm/issues/6426 * feat(vertex_ai.py): support code_execution tool call for vertex ai + gemini Closes https://github.com/BerriAI/litellm/issues/6434 * build(model_prices_and_context_window.json): Add 'supports_assistant_prefill' for bedrock claude-3-5-sonnet v2 models Closes https://github.com/BerriAI/litellm/issues/6437 * fix(types/utils.py): fix linting * test: update test to include required fields * test: fix test * test: handle flaky test * test: remove e2e test - hitting gemini rate limits * Litellm dev 10 26 2024 (#6472) * docs(exception_mapping.md): add missing exception types Fixes https://github.com/Aider-AI/aider/issues/2120#issuecomment-2438971183 * fix(main.py): register custom model pricing with specific key Ensure custom model pricing is registered to the specific model+provider key combination * test: make testing more robust for custom pricing * fix(redis_cache.py): instrument otel logging for sync redis calls ensures complete coverage for all redis cache calls * (Testing) Add unit testing for DualCache - ensure in memory cache is used when expected (#6471) * test test_dual_cache_get_set * unit testing for dual cache * fix async_set_cache_sadd * test_dual_cache_local_only * redis otel tracing + async support for latency routing (#6452) * docs(exception_mapping.md): add missing exception types Fixes https://github.com/Aider-AI/aider/issues/2120#issuecomment-2438971183 * fix(main.py): register custom model pricing with specific key Ensure custom model pricing is registered to the specific model+provider key combination * test: make testing more robust for custom pricing * fix(redis_cache.py): instrument otel logging for sync redis calls ensures complete coverage for all redis cache calls * refactor: pass parent_otel_span for redis caching calls in router allows for more observability into what calls are causing latency issues * test: update tests with new params * refactor: ensure e2e otel tracing for router * refactor(router.py): add more otel tracing acrosss router catch all latency issues for router requests * fix: fix linting error * fix(router.py): fix linting error * fix: fix test * test: fix tests * fix(dual_cache.py): pass ttl to redis cache * fix: fix param * fix(dual_cache.py): set default value for parent_otel_span * fix(transformation.py): support 'response_format' for anthropic calls * fix(transformation.py): check for cache_control inside 'function' block * fix: fix linting error * fix: fix linting errors --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
This commit is contained in:
Krish Dholakia
GitHub
parent
9431c1a1b5
commit
41339dfbed
19 changed files with 684 additions and 253 deletions
|
|
@ -3377,6 +3377,9 @@ def embedding( # noqa: PLR0915
|
|||
"azure_ad_token", None
|
||||
) or get_secret_str("AZURE_AD_TOKEN")
|
||||
|
||||
if extra_headers is not None:
|
||||
optional_params["extra_headers"] = extra_headers
|
||||
|
||||
api_key = (
|
||||
api_key
|
||||
or litellm.api_key
|
||||
|
|
@ -4458,7 +4461,10 @@ def image_generation( # noqa: PLR0915
|
|||
metadata = kwargs.get("metadata", {})
|
||||
litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj") # type: ignore
|
||||
client = kwargs.get("client", None)
|
||||
|
||||
extra_headers = kwargs.get("extra_headers", None)
|
||||
headers: dict = kwargs.get("headers", None) or {}
|
||||
if extra_headers is not None:
|
||||
headers.update(extra_headers)
|
||||
model_response: ImageResponse = litellm.utils.ImageResponse()
|
||||
if model is not None or custom_llm_provider is not None:
|
||||
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
|
||||
|
|
@ -4589,6 +4595,14 @@ def image_generation( # noqa: PLR0915
|
|||
"azure_ad_token", None
|
||||
) or get_secret_str("AZURE_AD_TOKEN")
|
||||
|
||||
default_headers = {
|
||||
"Content-Type": "application/json;",
|
||||
"api-key": api_key,
|
||||
}
|
||||
for k, v in default_headers.items():
|
||||
if k not in headers:
|
||||
headers[k] = v
|
||||
|
||||
model_response = azure_chat_completions.image_generation(
|
||||
model=model,
|
||||
prompt=prompt,
|
||||
|
|
@ -4601,6 +4615,7 @@ def image_generation( # noqa: PLR0915
|
|||
api_version=api_version,
|
||||
aimg_generation=aimg_generation,
|
||||
client=client,
|
||||
headers=headers,
|
||||
)
|
||||
elif custom_llm_provider == "openai":
|
||||
model_response = openai_chat_completions.image_generation(
|
||||
|
|
@ -4797,11 +4812,7 @@ def transcription(
|
|||
"""
|
||||
atranscription = kwargs.get("atranscription", False)
|
||||
litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj") # type: ignore
|
||||
kwargs.get("litellm_call_id", None)
|
||||
kwargs.get("logger_fn", None)
|
||||
kwargs.get("proxy_server_request", None)
|
||||
kwargs.get("model_info", None)
|
||||
kwargs.get("metadata", {})
|
||||
extra_headers = kwargs.get("extra_headers", None)
|
||||
kwargs.pop("tags", [])
|
||||
|
||||
drop_params = kwargs.get("drop_params", None)
|
||||
|
|
@ -4857,6 +4868,8 @@ def transcription(
|
|||
or get_secret_str("AZURE_API_KEY")
|
||||
)
|
||||
|
||||
optional_params["extra_headers"] = extra_headers
|
||||
|
||||
response = azure_audio_transcriptions.audio_transcriptions(
|
||||
model=model,
|
||||
audio_file=file,
|
||||
|
|
@ -4975,6 +4988,7 @@ def speech(
|
|||
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)
|
||||
extra_headers = kwargs.get("extra_headers", None)
|
||||
model_info = kwargs.get("model_info", None)
|
||||
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
|
||||
kwargs.pop("tags", [])
|
||||
|
|
@ -5087,7 +5101,8 @@ def speech(
|
|||
"AZURE_AD_TOKEN"
|
||||
)
|
||||
|
||||
headers = headers or litellm.headers
|
||||
if extra_headers:
|
||||
optional_params["extra_headers"] = extra_headers
|
||||
|
||||
response = azure_chat_completions.audio_speech(
|
||||
model=model,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue