mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-27 03:34:10 +00:00
LiteLLM Minor Fixes & Improvements (11/13/2024) (#6729)
* fix(utils.py): add logprobs support for together ai Fixes https://github.com/BerriAI/litellm/issues/6724 * feat(pass_through_endpoints/): add anthropic/ pass-through endpoint adds new `anthropic/` pass-through endpoint + refactors docs * feat(spend_management_endpoints.py): allow /global/spend/report to query team + customer id enables seeing spend for a customer in a team * Add integration with MLflow Tracing (#6147) * Add MLflow logger Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * Streaming handling Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * lint Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * address comments and fix issues Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * address comments and fix issues Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * Move logger construction code Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * Add docs Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * async handlers Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * new picture Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> --------- Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> * fix(mlflow.py): fix ruff linting errors * ci(config.yml): add mlflow to ci testing * fix: fix test * test: fix test * Litellm key update fix (#6710) * fix(caching): convert arg to equivalent kwargs in llm caching handler prevent unexpected errors * fix(caching_handler.py): don't pass args to caching * fix(caching): remove all *args from caching.py * fix(caching): consistent function signatures + abc method * test(caching_unit_tests.py): add unit tests for llm caching ensures coverage for common caching scenarios across different implementations * refactor(litellm_logging.py): move to using cache key from hidden params instead of regenerating one * fix(router.py): drop redis password requirement * fix(proxy_server.py): fix faulty slack alerting check * fix(langfuse.py): avoid copying functions/thread lock objects in metadata fixes metadata copy error when parent otel span in metadata * test: update test * fix(key_management_endpoints.py): fix /key/update with metadata update * fix(key_management_endpoints.py): fix key_prepare_update helper * fix(key_management_endpoints.py): reset value to none if set in key update * fix: update test ' * Litellm dev 11 11 2024 (#6693) * fix(__init__.py): add 'watsonx_text' as mapped llm api route Fixes https://github.com/BerriAI/litellm/issues/6663 * fix(opentelemetry.py): fix passing parallel tool calls to otel Fixes https://github.com/BerriAI/litellm/issues/6677 * refactor(test_opentelemetry_unit_tests.py): create a base set of unit tests for all logging integrations - test for parallel tool call handling reduces bugs in repo * fix(__init__.py): update provider-model mapping to include all known provider-model mappings Fixes https://github.com/BerriAI/litellm/issues/6669 * feat(anthropic): support passing document in llm api call * docs(anthropic.md): add pdf anthropic call to docs + expose new 'supports_pdf_input' function * fix(factory.py): fix linting error * add clear doc string for GCS bucket logging * Add docs to export logs to Laminar (#6674) * Add docs to export logs to Laminar * minor fix: newline at end of file * place laminar after http and grpc * (Feat) Add langsmith key based logging (#6682) * add langsmith_api_key to StandardCallbackDynamicParams * create a file for langsmith types * langsmith add key / team based logging * add key based logging for langsmith * fix langsmith key based logging * fix linting langsmith * remove NOQA violation * add unit test coverage for all helpers in test langsmith * test_langsmith_key_based_logging * docs langsmith key based logging * run langsmith tests in logging callback tests * fix logging testing * test_langsmith_key_based_logging * test_add_callback_via_key_litellm_pre_call_utils_langsmith * add debug statement langsmith key based logging * test_langsmith_key_based_logging * (fix) OpenAI's optional messages[].name does not work with Mistral API (#6701) * use helper for _transform_messages mistral * add test_message_with_name to base LLMChat test * fix linting * add xAI on Admin UI (#6680) * (docs) add benchmarks on 1K RPS (#6704) * docs litellm proxy benchmarks * docs GCS bucket * doc fix - reduce clutter on logging doc title * (feat) add cost tracking stable diffusion 3 on Bedrock (#6676) * add cost tracking for sd3 * test_image_generation_bedrock * fix get model info for image cost * add cost_calculator for stability 1 models * add unit testing for bedrock image cost calc * test_cost_calculator_with_no_optional_params * add test_cost_calculator_basic * correctly allow size Optional * fix cost_calculator * sd3 unit tests cost calc * fix raise correct error 404 when /key/info is called on non-existent key (#6653) * fix raise correct error on /key/info * add not_found_error error * fix key not found in DB error * use 1 helper for checking token hash * fix error code on key info * fix test key gen prisma * test_generate_and_call_key_info * test fix test_call_with_valid_model_using_all_models * fix key info tests * bump: version 1.52.4 → 1.52.5 * add defaults used for GCS logging * LiteLLM Minor Fixes & Improvements (11/12/2024) (#6705) * fix(caching): convert arg to equivalent kwargs in llm caching handler prevent unexpected errors * fix(caching_handler.py): don't pass args to caching * fix(caching): remove all *args from caching.py * fix(caching): consistent function signatures + abc method * test(caching_unit_tests.py): add unit tests for llm caching ensures coverage for common caching scenarios across different implementations * refactor(litellm_logging.py): move to using cache key from hidden params instead of regenerating one * fix(router.py): drop redis password requirement * fix(proxy_server.py): fix faulty slack alerting check * fix(langfuse.py): avoid copying functions/thread lock objects in metadata fixes metadata copy error when parent otel span in metadata * test: update test * bump: version 1.52.5 → 1.52.6 * (feat) helm hook to sync db schema (#6715) * v0 migration job * fix job * fix migrations job.yml * handle standalone DB on helm hook * fix argo cd annotations * fix db migration helm hook * fix migration job * doc fix Using Http/2 with Hypercorn * (fix proxy redis) Add redis sentinel support (#6154) * add sentinel_password support * add doc for setting redis sentinel password * fix redis sentinel - use sentinel password * Fix: Update gpt-4o costs to that of gpt-4o-2024-08-06 (#6714) Fixes #6713 * (fix) using Anthropic `response_format={"type": "json_object"}` (#6721) * add support for response_format=json anthropic * add test_json_response_format to baseLLM ChatTest * fix test_litellm_anthropic_prompt_caching_tools * fix test_anthropic_function_call_with_no_schema * test test_create_json_tool_call_for_response_format * (feat) Add cost tracking for Azure Dall-e-3 Image Generation + use base class to ensure basic image generation tests pass (#6716) * add BaseImageGenTest * use 1 class for unit testing * add debugging to BaseImageGenTest * TestAzureOpenAIDalle3 * fix response_cost_calculator * test_basic_image_generation * fix img gen basic test * fix _select_model_name_for_cost_calc * fix test_aimage_generation_bedrock_with_optional_params * fix undo changes cost tracking * fix response_cost_calculator * fix test_cost_azure_gpt_35 * fix remove dup test (#6718) * (build) update db helm hook * (build) helm db pre sync hook * (build) helm db sync hook * test: run test_team_logging firdst --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: Dinmukhamed Mailibay <47117969+dinmukhamedm@users.noreply.github.com> Co-authored-by: Kilian Lieret <kilian.lieret@posteo.de> * test: update test * test: skip anthropic overloaded error * test: cleanup test * test: update tests * test: fix test * test: handle gemini overloaded model error * test: handle internal server error * test: handle anthropic overloaded error * test: handle claude instability --------- Signed-off-by: B-Step62 <yuki.watanabe@databricks.com> Co-authored-by: Yuki Watanabe <31463517+B-Step62@users.noreply.github.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: Dinmukhamed Mailibay <47117969+dinmukhamedm@users.noreply.github.com> Co-authored-by: Kilian Lieret <kilian.lieret@posteo.de>
This commit is contained in:
Krish Dholakia
GitHub
parent
4efa9e9000
commit
3b3e19643c
23 changed files with 874 additions and 97 deletions
|
|
@ -161,17 +161,7 @@ def get_supported_openai_params( # noqa: PLR0915
|
|||
elif custom_llm_provider == "huggingface":
|
||||
return litellm.HuggingfaceConfig().get_supported_openai_params()
|
||||
elif custom_llm_provider == "together_ai":
|
||||
return [
|
||||
"stream",
|
||||
"temperature",
|
||||
"max_tokens",
|
||||
"top_p",
|
||||
"stop",
|
||||
"frequency_penalty",
|
||||
"tools",
|
||||
"tool_choice",
|
||||
"response_format",
|
||||
]
|
||||
return litellm.TogetherAIConfig().get_supported_openai_params(model=model)
|
||||
elif custom_llm_provider == "ai21":
|
||||
return [
|
||||
"stream",
|
||||
|
|
|
|||
|
|
@ -28,6 +28,7 @@ from litellm.caching.caching_handler import LLMCachingHandler
|
|||
from litellm.cost_calculator import _select_model_name_for_cost_calc
|
||||
from litellm.integrations.custom_guardrail import CustomGuardrail
|
||||
from litellm.integrations.custom_logger import CustomLogger
|
||||
from litellm.integrations.mlflow import MlflowLogger
|
||||
from litellm.litellm_core_utils.redact_messages import (
|
||||
redact_message_input_output_from_custom_logger,
|
||||
redact_message_input_output_from_logging,
|
||||
|
|
@ -563,6 +564,7 @@ class Logging:
|
|||
message=f"Model Call Details pre-call: {details_to_log}",
|
||||
level="info",
|
||||
)
|
||||
|
||||
elif isinstance(callback, CustomLogger): # custom logger class
|
||||
callback.log_pre_api_call(
|
||||
model=self.model,
|
||||
|
|
@ -1258,6 +1260,7 @@ class Logging:
|
|||
end_time=end_time,
|
||||
print_verbose=print_verbose,
|
||||
)
|
||||
|
||||
if (
|
||||
callback == "openmeter"
|
||||
and self.model_call_details.get("litellm_params", {}).get(
|
||||
|
|
@ -2347,6 +2350,14 @@ def _init_custom_logger_compatible_class( # noqa: PLR0915
|
|||
_in_memory_loggers.append(_otel_logger)
|
||||
return _otel_logger # type: ignore
|
||||
|
||||
elif logging_integration == "mlflow":
|
||||
for callback in _in_memory_loggers:
|
||||
if isinstance(callback, MlflowLogger):
|
||||
return callback # type: ignore
|
||||
|
||||
_mlflow_logger = MlflowLogger()
|
||||
_in_memory_loggers.append(_mlflow_logger)
|
||||
return _mlflow_logger # type: ignore
|
||||
|
||||
def get_custom_logger_compatible_class(
|
||||
logging_integration: litellm._custom_logger_compatible_callbacks_literal,
|
||||
|
|
@ -2448,6 +2459,12 @@ def get_custom_logger_compatible_class(
|
|||
and callback.callback_name == "langtrace"
|
||||
):
|
||||
return callback
|
||||
|
||||
elif logging_integration == "mlflow":
|
||||
for callback in _in_memory_loggers:
|
||||
if isinstance(callback, MlflowLogger):
|
||||
return callback
|
||||
|
||||
return None
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue