From 3ee871b7a9d142f3bdda7d2a24e29cd05969efe4 Mon Sep 17 00:00:00 2001 From: Krish Dholakia Date: Thu, 14 Nov 2024 00:42:37 +0530 Subject: [PATCH] Litellm key update fix (#6710) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit * 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 Co-authored-by: Dinmukhamed Mailibay <47117969+dinmukhamedm@users.noreply.github.com> Co-authored-by: Kilian Lieret --- .../key_management_endpoints.py | 16 +++++-------- tests/proxy_unit_tests/test_proxy_utils.py | 20 ++++++++++++++++ tests/test_keys.py | 23 ++++++++++++++----- tests/test_team_logging.py | 4 ++-- 4 files changed, 45 insertions(+), 18 deletions(-) diff --git a/litellm/proxy/management_endpoints/key_management_endpoints.py b/litellm/proxy/management_endpoints/key_management_endpoints.py index c50aa0f9f..01baa5a43 100644 --- a/litellm/proxy/management_endpoints/key_management_endpoints.py +++ b/litellm/proxy/management_endpoints/key_management_endpoints.py @@ -303,21 +303,17 @@ async def generate_key_fn( # noqa: PLR0915 ) -async def prepare_key_update_data( +def prepare_key_update_data( data: Union[UpdateKeyRequest, RegenerateKeyRequest], existing_key_row ): - data_json: dict = data.dict(exclude_unset=True) + data_json: dict = data.model_dump(exclude_unset=True) data_json.pop("key", None) _metadata_fields = ["model_rpm_limit", "model_tpm_limit", "guardrails"] non_default_values = {} for k, v in data_json.items(): if k in _metadata_fields: continue - if v is not None: - if not isinstance(v, bool) and v in ([], {}, 0): - pass - else: - non_default_values[k] = v + non_default_values[k] = v if "duration" in non_default_values: duration = non_default_values.pop("duration") @@ -379,7 +375,7 @@ async def update_key_fn( ) try: - data_json: dict = data.json() + data_json: dict = data.model_dump(exclude_unset=True) key = data_json.pop("key") # get the row from db if prisma_client is None: @@ -395,7 +391,7 @@ async def update_key_fn( detail={"error": f"Team not found, passed team_id={data.team_id}"}, ) - non_default_values = await prepare_key_update_data( + non_default_values = prepare_key_update_data( data=data, existing_key_row=existing_key_row ) @@ -1144,7 +1140,7 @@ async def regenerate_key_fn( non_default_values = {} if data is not None: # Update with any provided parameters from GenerateKeyRequest - non_default_values = await prepare_key_update_data( + non_default_values = prepare_key_update_data( data=data, existing_key_row=_key_in_db ) diff --git a/tests/proxy_unit_tests/test_proxy_utils.py b/tests/proxy_unit_tests/test_proxy_utils.py index f3f33bad6..2e857808d 100644 --- a/tests/proxy_unit_tests/test_proxy_utils.py +++ b/tests/proxy_unit_tests/test_proxy_utils.py @@ -510,3 +510,23 @@ async def test_proxy_config_update_from_db(): "success_callback": "langfuse", } } + + +def test_prepare_key_update_data(): + from litellm.proxy.management_endpoints.key_management_endpoints import ( + prepare_key_update_data, + ) + from litellm.proxy._types import UpdateKeyRequest + + existing_key_row = MagicMock() + data = UpdateKeyRequest(key="test_key", models=["gpt-4"], duration="120s") + updated_data = prepare_key_update_data(data, existing_key_row) + assert "expires" in updated_data + + data = UpdateKeyRequest(key="test_key", metadata={}) + updated_data = prepare_key_update_data(data, existing_key_row) + assert updated_data["metadata"] == {} + + data = UpdateKeyRequest(key="test_key", metadata=None) + updated_data = prepare_key_update_data(data, existing_key_row) + assert updated_data["metadata"] == None diff --git a/tests/test_keys.py b/tests/test_keys.py index 437afc336..a569634bc 100644 --- a/tests/test_keys.py +++ b/tests/test_keys.py @@ -66,6 +66,7 @@ async def generate_key( max_parallel_requests: Optional[int] = None, user_id: Optional[str] = None, team_id: Optional[str] = None, + metadata: Optional[dict] = None, calling_key="sk-1234", ): url = "http://0.0.0.0:4000/key/generate" @@ -82,6 +83,7 @@ async def generate_key( "max_parallel_requests": max_parallel_requests, "user_id": user_id, "team_id": team_id, + "metadata": metadata, } print(f"data: {data}") @@ -136,16 +138,21 @@ async def test_key_gen_bad_key(): pass -async def update_key(session, get_key): +async def update_key(session, get_key, metadata: Optional[dict] = None): """ Make sure only models user has access to are returned """ url = "http://0.0.0.0:4000/key/update" headers = { - "Authorization": f"Bearer sk-1234", + "Authorization": "Bearer sk-1234", "Content-Type": "application/json", } - data = {"key": get_key, "models": ["gpt-4"], "duration": "120s"} + data = {"key": get_key} + + if metadata is not None: + data["metadata"] = metadata + else: + data.update({"models": ["gpt-4"], "duration": "120s"}) async with session.post(url, headers=headers, json=data) as response: status = response.status @@ -276,20 +283,24 @@ async def chat_completion_streaming(session, key, model="gpt-4"): return prompt_tokens, completion_tokens +@pytest.mark.parametrize("metadata", [{"test": "new"}, {}]) @pytest.mark.asyncio -async def test_key_update(): +async def test_key_update(metadata): """ Create key Update key with new model Test key w/ model """ async with aiohttp.ClientSession() as session: - key_gen = await generate_key(session=session, i=0) + key_gen = await generate_key(session=session, i=0, metadata={"test": "test"}) key = key_gen["key"] - await update_key( + assert key_gen["metadata"]["test"] == "test" + updated_key = await update_key( session=session, get_key=key, + metadata=metadata, ) + assert updated_key["metadata"] == metadata await update_proxy_budget(session=session) # resets proxy spend await chat_completion(session=session, key=key) diff --git a/tests/test_team_logging.py b/tests/test_team_logging.py index 97f18b42e..cf0fa6354 100644 --- a/tests/test_team_logging.py +++ b/tests/test_team_logging.py @@ -62,8 +62,8 @@ async def chat_completion(session, key, model="azure-gpt-3.5", request_metadata= @pytest.mark.asyncio -@pytest.mark.flaky(retries=6, delay=1) -async def test_team_logging(): +@pytest.mark.flaky(retries=12, delay=2) +async def test_aaateam_logging(): """ -> Team 1 logs to project 1 -> Create Key