litellm/tests/logging_callback_tests/test_langfuse_unit_tests.py

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

390 lines
13 KiB
Python
Raw Normal View History

import os
import sys
LiteLLM Minor Fixes & Improvements (11/05/2024) (#6590) * fix(pattern_matching_router.py): update model name using correct function * fix(langfuse.py): metadata deepcopy can cause unhandled error (#6563) Co-authored-by: seva <seva@inita.com> * fix(stream_chunk_builder_utils.py): correctly set prompt tokens + log correct streaming usage Closes https://github.com/BerriAI/litellm/issues/6488 * build(deps): bump cookie and express in /docs/my-website (#6566) Bumps [cookie](https://github.com/jshttp/cookie) and [express](https://github.com/expressjs/express). These dependencies needed to be updated together. Updates `cookie` from 0.6.0 to 0.7.1 - [Release notes](https://github.com/jshttp/cookie/releases) - [Commits](https://github.com/jshttp/cookie/compare/v0.6.0...v0.7.1) Updates `express` from 4.20.0 to 4.21.1 - [Release notes](https://github.com/expressjs/express/releases) - [Changelog](https://github.com/expressjs/express/blob/4.21.1/History.md) - [Commits](https://github.com/expressjs/express/compare/4.20.0...4.21.1) --- updated-dependencies: - dependency-name: cookie dependency-type: indirect - dependency-name: express dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * docs(virtual_keys.md): update Dockerfile reference (#6554) Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> * (proxy fix) - call connect on prisma client when running setup (#6534) * critical fix - call connect on prisma client when running setup * fix test_proxy_server_prisma_setup * fix test_proxy_server_prisma_setup * Add 3.5 haiku (#6588) * feat: add claude-3-5-haiku-20241022 entries * feat: add claude-3-5-haiku-20241022 and vertex_ai/claude-3-5-haiku@20241022 models * add missing entries, remove vision * remove image token costs * Litellm perf improvements 3 (#6573) * perf: move writing key to cache, to background task * perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils adds 200ms on calls with pgdb connected * fix(litellm_pre_call_utils.py'): rename call_type to actual call used * perf(proxy_server.py): remove db logic from _get_config_from_file was causing db calls to occur on every llm request, if team_id was set on key * fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db reduces latency/call by ~100ms * fix(proxy_server.py): minor fix on existing_settings not incl alerting * fix(exception_mapping_utils.py): map databricks exception string * fix(auth_checks.py): fix auth check logic * test: correctly mark flaky test * fix(utils.py): handle auth token error for tokenizers.from_pretrained * build: fix map * build: fix map * build: fix json for model map * fix ImageObject conversion (#6584) * (fix) litellm.text_completion raises a non-blocking error on simple usage (#6546) * unit test test_huggingface_text_completion_logprobs * fix return TextCompletionHandler convert_chat_to_text_completion * fix hf rest api * fix test_huggingface_text_completion_logprobs * fix linting errors * fix importLiteLLMResponseObjectHandler * fix test for LiteLLMResponseObjectHandler * fix test text completion * fix allow using 15 seconds for premium license check * testing fix bedrock deprecated cohere.command-text-v14 * (feat) add `Predicted Outputs` for OpenAI (#6594) * bump openai to openai==1.54.0 * add 'prediction' param * testing fix bedrock deprecated cohere.command-text-v14 * test test_openai_prediction_param.py * test_openai_prediction_param_with_caching * doc Predicted Outputs * doc Predicted Output * (fix) Vertex Improve Performance when using `image_url` (#6593) * fix transformation vertex * test test_process_gemini_image * test_image_completion_request * testing fix - bedrock has deprecated cohere.command-text-v14 * fix vertex pdf * bump: version 1.51.5 → 1.52.0 * fix(lowest_tpm_rpm_routing.py): fix parallel rate limit check (#6577) * fix(lowest_tpm_rpm_routing.py): fix parallel rate limit check * fix(lowest_tpm_rpm_v2.py): return headers in correct format * test: update test * build(deps): bump cookie and express in /docs/my-website (#6566) Bumps [cookie](https://github.com/jshttp/cookie) and [express](https://github.com/expressjs/express). These dependencies needed to be updated together. Updates `cookie` from 0.6.0 to 0.7.1 - [Release notes](https://github.com/jshttp/cookie/releases) - [Commits](https://github.com/jshttp/cookie/compare/v0.6.0...v0.7.1) Updates `express` from 4.20.0 to 4.21.1 - [Release notes](https://github.com/expressjs/express/releases) - [Changelog](https://github.com/expressjs/express/blob/4.21.1/History.md) - [Commits](https://github.com/expressjs/express/compare/4.20.0...4.21.1) --- updated-dependencies: - dependency-name: cookie dependency-type: indirect - dependency-name: express dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * docs(virtual_keys.md): update Dockerfile reference (#6554) Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> * (proxy fix) - call connect on prisma client when running setup (#6534) * critical fix - call connect on prisma client when running setup * fix test_proxy_server_prisma_setup * fix test_proxy_server_prisma_setup * Add 3.5 haiku (#6588) * feat: add claude-3-5-haiku-20241022 entries * feat: add claude-3-5-haiku-20241022 and vertex_ai/claude-3-5-haiku@20241022 models * add missing entries, remove vision * remove image token costs * Litellm perf improvements 3 (#6573) * perf: move writing key to cache, to background task * perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils adds 200ms on calls with pgdb connected * fix(litellm_pre_call_utils.py'): rename call_type to actual call used * perf(proxy_server.py): remove db logic from _get_config_from_file was causing db calls to occur on every llm request, if team_id was set on key * fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db reduces latency/call by ~100ms * fix(proxy_server.py): minor fix on existing_settings not incl alerting * fix(exception_mapping_utils.py): map databricks exception string * fix(auth_checks.py): fix auth check logic * test: correctly mark flaky test * fix(utils.py): handle auth token error for tokenizers.from_pretrained * build: fix map * build: fix map * build: fix json for model map * test: remove eol model * fix(proxy_server.py): fix db config loading logic * fix(proxy_server.py): fix order of config / db updates, to ensure fields not overwritten * test: skip test if required env var is missing * test: fix test --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: paul-gauthier <69695708+paul-gauthier@users.noreply.github.com> * test: mark flaky test * test: handle anthropic api instability * test(test_proxy_utils.py): add testing for db config update logic * Update setuptools in docker and fastapi to latest verison, in order to upgrade starlette version (#6597) * build(deps): bump cookie and express in /docs/my-website (#6566) Bumps [cookie](https://github.com/jshttp/cookie) and [express](https://github.com/expressjs/express). These dependencies needed to be updated together. Updates `cookie` from 0.6.0 to 0.7.1 - [Release notes](https://github.com/jshttp/cookie/releases) - [Commits](https://github.com/jshttp/cookie/compare/v0.6.0...v0.7.1) Updates `express` from 4.20.0 to 4.21.1 - [Release notes](https://github.com/expressjs/express/releases) - [Changelog](https://github.com/expressjs/express/blob/4.21.1/History.md) - [Commits](https://github.com/expressjs/express/compare/4.20.0...4.21.1) --- updated-dependencies: - dependency-name: cookie dependency-type: indirect - dependency-name: express dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * docs(virtual_keys.md): update Dockerfile reference (#6554) Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> * (proxy fix) - call connect on prisma client when running setup (#6534) * critical fix - call connect on prisma client when running setup * fix test_proxy_server_prisma_setup * fix test_proxy_server_prisma_setup * Add 3.5 haiku (#6588) * feat: add claude-3-5-haiku-20241022 entries * feat: add claude-3-5-haiku-20241022 and vertex_ai/claude-3-5-haiku@20241022 models * add missing entries, remove vision * remove image token costs * Litellm perf improvements 3 (#6573) * perf: move writing key to cache, to background task * perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils adds 200ms on calls with pgdb connected * fix(litellm_pre_call_utils.py'): rename call_type to actual call used * perf(proxy_server.py): remove db logic from _get_config_from_file was causing db calls to occur on every llm request, if team_id was set on key * fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db reduces latency/call by ~100ms * fix(proxy_server.py): minor fix on existing_settings not incl alerting * fix(exception_mapping_utils.py): map databricks exception string * fix(auth_checks.py): fix auth check logic * test: correctly mark flaky test * fix(utils.py): handle auth token error for tokenizers.from_pretrained * build: fix map * build: fix map * build: fix json for model map * fix ImageObject conversion (#6584) * (fix) litellm.text_completion raises a non-blocking error on simple usage (#6546) * unit test test_huggingface_text_completion_logprobs * fix return TextCompletionHandler convert_chat_to_text_completion * fix hf rest api * fix test_huggingface_text_completion_logprobs * fix linting errors * fix importLiteLLMResponseObjectHandler * fix test for LiteLLMResponseObjectHandler * fix test text completion * fix allow using 15 seconds for premium license check * testing fix bedrock deprecated cohere.command-text-v14 * (feat) add `Predicted Outputs` for OpenAI (#6594) * bump openai to openai==1.54.0 * add 'prediction' param * testing fix bedrock deprecated cohere.command-text-v14 * test test_openai_prediction_param.py * test_openai_prediction_param_with_caching * doc Predicted Outputs * doc Predicted Output * (fix) Vertex Improve Performance when using `image_url` (#6593) * fix transformation vertex * test test_process_gemini_image * test_image_completion_request * testing fix - bedrock has deprecated cohere.command-text-v14 * fix vertex pdf * bump: version 1.51.5 → 1.52.0 * Update setuptools in docker and fastapi to latest verison, in order to upgrade starlette version --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: paul-gauthier <69695708+paul-gauthier@users.noreply.github.com> Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com> Co-authored-by: Jacob Hagstedt <wcgs@novonordisk.com> * fix(langfuse.py): fix linting errors * fix: fix linting errors * fix: fix casting error * fix: fix typing error * fix: add more tests * fix(utils.py): fix return_processed_chunk_logic * Revert "Update setuptools in docker and fastapi to latest verison, in order t…" (#6615) This reverts commit 1a7f7bdfb75df0efbc930b7f2e39febc80e97d5a. * docs fix clarify team_id on team based logging * doc fix team based logging with langfuse * fix flake8 checks * test: bump sleep time * refactor: replace claude-instant-1.2 with haiku in testing * fix(proxy_server.py): move to using sl payload in track_cost_callback * fix(proxy_server.py): fix linting errors * fix(proxy_server.py): fallback to kwargs(response_cost) if given * test: remove claude-instant-1 from tests * test: fix claude test * docs fix clarify team_id on team based logging * doc fix team based logging with langfuse * build: remove lint.yml --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: Vsevolod Karvetskiy <56288164+karvetskiy@users.noreply.github.com> Co-authored-by: seva <seva@inita.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: paul-gauthier <69695708+paul-gauthier@users.noreply.github.com> Co-authored-by: Jacob Hagstedt P Suorra <Jacobh2@users.noreply.github.com> Co-authored-by: Jacob Hagstedt <wcgs@novonordisk.com>
2024-11-07 06:47:05 +08:00
import threading
from datetime import datetime
sys.path.insert(
0, os.path.abspath("../..")
) # Adds the parent directory to the system-path
import pytest
from litellm.integrations.langfuse.langfuse import (
LangFuseLogger,
)
from litellm.integrations.langfuse.langfuse_handler import LangFuseHandler
from litellm.litellm_core_utils.litellm_logging import DynamicLoggingCache
from unittest.mock import Mock, patch
from respx import MockRouter
from litellm.types.utils import (
StandardLoggingPayload,
StandardLoggingModelInformation,
StandardLoggingMetadata,
StandardLoggingHiddenParams,
StandardCallbackDynamicParams,
ModelResponse,
Choices,
Message,
TextCompletionResponse,
TextChoices,
)
def create_standard_logging_payload() -> StandardLoggingPayload:
return StandardLoggingPayload(
id="test_id",
call_type="completion",
response_cost=0.1,
response_cost_failure_debug_info=None,
status="success",
total_tokens=30,
prompt_tokens=20,
completion_tokens=10,
startTime=1234567890.0,
endTime=1234567891.0,
completionStartTime=1234567890.5,
model_map_information=StandardLoggingModelInformation(
model_map_key="gpt-3.5-turbo", model_map_value=None
),
model="gpt-3.5-turbo",
model_id="model-123",
model_group="openai-gpt",
api_base="https://api.openai.com",
metadata=StandardLoggingMetadata(
user_api_key_hash="test_hash",
user_api_key_org_id=None,
user_api_key_alias="test_alias",
user_api_key_team_id="test_team",
user_api_key_user_id="test_user",
user_api_key_team_alias="test_team_alias",
spend_logs_metadata=None,
requester_ip_address="127.0.0.1",
requester_metadata=None,
),
cache_hit=False,
cache_key=None,
saved_cache_cost=0.0,
request_tags=[],
end_user=None,
requester_ip_address="127.0.0.1",
messages=[{"role": "user", "content": "Hello, world!"}],
response={"choices": [{"message": {"content": "Hi there!"}}]},
error_str=None,
model_parameters={"stream": True},
hidden_params=StandardLoggingHiddenParams(
model_id="model-123",
cache_key=None,
api_base="https://api.openai.com",
response_cost="0.1",
additional_headers=None,
),
)
@pytest.fixture
def dynamic_logging_cache():
return DynamicLoggingCache()
global_langfuse_logger = LangFuseLogger(
langfuse_public_key="global_public_key",
langfuse_secret="global_secret",
langfuse_host="https://global.langfuse.com",
)
# IMPORTANT: Test that passing both langfuse_secret_key and langfuse_secret works
standard_params_1 = StandardCallbackDynamicParams(
langfuse_public_key="test_public_key",
langfuse_secret="test_secret",
langfuse_host="https://test.langfuse.com",
)
standard_params_2 = StandardCallbackDynamicParams(
langfuse_public_key="test_public_key",
langfuse_secret_key="test_secret",
langfuse_host="https://test.langfuse.com",
)
@pytest.mark.parametrize("globalLangfuseLogger", [None, global_langfuse_logger])
@pytest.mark.parametrize("standard_params", [standard_params_1, standard_params_2])
def test_get_langfuse_logger_for_request_with_dynamic_params(
dynamic_logging_cache, globalLangfuseLogger, standard_params
):
"""
If StandardCallbackDynamicParams contain langfuse credentials the returned Langfuse logger should use the dynamic params
the new Langfuse logger should be cached
Even if globalLangfuseLogger is provided, it should use dynamic params if they are passed
"""
result = LangFuseHandler.get_langfuse_logger_for_request(
standard_callback_dynamic_params=standard_params,
in_memory_dynamic_logger_cache=dynamic_logging_cache,
globalLangfuseLogger=globalLangfuseLogger,
)
assert isinstance(result, LangFuseLogger)
assert result.public_key == "test_public_key"
assert result.secret_key == "test_secret"
assert result.langfuse_host == "https://test.langfuse.com"
print("langfuse logger=", result)
print("vars in langfuse logger=", vars(result))
# Check if the logger is cached
cached_logger = dynamic_logging_cache.get_cache(
credentials={
"langfuse_public_key": "test_public_key",
"langfuse_secret": "test_secret",
"langfuse_host": "https://test.langfuse.com",
},
service_name="langfuse",
)
assert cached_logger is result
@pytest.mark.parametrize("globalLangfuseLogger", [None, global_langfuse_logger])
def test_get_langfuse_logger_for_request_with_no_dynamic_params(
dynamic_logging_cache, globalLangfuseLogger
):
"""
If StandardCallbackDynamicParams are not provided, the globalLangfuseLogger should be returned
"""
result = LangFuseHandler.get_langfuse_logger_for_request(
standard_callback_dynamic_params=StandardCallbackDynamicParams(),
in_memory_dynamic_logger_cache=dynamic_logging_cache,
globalLangfuseLogger=globalLangfuseLogger,
)
assert result is not None
assert isinstance(result, LangFuseLogger)
print("langfuse logger=", result)
if globalLangfuseLogger is not None:
assert result.public_key == "global_public_key"
assert result.secret_key == "global_secret"
assert result.langfuse_host == "https://global.langfuse.com"
def test_dynamic_langfuse_credentials_are_passed():
# Test when credentials are passed
params_with_credentials = StandardCallbackDynamicParams(
langfuse_public_key="test_key",
langfuse_secret="test_secret",
langfuse_host="https://test.langfuse.com",
)
assert (
LangFuseHandler._dynamic_langfuse_credentials_are_passed(
params_with_credentials
)
is True
)
# Test when no credentials are passed
params_without_credentials = StandardCallbackDynamicParams()
assert (
LangFuseHandler._dynamic_langfuse_credentials_are_passed(
params_without_credentials
)
is False
)
# Test when only some credentials are passed
params_partial_credentials = StandardCallbackDynamicParams(
langfuse_public_key="test_key"
)
assert (
LangFuseHandler._dynamic_langfuse_credentials_are_passed(
params_partial_credentials
)
is True
)
def test_get_dynamic_langfuse_logging_config():
# Test with dynamic params
dynamic_params = StandardCallbackDynamicParams(
langfuse_public_key="dynamic_key",
langfuse_secret="dynamic_secret",
langfuse_host="https://dynamic.langfuse.com",
)
config = LangFuseHandler.get_dynamic_langfuse_logging_config(dynamic_params)
assert config["langfuse_public_key"] == "dynamic_key"
assert config["langfuse_secret"] == "dynamic_secret"
assert config["langfuse_host"] == "https://dynamic.langfuse.com"
# Test with no dynamic params
empty_params = StandardCallbackDynamicParams()
config = LangFuseHandler.get_dynamic_langfuse_logging_config(empty_params)
assert config["langfuse_public_key"] is None
assert config["langfuse_secret"] is None
assert config["langfuse_host"] is None
def test_return_global_langfuse_logger():
mock_cache = Mock()
global_logger = LangFuseLogger(
langfuse_public_key="global_key", langfuse_secret="global_secret"
)
# Test with existing global logger
result = LangFuseHandler._return_global_langfuse_logger(global_logger, mock_cache)
assert result == global_logger
# Test without global logger, but with cached logger, should return cached logger
mock_cache.get_cache.return_value = global_logger
result = LangFuseHandler._return_global_langfuse_logger(None, mock_cache)
assert result == global_logger
# Test without global logger and without cached logger, should create new logger
mock_cache.get_cache.return_value = None
with patch.object(
LangFuseHandler,
"_create_langfuse_logger_from_credentials",
return_value=global_logger,
):
result = LangFuseHandler._return_global_langfuse_logger(None, mock_cache)
assert result == global_logger
def test_get_langfuse_logger_for_request_with_cached_logger():
"""
Test that get_langfuse_logger_for_request returns the cached logger if it exists when dynamic params are passed
"""
mock_cache = Mock()
cached_logger = LangFuseLogger(
langfuse_public_key="cached_key", langfuse_secret="cached_secret"
)
mock_cache.get_cache.return_value = cached_logger
dynamic_params = StandardCallbackDynamicParams(
langfuse_public_key="test_key",
langfuse_secret="test_secret",
langfuse_host="https://test.langfuse.com",
)
result = LangFuseHandler.get_langfuse_logger_for_request(
standard_callback_dynamic_params=dynamic_params,
in_memory_dynamic_logger_cache=mock_cache,
globalLangfuseLogger=None,
)
assert result == cached_logger
mock_cache.get_cache.assert_called_once()
LiteLLM Minor Fixes & Improvements (11/05/2024) (#6590) * fix(pattern_matching_router.py): update model name using correct function * fix(langfuse.py): metadata deepcopy can cause unhandled error (#6563) Co-authored-by: seva <seva@inita.com> * fix(stream_chunk_builder_utils.py): correctly set prompt tokens + log correct streaming usage Closes https://github.com/BerriAI/litellm/issues/6488 * build(deps): bump cookie and express in /docs/my-website (#6566) Bumps [cookie](https://github.com/jshttp/cookie) and [express](https://github.com/expressjs/express). These dependencies needed to be updated together. Updates `cookie` from 0.6.0 to 0.7.1 - [Release notes](https://github.com/jshttp/cookie/releases) - [Commits](https://github.com/jshttp/cookie/compare/v0.6.0...v0.7.1) Updates `express` from 4.20.0 to 4.21.1 - [Release notes](https://github.com/expressjs/express/releases) - [Changelog](https://github.com/expressjs/express/blob/4.21.1/History.md) - [Commits](https://github.com/expressjs/express/compare/4.20.0...4.21.1) --- updated-dependencies: - dependency-name: cookie dependency-type: indirect - dependency-name: express dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * docs(virtual_keys.md): update Dockerfile reference (#6554) Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> * (proxy fix) - call connect on prisma client when running setup (#6534) * critical fix - call connect on prisma client when running setup * fix test_proxy_server_prisma_setup * fix test_proxy_server_prisma_setup * Add 3.5 haiku (#6588) * feat: add claude-3-5-haiku-20241022 entries * feat: add claude-3-5-haiku-20241022 and vertex_ai/claude-3-5-haiku@20241022 models * add missing entries, remove vision * remove image token costs * Litellm perf improvements 3 (#6573) * perf: move writing key to cache, to background task * perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils adds 200ms on calls with pgdb connected * fix(litellm_pre_call_utils.py'): rename call_type to actual call used * perf(proxy_server.py): remove db logic from _get_config_from_file was causing db calls to occur on every llm request, if team_id was set on key * fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db reduces latency/call by ~100ms * fix(proxy_server.py): minor fix on existing_settings not incl alerting * fix(exception_mapping_utils.py): map databricks exception string * fix(auth_checks.py): fix auth check logic * test: correctly mark flaky test * fix(utils.py): handle auth token error for tokenizers.from_pretrained * build: fix map * build: fix map * build: fix json for model map * fix ImageObject conversion (#6584) * (fix) litellm.text_completion raises a non-blocking error on simple usage (#6546) * unit test test_huggingface_text_completion_logprobs * fix return TextCompletionHandler convert_chat_to_text_completion * fix hf rest api * fix test_huggingface_text_completion_logprobs * fix linting errors * fix importLiteLLMResponseObjectHandler * fix test for LiteLLMResponseObjectHandler * fix test text completion * fix allow using 15 seconds for premium license check * testing fix bedrock deprecated cohere.command-text-v14 * (feat) add `Predicted Outputs` for OpenAI (#6594) * bump openai to openai==1.54.0 * add 'prediction' param * testing fix bedrock deprecated cohere.command-text-v14 * test test_openai_prediction_param.py * test_openai_prediction_param_with_caching * doc Predicted Outputs * doc Predicted Output * (fix) Vertex Improve Performance when using `image_url` (#6593) * fix transformation vertex * test test_process_gemini_image * test_image_completion_request * testing fix - bedrock has deprecated cohere.command-text-v14 * fix vertex pdf * bump: version 1.51.5 → 1.52.0 * fix(lowest_tpm_rpm_routing.py): fix parallel rate limit check (#6577) * fix(lowest_tpm_rpm_routing.py): fix parallel rate limit check * fix(lowest_tpm_rpm_v2.py): return headers in correct format * test: update test * build(deps): bump cookie and express in /docs/my-website (#6566) Bumps [cookie](https://github.com/jshttp/cookie) and [express](https://github.com/expressjs/express). These dependencies needed to be updated together. Updates `cookie` from 0.6.0 to 0.7.1 - [Release notes](https://github.com/jshttp/cookie/releases) - [Commits](https://github.com/jshttp/cookie/compare/v0.6.0...v0.7.1) Updates `express` from 4.20.0 to 4.21.1 - [Release notes](https://github.com/expressjs/express/releases) - [Changelog](https://github.com/expressjs/express/blob/4.21.1/History.md) - [Commits](https://github.com/expressjs/express/compare/4.20.0...4.21.1) --- updated-dependencies: - dependency-name: cookie dependency-type: indirect - dependency-name: express dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * docs(virtual_keys.md): update Dockerfile reference (#6554) Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> * (proxy fix) - call connect on prisma client when running setup (#6534) * critical fix - call connect on prisma client when running setup * fix test_proxy_server_prisma_setup * fix test_proxy_server_prisma_setup * Add 3.5 haiku (#6588) * feat: add claude-3-5-haiku-20241022 entries * feat: add claude-3-5-haiku-20241022 and vertex_ai/claude-3-5-haiku@20241022 models * add missing entries, remove vision * remove image token costs * Litellm perf improvements 3 (#6573) * perf: move writing key to cache, to background task * perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils adds 200ms on calls with pgdb connected * fix(litellm_pre_call_utils.py'): rename call_type to actual call used * perf(proxy_server.py): remove db logic from _get_config_from_file was causing db calls to occur on every llm request, if team_id was set on key * fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db reduces latency/call by ~100ms * fix(proxy_server.py): minor fix on existing_settings not incl alerting * fix(exception_mapping_utils.py): map databricks exception string * fix(auth_checks.py): fix auth check logic * test: correctly mark flaky test * fix(utils.py): handle auth token error for tokenizers.from_pretrained * build: fix map * build: fix map * build: fix json for model map * test: remove eol model * fix(proxy_server.py): fix db config loading logic * fix(proxy_server.py): fix order of config / db updates, to ensure fields not overwritten * test: skip test if required env var is missing * test: fix test --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: paul-gauthier <69695708+paul-gauthier@users.noreply.github.com> * test: mark flaky test * test: handle anthropic api instability * test(test_proxy_utils.py): add testing for db config update logic * Update setuptools in docker and fastapi to latest verison, in order to upgrade starlette version (#6597) * build(deps): bump cookie and express in /docs/my-website (#6566) Bumps [cookie](https://github.com/jshttp/cookie) and [express](https://github.com/expressjs/express). These dependencies needed to be updated together. Updates `cookie` from 0.6.0 to 0.7.1 - [Release notes](https://github.com/jshttp/cookie/releases) - [Commits](https://github.com/jshttp/cookie/compare/v0.6.0...v0.7.1) Updates `express` from 4.20.0 to 4.21.1 - [Release notes](https://github.com/expressjs/express/releases) - [Changelog](https://github.com/expressjs/express/blob/4.21.1/History.md) - [Commits](https://github.com/expressjs/express/compare/4.20.0...4.21.1) --- updated-dependencies: - dependency-name: cookie dependency-type: indirect - dependency-name: express dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * docs(virtual_keys.md): update Dockerfile reference (#6554) Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> * (proxy fix) - call connect on prisma client when running setup (#6534) * critical fix - call connect on prisma client when running setup * fix test_proxy_server_prisma_setup * fix test_proxy_server_prisma_setup * Add 3.5 haiku (#6588) * feat: add claude-3-5-haiku-20241022 entries * feat: add claude-3-5-haiku-20241022 and vertex_ai/claude-3-5-haiku@20241022 models * add missing entries, remove vision * remove image token costs * Litellm perf improvements 3 (#6573) * perf: move writing key to cache, to background task * perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils adds 200ms on calls with pgdb connected * fix(litellm_pre_call_utils.py'): rename call_type to actual call used * perf(proxy_server.py): remove db logic from _get_config_from_file was causing db calls to occur on every llm request, if team_id was set on key * fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db reduces latency/call by ~100ms * fix(proxy_server.py): minor fix on existing_settings not incl alerting * fix(exception_mapping_utils.py): map databricks exception string * fix(auth_checks.py): fix auth check logic * test: correctly mark flaky test * fix(utils.py): handle auth token error for tokenizers.from_pretrained * build: fix map * build: fix map * build: fix json for model map * fix ImageObject conversion (#6584) * (fix) litellm.text_completion raises a non-blocking error on simple usage (#6546) * unit test test_huggingface_text_completion_logprobs * fix return TextCompletionHandler convert_chat_to_text_completion * fix hf rest api * fix test_huggingface_text_completion_logprobs * fix linting errors * fix importLiteLLMResponseObjectHandler * fix test for LiteLLMResponseObjectHandler * fix test text completion * fix allow using 15 seconds for premium license check * testing fix bedrock deprecated cohere.command-text-v14 * (feat) add `Predicted Outputs` for OpenAI (#6594) * bump openai to openai==1.54.0 * add 'prediction' param * testing fix bedrock deprecated cohere.command-text-v14 * test test_openai_prediction_param.py * test_openai_prediction_param_with_caching * doc Predicted Outputs * doc Predicted Output * (fix) Vertex Improve Performance when using `image_url` (#6593) * fix transformation vertex * test test_process_gemini_image * test_image_completion_request * testing fix - bedrock has deprecated cohere.command-text-v14 * fix vertex pdf * bump: version 1.51.5 → 1.52.0 * Update setuptools in docker and fastapi to latest verison, in order to upgrade starlette version --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: paul-gauthier <69695708+paul-gauthier@users.noreply.github.com> Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com> Co-authored-by: Jacob Hagstedt <wcgs@novonordisk.com> * fix(langfuse.py): fix linting errors * fix: fix linting errors * fix: fix casting error * fix: fix typing error * fix: add more tests * fix(utils.py): fix return_processed_chunk_logic * Revert "Update setuptools in docker and fastapi to latest verison, in order t…" (#6615) This reverts commit 1a7f7bdfb75df0efbc930b7f2e39febc80e97d5a. * docs fix clarify team_id on team based logging * doc fix team based logging with langfuse * fix flake8 checks * test: bump sleep time * refactor: replace claude-instant-1.2 with haiku in testing * fix(proxy_server.py): move to using sl payload in track_cost_callback * fix(proxy_server.py): fix linting errors * fix(proxy_server.py): fallback to kwargs(response_cost) if given * test: remove claude-instant-1 from tests * test: fix claude test * docs fix clarify team_id on team based logging * doc fix team based logging with langfuse * build: remove lint.yml --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: Vsevolod Karvetskiy <56288164+karvetskiy@users.noreply.github.com> Co-authored-by: seva <seva@inita.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: paul-gauthier <69695708+paul-gauthier@users.noreply.github.com> Co-authored-by: Jacob Hagstedt P Suorra <Jacobh2@users.noreply.github.com> Co-authored-by: Jacob Hagstedt <wcgs@novonordisk.com>
2024-11-07 06:47:05 +08:00
def test_get_langfuse_tags():
"""
Test that _get_langfuse_tags correctly extracts tags from the standard logging payload
"""
# Create a mock logging payload with tags
mock_payload = create_standard_logging_payload()
mock_payload["request_tags"] = ["tag1", "tag2", "test_tag"]
# Test with payload containing tags
result = global_langfuse_logger._get_langfuse_tags(mock_payload)
assert result == ["tag1", "tag2", "test_tag"]
# Test with payload without tags
mock_payload["request_tags"] = None
result = global_langfuse_logger._get_langfuse_tags(mock_payload)
assert result == []
# Test with empty tags list
mock_payload["request_tags"] = []
result = global_langfuse_logger._get_langfuse_tags(mock_payload)
assert result == []
@patch.dict(os.environ, {}, clear=True) # Start with empty environment
def test_get_langfuse_flush_interval():
"""
Test that _get_langfuse_flush_interval correctly reads from environment variable
or falls back to the provided flush_interval
"""
default_interval = 60
# Test when env var is not set
result = LangFuseLogger._get_langfuse_flush_interval(
flush_interval=default_interval
)
assert result == default_interval
# Test when env var is set
with patch.dict(os.environ, {"LANGFUSE_FLUSH_INTERVAL": "120"}):
result = LangFuseLogger._get_langfuse_flush_interval(
flush_interval=default_interval
)
assert result == 120
def test_langfuse_e2e_sync(monkeypatch):
from litellm import completion
import litellm
import respx
import httpx
import time
2025-06-01 03:42:56 +08:00
litellm.disable_aiohttp_transport = True # since this uses respx, we need to set use_aiohttp_transport to False
litellm._turn_on_debug()
monkeypatch.setattr(litellm, "success_callback", ["langfuse"])
with respx.mock:
# Mock Langfuse
# Mock any Langfuse endpoint
langfuse_mock = respx.post(
"https://*.cloud.langfuse.com/api/public/ingestion"
).mock(return_value=httpx.Response(200))
completion(
model="openai/my-fake-endpoint",
messages=[{"role": "user", "content": "hello from litellm"}],
stream=False,
mock_response="Hello from litellm 2",
)
time.sleep(3)
assert langfuse_mock.called
def test_get_chat_content_for_langfuse():
"""
Test that _get_chat_content_for_langfuse correctly extracts content from chat completion responses
"""
# Test with valid response
mock_response = ModelResponse(
choices=[Choices(message=Message(role="assistant", content="Hello world"))]
)
result = LangFuseLogger._get_chat_content_for_langfuse(mock_response)
Litellm dev bedrock anthropic 3 7 v2 (#8843) * feat(bedrock/converse/transformation.py): support claude-3-7-sonnet reasoning_Content transformation Closes https://github.com/BerriAI/litellm/issues/8777 * fix(bedrock/): support returning `reasoning_content` on streaming for claude-3-7 Resolves https://github.com/BerriAI/litellm/issues/8777 * feat(bedrock/): unify converse reasoning content blocks for consistency across anthropic and bedrock * fix(anthropic/chat/transformation.py): handle deepseek-style 'reasoning_content' extraction within transformation.py simpler logic * feat(bedrock/): fix streaming to return blocks in consistent format * fix: fix linting error * test: fix test * feat(factory.py): fix bedrock thinking block translation on tool calling allows passing the thinking blocks back to bedrock for tool calling * fix(types/utils.py): don't exclude provider_specific_fields on model dump ensures consistent responses * fix: fix linting errors * fix(convert_dict_to_response.py): pass reasoning_content on root * fix: test * fix(streaming_handler.py): add helper util for setting model id * fix(streaming_handler.py): fix setting model id on model response stream chunk * fix(streaming_handler.py): fix linting error * fix(streaming_handler.py): fix linting error * fix(types/utils.py): add provider_specific_fields to model stream response * fix(streaming_handler.py): copy provider specific fields and add them to the root of the streaming response * fix(streaming_handler.py): fix check * fix: fix test * fix(types/utils.py): ensure messages content is always openai compatible * fix(types/utils.py): fix delta object to always be openai compatible only introduce new params if variable exists * test: fix bedrock nova tests * test: skip flaky test * test: skip flaky test in ci/cd
2025-02-27 08:05:33 +08:00
assert result["content"] == "Hello world"
assert result["role"] == "assistant"
# Test with empty choices
mock_response = ModelResponse(choices=[])
result = LangFuseLogger._get_chat_content_for_langfuse(mock_response)
assert result is None
def test_get_text_completion_content_for_langfuse():
"""
Test that _get_text_completion_content_for_langfuse correctly extracts content from text completion responses
"""
# Test with valid response
mock_response = TextCompletionResponse(choices=[TextChoices(text="Hello world")])
result = LangFuseLogger._get_text_completion_content_for_langfuse(mock_response)
assert result == "Hello world"
# Test with empty choices
mock_response = TextCompletionResponse(choices=[])
result = LangFuseLogger._get_text_completion_content_for_langfuse(mock_response)
assert result is None
# Test with no choices field
mock_response = TextCompletionResponse()
result = LangFuseLogger._get_text_completion_content_for_langfuse(mock_response)
assert result is None