mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 02:34:29 +00:00
* 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 1a7f7bdfb7
.
* 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>
237 lines
7.8 KiB
Python
237 lines
7.8 KiB
Python
import os
|
|
import sys
|
|
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.types.utils import StandardCallbackDynamicParams
|
|
from litellm.litellm_core_utils.litellm_logging import DynamicLoggingCache
|
|
from unittest.mock import Mock, patch
|
|
|
|
|
|
@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()
|
|
|
|
@pytest.mark.parametrize("metadata", [
|
|
{'a': 1, 'b': 2, 'c': 3},
|
|
{'a': {'nested_a': 1}, 'b': {'nested_b': 2}},
|
|
{'a': [1, 2, 3], 'b': {4, 5, 6}},
|
|
{'a': (1, 2), 'b': frozenset([3, 4]), 'c': {'d': [5, 6]}},
|
|
{'lock': threading.Lock()},
|
|
{'func': lambda x: x + 1},
|
|
{
|
|
'int': 42,
|
|
'str': 'hello',
|
|
'list': [1, 2, 3],
|
|
'set': {4, 5},
|
|
'dict': {'nested': 'value'},
|
|
'non_copyable': threading.Lock(),
|
|
'function': print
|
|
},
|
|
['list', 'not', 'a', 'dict'],
|
|
{'timestamp': datetime.now()},
|
|
{},
|
|
None,
|
|
])
|
|
def test_langfuse_logger_prepare_metadata(metadata):
|
|
global_langfuse_logger._prepare_metadata(metadata)
|