mirror of
https://github.com/tiennm99/litellm.git
synced 2026-07-06 11:10:14 +00:00
136693cac4
* 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>
87 lines
2.1 KiB
Python
87 lines
2.1 KiB
Python
#### What this tests ####
|
|
# This tests calling batch_completions by running 100 messages together
|
|
|
|
import sys, os
|
|
import traceback
|
|
import pytest
|
|
|
|
sys.path.insert(
|
|
0, os.path.abspath("../..")
|
|
) # Adds the parent directory to the system path
|
|
from openai import APITimeoutError as Timeout
|
|
import litellm
|
|
|
|
litellm.num_retries = 0
|
|
from litellm import (
|
|
batch_completion,
|
|
batch_completion_models,
|
|
completion,
|
|
batch_completion_models_all_responses,
|
|
)
|
|
|
|
# litellm.set_verbose=True
|
|
|
|
|
|
def test_batch_completions():
|
|
messages = [[{"role": "user", "content": "write a short poem"}] for _ in range(3)]
|
|
model = "gpt-3.5-turbo"
|
|
litellm.set_verbose = True
|
|
try:
|
|
result = batch_completion(
|
|
model=model,
|
|
messages=messages,
|
|
max_tokens=10,
|
|
temperature=0.2,
|
|
request_timeout=1,
|
|
)
|
|
print(result)
|
|
print(len(result))
|
|
assert len(result) == 3
|
|
|
|
for response in result:
|
|
assert response.choices[0].message.content is not None
|
|
except Timeout as e:
|
|
print(f"IN TIMEOUT")
|
|
pass
|
|
except Exception as e:
|
|
pytest.fail(f"An error occurred: {e}")
|
|
|
|
|
|
# test_batch_completions()
|
|
|
|
|
|
def test_batch_completions_models():
|
|
try:
|
|
result = batch_completion_models(
|
|
models=["gpt-3.5-turbo", "gpt-3.5-turbo", "gpt-3.5-turbo"],
|
|
messages=[{"role": "user", "content": "Hey, how's it going"}],
|
|
)
|
|
print(result)
|
|
except Timeout as e:
|
|
pass
|
|
except Exception as e:
|
|
pytest.fail(f"An error occurred: {e}")
|
|
|
|
|
|
# test_batch_completions_models()
|
|
|
|
|
|
def test_batch_completion_models_all_responses():
|
|
try:
|
|
responses = batch_completion_models_all_responses(
|
|
models=["j2-light", "claude-3-haiku-20240307"],
|
|
messages=[{"role": "user", "content": "write a poem"}],
|
|
max_tokens=10,
|
|
)
|
|
print(responses)
|
|
assert len(responses) == 2
|
|
except Timeout as e:
|
|
pass
|
|
except litellm.APIError as e:
|
|
pass
|
|
except Exception as e:
|
|
pytest.fail(f"An error occurred: {e}")
|
|
|
|
|
|
# test_batch_completion_models_all_responses()
|