Commit graph

15504 commits

Author SHA1 Message Date
Ishaan Jaff
bd160745f9
Merge pull request #4379 from 7HR4IZ3/main
fix: Lunary integration
2024-06-24 08:11:19 -07:00
Ishaan Jaff
acbcfef5af fix ui login bug 2024-06-24 07:54:08 -07:00
7HR4IZ3
515dc9acc7
fix: Lunary integration
Fixes the bug of litellm not logging system messages to lunary
2024-06-24 14:09:40 +01:00
Islam Nofl
e2af13550a
Rename ollama prompt 'Function' word to 'Name' 2024-06-24 08:01:15 +03:00
corrm
b8a8b0847c Added improved function name handling in ollama_async_streaming 2024-06-24 05:56:56 +03:00
corrm
423a60c8bc chore: Improved OllamaConfig get_required_params and ollama_acompletion and ollama_async_streaming functions 2024-06-24 05:55:22 +03:00
corrm
b2c1a3ad79 chore: Improved prompt generation in ollama_pt function 2024-06-24 05:54:58 +03:00
Brian Schultheiss
5a6588342c added test for change 2024-06-23 15:19:54 -07:00
Brian Schultheiss
3fbb25f903 Updated more references to AWS session token 2024-06-23 13:37:38 -07:00
Brian Schultheiss
7f91e53548 updated documentation to reference boto3.client credential extraction, and update boto3.client creation to support session_token. 2024-06-23 13:15:04 -07:00
Brian Schultheiss
8ad1ae73e5 Support aws_session_token for bedrock client. https://github.com/BerriAI/litellm/issues/4346 2024-06-23 12:51:25 -07:00
Krrish Dholakia
769c60e4f6 test: skip unstable tests 2024-06-23 00:30:45 -07:00
Krrish Dholakia
3d09a196a4 test(test_completion.py): handle replicate api error 2024-06-23 00:06:15 -07:00
Krrish Dholakia
9cff2b03f3 test(test_proxy_server_langfuse.py): cleanup tests causing OOM issues. 2024-06-22 23:53:18 -07:00
Krrish Dholakia
d857d82b0e fix(redact_messages.py): fix pr 2024-06-22 23:27:13 -07:00
Krrish Dholakia
9450d2cf77 fix(test_dynamic_rate_limit_handler.py): cleanup 2024-06-22 22:43:56 -07:00
Krrish Dholakia
dc43ffb771 fix(redact_messages.py): fix get 2024-06-22 21:57:54 -07:00
Krrish Dholakia
4d9a0d45b2 docs(team_budgets.md): cleanup docs 2024-06-22 21:38:01 -07:00
Krrish Dholakia
bf12536fdb bump: version 1.40.24 → 1.40.25 2024-06-22 21:34:55 -07:00
Krish Dholakia
9bffa9a48e
Merge pull request #4352 from msabramo/msabramo/turn-on-message-logging-via-request-header
Disable message redaction in logs via request header
2024-06-22 21:30:41 -07:00
Krish Dholakia
5e11702677
Merge pull request #4365 from BerriAI/litellm_azure_content_filter_fallbacks
fix(router.py): Content Policy Fallbacks for Azure 'content_filter' responses
2024-06-22 21:28:36 -07:00
Krish Dholakia
0454c0781a
Merge branch 'main' into litellm_azure_content_filter_fallbacks 2024-06-22 21:28:29 -07:00
Krrish Dholakia
cea630022e fix(add-exception-mapping-+-langfuse-exception-logging-for-streaming-exceptions): add exception mapping + langfuse exception logging for streaming exceptions
Fixes https://github.com/BerriAI/litellm/issues/4338
2024-06-22 21:26:15 -07:00
Krrish Dholakia
0fd9033502 fix(vertex_httpx.py): flush remaining chunks from stream 2024-06-22 20:33:54 -07:00
Krrish Dholakia
73254987da fix(vertex_httpx.py): ignore vertex finish reason - wait for stream to end
Fixes https://github.com/BerriAI/litellm/issues/4339
2024-06-22 20:21:01 -07:00
Ishaan Jaff
8a66e074ce fix in mem cache tests 2024-06-22 19:52:18 -07:00
Ishaan Jaff
fbef5013a1
Merge branch 'main' into litellm_fix_in_mem_usage 2024-06-22 19:23:37 -07:00
Ishaan Jaff
0418db3044 fix caching clear in memory cache mem util 2024-06-22 19:21:37 -07:00
Krish Dholakia
eaad36a2cb
Merge pull request #4349 from BerriAI/litellm_dynamic_tpm_limits
feat(dynamic_rate_limiter.py): Dynamic tpm quota (multiple projects)
2024-06-22 19:15:05 -07:00
Krish Dholakia
961e7ac95d
Merge branch 'main' into litellm_dynamic_tpm_limits 2024-06-22 19:14:59 -07:00
Krrish Dholakia
2c7a80d08d fix(router.py): check if azure returns 'content_filter' response + fallback available -> fallback
Exception maps azure content filter response exceptions
2024-06-22 19:10:15 -07:00
Ishaan Jaff
fa554ae218 fix - clean up in memory cache 2024-06-22 18:46:30 -07:00
Ishaan Jaff
4fc8efd640 bump: version 1.40.23 → 1.40.24 2024-06-22 18:00:40 -07:00
Ishaan Jaff
3105eaebc3 feat - add debug_utils 2024-06-22 16:12:42 -07:00
Krrish Dholakia
c4b1540ce0 fix(utils.py): support streamingchoices in 'get_response_string 2024-06-22 15:45:52 -07:00
Krrish Dholakia
bae7377128 docs(team_budgets.md): fix script
/
2024-06-22 15:42:05 -07:00
Krrish Dholakia
fc4e900a23 docs(team_budgets.md): update docs with script for testing dynamic rate limiting 2024-06-22 15:26:58 -07:00
Krrish Dholakia
a31a05d45d feat(dynamic_rate_limiter.py): working e2e 2024-06-22 14:41:22 -07:00
Ishaan Jaff
cb828a464a fix langfuse tests in_memory_langfuse_clients 2024-06-22 13:59:36 -07:00
Ishaan Jaff
ebbe97910c
Merge pull request #4360 from BerriAI/litellm_fix_access_audio_endpoint
fix[ - Can't access /v1/audio/speech with some user key
2024-06-22 13:46:50 -07:00
Ishaan Jaff
ab38a90be0 fix /audio/speech 2024-06-22 13:45:34 -07:00
Ishaan Jaff
c44e5a3d93 testing - use in memory langfuse client cache 2024-06-22 13:40:34 -07:00
Ishaan Jaff
b201402b0b fix testing - we had two files running the exact same langfuse test 2024-06-22 13:32:28 -07:00
Ishaan Jaff
c4f6b903b3 ui - new build 2024-06-22 09:13:34 -07:00
Ishaan Jaff
1a4ddf9a8e
Merge pull request #4356 from BerriAI/litellm_test_routes_on_proxy
[Test] Test routes on LiteLLM Proxy always includes OpenAI Routes
2024-06-22 09:12:30 -07:00
Ishaan Jaff
d32b8d589b
Merge pull request #4357 from BerriAI/litellm_use_jwt_in_cookies
[Security Fix - Proxy Server ADMIN UI] - Store credentials in cookies + use strong JWT signing secret
2024-06-22 09:12:17 -07:00
Krrish Dholakia
f814f24d9d fix(litellm_logging.py): Fix gemini google ai studio system prompt logging
Fixes https://github.com/BerriAI/litellm/issues/2963
2024-06-22 09:11:23 -07:00
Ishaan Jaff
066ed01d0f read token from cookie 2024-06-22 09:05:06 -07:00
Ishaan Jaff
c86efa55a5 use hash of master key encode the jwt 2024-06-22 08:58:31 -07:00
Ishaan Jaff
03d1d9229d ui - use cookies to return JWTs 2024-06-22 08:50:26 -07:00