Commit graph

7255 commits

Author SHA1 Message Date
Ishaan Jaff
2519879e67 add ImageObject 2024-05-20 10:45:37 -07:00
Krrish Dholakia
372323c38a feat(proxy_server.py): allow admin to return rejected response as string to user
Closes https://github.com/BerriAI/litellm/issues/3671
2024-05-20 10:30:23 -07:00
Ishaan Jaff
a4f906b464 feat - add litellm.ImageResponse 2024-05-20 10:09:41 -07:00
Ishaan Jaff
24951d44a4 feat - working httpx requests vertex ai image gen 2024-05-20 09:51:15 -07:00
Krrish Dholakia
52acd3955d fix(_logging.py): support all logs being in json mode, if enabled 2024-05-20 09:22:59 -07:00
Krrish Dholakia
058bfb101d feat(proxy_cli.py): support json logs on proxy
allow user to enable 'json logs' for proxy server
2024-05-20 09:18:12 -07:00
Krrish Dholakia
25df95ab10 feat(proxy_server.py): new 'supported_openai_params' endpoint
get supported openai params for a given model
2024-05-20 08:39:50 -07:00
Ishaan Jaff
5ba5f15b56 test - test_aimage_generation_vertex_ai 2024-05-20 08:14:43 -07:00
Krish Dholakia
bb85a5e6b2
Merge pull request #3729 from BerriAI/litellm_vertex_history
fix(vertex_ai.py): support passing in result of tool call to vertex
2024-05-20 07:33:05 -07:00
Krrish Dholakia
49b71c8118 fix(vertex_ai.py): revert system instructions - unable to find supported vertex version 2024-05-20 06:30:11 -07:00
Krrish Dholakia
45c46a84d0 fix(vertex_ai.py): support passing system instructions to vertex ai 2024-05-20 06:18:19 -07:00
Krrish Dholakia
6216c3639f fix(types/vertex_ai.py): fix typing 2024-05-19 12:36:05 -07:00
Krish Dholakia
c94ce069f7
Merge pull request #3724 from BerriAI/litellm_gpt_4_response_format_drop_params
fix(utils.py): drop response_format if 'drop_params=True' for gpt-4
2024-05-19 12:35:13 -07:00
Krrish Dholakia
65aacc0c1a fix(vertex_ai.py): use chat_messages_with_history for async + streaming calls 2024-05-19 12:30:24 -07:00
Krrish Dholakia
f9ab72841a fix(vertex_ai.py): passing all tests on 'test_amazing_vertex_completion.py 2024-05-19 12:22:21 -07:00
Krrish Dholakia
a2c66ed4fb fix(vertex_ai.py): support passing in result of tool call to vertex
Fixes https://github.com/BerriAI/litellm/issues/3709
2024-05-19 11:34:07 -07:00
Krrish Dholakia
12942c39db fix(utils.py): drop response_format if 'drop_params=True' for gpt-4 2024-05-18 13:02:48 -07:00
Krish Dholakia
5e5179e476
Merge branch 'main' into litellm_model_id_fix 2024-05-17 22:36:17 -07:00
Krrish Dholakia
5d3fe52a08 test: fix test 2024-05-17 22:35:34 -07:00
Krrish Dholakia
1cecdc4690 fix(utils.py): fix replicate completion cost calculation 2024-05-17 22:18:57 -07:00
Ishaan Jaff
c8a1cf6ce2 (ci/cd) run again 2024-05-17 22:07:21 -07:00
Krrish Dholakia
a75b865ebc test(test_config.py): fix test 2024-05-17 22:00:44 -07:00
Ishaan Jaff
6708a1adaa ui - new build 2024-05-17 21:58:10 -07:00
Ishaan Jaff
8281c150f0
Merge pull request #3713 from BerriAI/litellm_ui_infer_azure_prefix
[Feat] Admin UI - use `base_model` for Slack Alerts
2024-05-17 21:55:23 -07:00
Ishaan Jaff
f7a1675337 fix - cooldown based on exception header 2024-05-17 18:52:45 -07:00
Ishaan Jaff
6368d5a725 feat - read cooldown time from exception header 2024-05-17 18:50:33 -07:00
Krrish Dholakia
4b3551abfc fix(slack_alerting.py): show langfuse traces on error messages 2024-05-17 18:42:30 -07:00
Krish Dholakia
3a06fe2818
Merge branch 'main' into litellm_bedrock_anthropic_fix 2024-05-17 17:47:32 -07:00
Krrish Dholakia
b137cea230 fix(proxy_server.py): fix setting model id for db models
get model_id and use that as it's id in router, this enables `/model/delete` to work with the given id from `/model/info`
2024-05-17 17:45:05 -07:00
Krrish Dholakia
4682802444 fix(bedrock_httpx.py): raise better timeout exception 2024-05-17 17:16:36 -07:00
Krrish Dholakia
b486bb1f8b fix(utils.py): exception map bedrock error 2024-05-17 16:18:25 -07:00
Krrish Dholakia
5d24a72b7e fix(bedrock_httpx.py): support mapping for bedrock cohere command r text 2024-05-17 16:13:49 -07:00
Ishaan Jaff
be273b3c3b fix - show correct base_model in slack alerts 2024-05-17 16:07:02 -07:00
Krrish Dholakia
29a26af298 fix(litellm_license.py): fix json handling 2024-05-17 15:48:39 -07:00
Krrish Dholakia
c0d62e94ae feat(proxy_server.py): enable custom branding + routes on openapi docs
Allows user to add their branding + show only openai routes on docs
2024-05-17 15:21:29 -07:00
Ishaan Jaff
f1a482f358
Merge pull request #3710 from BerriAI/litellm_fix_llm_utils_auth
fix - allow non master key to access llm_utils_routes
2024-05-17 13:52:22 -07:00
hugo.lima
32e25cdb11 added decoding of base64 image data in _gemini_vision_convert_messages function 2024-05-17 16:46:56 +01:00
Ishaan Jaff
cae5ecea8e fix llm utils routes 2024-05-17 08:41:46 -07:00
Ishaan Jaff
c1ed863dfa fix - allow non master key to access llm_utils_routes 2024-05-17 08:25:10 -07:00
Krrish Dholakia
26aefc7cd6 fix(utils.py): support openrouter function calling 2024-05-17 08:02:24 -07:00
Krrish Dholakia
32a04c59cf fix(anthropic.py): bump default anthropic api version for tool use 2024-05-17 00:41:11 -07:00
Krrish Dholakia
9aa05c19d1 fix(bedrock_httpx.py): fix bedrock logging 2024-05-16 23:53:54 -07:00
Krrish Dholakia
0258351c61 fix(main.py): fix async stream handling during bedrock error 2024-05-16 23:37:59 -07:00
Krrish Dholakia
21f2ba6f1f fix(bedrock_httpx.py): logging fixes 2024-05-16 23:20:51 -07:00
Krrish Dholakia
92c2e2af6a fix(bedrock_httpx.py): add async support for bedrock amazon, meta, mistral models 2024-05-16 22:39:25 -07:00
Krish Dholakia
d9ce94ae23
Merge pull request #3703 from msabramo/msabramo/make-langsmith-integration-work-with-custom-langsmith
Work with custom `LANGSMITH_BASE_URL`
2024-05-16 22:23:09 -07:00
Krrish Dholakia
0293f7766a fix(bedrock_httpx.py): move bedrock ai21 calls to being async 2024-05-16 22:21:30 -07:00
Krrish Dholakia
180bc46ca4 fix(bedrock_httpx.py): move anthropic bedrock calls to httpx
Fixing https://github.com/BerriAI/litellm/issues/2921
2024-05-16 21:51:55 -07:00
Ishaan Jaff
12d2dcd48c ci/cd run again 2024-05-16 21:15:06 -07:00
Krrish Dholakia
10a672634d fix(proxy_server.py): fix invalid header string 2024-05-16 21:05:40 -07:00