phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 19:54:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
16965 commits 2497 branches 898 tags 550 MiB
Commit graph

1831 commits

Author SHA1 Message Date
Krrish Dholakia
a2ca3887d1 feat(aws_secret_manager.py): allows user to keep a hash of the proxy master key in their env 2024-06-06 15:32:51 -07:00
Krrish Dholakia
e391e30285 refactor: replace 'traceback.print_exc()' with logging library 
allows error logs to be in json format for otel logging
 2024-06-06 13:47:43 -07:00
Ishaan Jaff
3df177d0d0 feat - redact messages from slack alerting 2024-06-06 10:38:15 -07:00
Raymond1415926
f9368228c0 Merge branch 'BerriAI:main' into main 2024-06-06 10:12:20 -07:00
Krrish Dholakia
005128addc feat(router.py): enable settting 'order' for a deployment in model list 
Allows user to control which model gets called first in model group
 2024-06-06 09:46:51 -07:00
Raymond Huang
fe8539923d fix token counter bug 2024-06-05 23:40:55 -07:00
Sha Ahammed Roze
2c2315431a Merge branch 'BerriAI:main' into main 2024-06-06 10:02:15 +05:30
Krrish Dholakia
96b556f385 feat(bedrock_httpx.py): add support for bedrock converse api 
closes https://github.com/BerriAI/litellm/issues/4000
 2024-06-05 21:20:36 -07:00
Ishaan Jaff
d09353a5e7 Merge branch 'main' into patch-1 2024-06-05 13:35:31 -07:00
Sha Ahammed Roze
01e1a8e518 Merge branch 'BerriAI:main' into main 2024-06-05 21:56:41 +05:30
Krrish Dholakia
129745da90 fix(azure.py): support dynamic drop params 2024-06-05 09:03:10 -07:00
Krrish Dholakia
72a0fa7db5 feat(utils.py): support dynamically setting 'drop_params' 
Allows user to turn this on/off for individual calls by passing in as a completion arg
 2024-06-05 08:44:04 -07:00
sha-ahammed
93e7b9346c feat: Add Ollama as a provider in the proxy UI 2024-06-05 16:48:38 +05:30
Ishaan Jaff
53e6286622 fix VertexAIException APIError 2024-06-04 22:11:11 -07:00
Ishaan Jaff
cb810965b5 fix langfuse log metadata 2024-06-04 21:34:49 -07:00
Krish Dholakia
e678dce88b Merge pull request #4009 from BerriAI/litellm_fix_streaming_cost_cal 
fix(utils.py): fix cost calculation for openai-compatible streaming object
 2024-06-04 21:00:22 -07:00
Krish Dholakia
56b5f4bab8 Merge pull request #4015 from BerriAI/litellm_stream_options_fix_2 
feat(utils.py): Support `stream_options` param across all providers
 2024-06-04 20:59:39 -07:00
Krrish Dholakia
3dcf287826 fix(test_completion.py): fix predibase test to be mock + fix optional param mapping for predibase 2024-06-04 20:06:23 -07:00
Krrish Dholakia
1336957077 fix(utils.py): fix 2024-06-04 19:41:20 -07:00
Krrish Dholakia
e279498970 feat(utils.py): support 'stream_options' param across all providers 
Closes https://github.com/BerriAI/litellm/issues/3553
 2024-06-04 19:03:26 -07:00
Krrish Dholakia
5b9808270b fix(utils.py): add coverage for text openai and databricks 2024-06-04 18:27:03 -07:00
Krrish Dholakia
d74ccc6c84 fix(utils.py): fix stream options to return consistent response object 2024-06-04 18:17:45 -07:00
Ishaan Jaff
bf81065ac6 fix - by default log raw curl command on langfuse 2024-06-04 16:30:25 -07:00
Krrish Dholakia
7432c6a4d9 fix(utils.py): fix cost calculation for openai-compatible streaming object 2024-06-04 10:36:25 -07:00
Krrish Dholakia
8a0b4f5bef fix(utils.py): add coverage for azure img gen content policy violation error 2024-06-04 08:29:30 -07:00
Krrish Dholakia
ae52e7559e fix(router.py): use litellm.request_timeout as default for router clients 2024-06-03 14:19:53 -07:00
Ishaan Jaff
6ee073928b Merge pull request #3983 from BerriAI/litellm_log_request_boddy_langfuse 
[Feat] Log Raw Request from LiteLLM on Langfuse - when `"log_raw_request": true`
 2024-06-03 13:42:06 -07:00
Ishaan Jaff
7f824e5705 feat - log raw_request to langfuse / other logging providers 2024-06-03 07:53:52 -07:00
Krrish Dholakia
aa99012397 fix(utils.py): handle else block for get optional params 2024-06-03 07:45:44 -07:00
Krrish Dholakia
594daef07a fix(utils.py): correctly instrument passing through api version in optional param check 2024-06-01 19:31:52 -07:00
Krrish Dholakia
23087295e1 fix(azure.py): support dropping 'tool_choice=required' for older azure API versions 
Closes https://github.com/BerriAI/litellm/issues/3876
 2024-06-01 18:44:50 -07:00
Krish Dholakia
f2ca86b0e7 Merge pull request #3944 from BerriAI/litellm_fix_parallel_streaming 
fix: fix streaming with httpx client
 2024-05-31 21:42:37 -07:00
Krrish Dholakia
ecbb3c54c3 fix(utils.py): support get_max_tokens() call with same model_name as completion 
Closes https://github.com/BerriAI/litellm/issues/3921
 2024-05-31 21:37:51 -07:00
Yulong Liu
4177cf7a59 add document 2024-05-31 18:55:22 -07:00
Krrish Dholakia
3896e3e88f fix: fix streaming with httpx client 
prevent overwriting streams in parallel streaming calls
 2024-05-31 10:55:18 -07:00
lj
f1fe41db74 Merge branch 'main' into fix-pydantic-warnings-again 2024-05-31 11:35:42 +08:00
Krish Dholakia
73e3dba2f6 Merge pull request #3928 from BerriAI/litellm_audio_speech_endpoint 
feat(main.py): support openai tts endpoint
 2024-05-30 17:30:42 -07:00
Krrish Dholakia
6b4153ff03 fix(main.py): add logging to audio_transcription calls 2024-05-30 16:57:11 -07:00
KX
ddb998fac1 fix: add missing seed parameter to ollama input 
Current ollama interfacing does not allow for seed, which is supported in https://github.com/ollama/ollama/blob/main/docs/api.md#parameters and https://github.com/ollama/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values

This resolves that by adding in handling of seed parameter.
 2024-05-31 01:47:56 +08:00
Nir Gazit
8aebad9d25 Revert "Revert "fix: Log errors in Traceloop Integration (reverts previous revert)"" 2024-05-30 04:06:45 +03:00
Krish Dholakia
06ae6cad8d Revert "fix: Log errors in Traceloop Integration (reverts previous revert)" 2024-05-29 16:30:09 -07:00
Krish Dholakia
5063f0eab8 Merge pull request #3846 from nirga/revert-3831-revert-3780-traceloop-failures 
fix: Log errors in Traceloop Integration (reverts previous revert)
 2024-05-29 08:54:01 -07:00
Ishaan Jaff
000f23d005 Merge branch 'main' into litellm_show_openai_params_model_hub 2024-05-27 09:27:56 -07:00
Krrish Dholakia
23542fc1d2 fix(utils.py): support deepinfra optional params 
Fixes https://github.com/BerriAI/litellm/issues/3855
 2024-05-27 09:16:56 -07:00
Ishaan Jaff
50f1cbb1dd fix - return supported_openai_params from get_model_info 2024-05-27 09:00:12 -07:00
Krrish Dholakia
8e9a3fef81 feat(proxy_server.py): expose new /model_group/info endpoint 
returns model-group level info on supported params, max tokens, pricing, etc.
 2024-05-26 14:07:35 -07:00
Nir Gazit
5509e9f531 Revert "Revert "Log errors in Traceloop Integration"" 2024-05-26 12:01:10 +03:00
Ishaan Jaff
af82336cad Merge pull request #3824 from BerriAI/litellm_include_litellm_exception-in-error 
[Feature]: Attach litellm exception in error string
 2024-05-25 17:09:22 -07:00
Krrish Dholakia
b0afacf7e3 fix(proxy_server.py): fix model check for /v1/models endpoint when team has restricted access 2024-05-25 13:02:03 -07:00
Ishaan Jaff
b16c58d521 Revert "Log errors in Traceloop Integration" 2024-05-24 21:25:17 -07:00