phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
3369 commits 2484 branches 894 tags 537 MiB
Commit graph

545 commits

Author SHA1 Message Date
Krrish Dholakia
cf0a9f591c fix(router.py): introducing usage-based-routing 2023-11-17 17:56:26 -08:00
ishaan-jaff
0ba90475c9 (feat) support parallel function calling 2023-11-17 15:51:27 -08:00
ishaan-jaff
698f47c226 (feat) improve logging - show model_call_details 2023-11-17 15:51:27 -08:00
Krrish Dholakia
02ed97d0b2 fix(acompletion): support client side timeouts + raise exceptions correctly for async calls 2023-11-17 15:39:47 -08:00
ishaan-jaff
ef8d82a54c (feat) completion: add response_format, seed, tools, tool_choice 2023-11-17 13:59:57 -08:00
ishaan-jaff
e9f6741b0b (v1.0+ breaking change) get_max_tokens -> return int 2023-11-17 10:38:50 -08:00
Krrish Dholakia
1e0560e4d2 fix(utils.py): improve exception mapping for vertex ai 2023-11-16 22:02:26 -08:00
Krrish Dholakia
d9123ea2e8 docs(routing.md): update tutorial on deploying router 2023-11-16 21:46:43 -08:00
Krrish Dholakia
48a508bab6 feat: global client for sync + async calls (openai + Azure only) 2023-11-16 14:44:13 -08:00
Krrish Dholakia
a6e9f147d3 fix(openai.py): handling extra headers 2023-11-16 12:48:21 -08:00
ishaan-jaff
56838ee815 (fix) bedrock meta llama optional params 2023-11-16 12:38:27 -08:00
ishaan-jaff
55a054f3f6 (fix) only decode chunk when it's not a str 2023-11-16 12:24:31 -08:00
Krrish Dholakia
e54056f0ed fix(azure.py): use openai client sdk for handling sync+async calling 2023-11-16 12:08:12 -08:00
ishaan-jaff
aa84ca04d8 (fix) HF api + streaming 2023-11-16 11:59:56 -08:00
ishaan-jaff
fb2d398d2c (fix) langfuse logging + openai streaming when chunk = [DONE} 2023-11-16 10:45:35 -08:00
Krrish Dholakia
9c7cc84eb0 fix(openai.py): supporting openai client sdk for handling sync + async calls (incl. for openai-compatible apis) 2023-11-16 10:35:03 -08:00
Ishaan Jaff
da9a0ab928 Merge pull request #811 from dchristian3188/bedrock-llama 
Bedrock llama
 2023-11-16 07:57:50 -08:00
Ishaan Jaff
d6d0cbd63c Merge pull request #826 from rodneyxr/ollama-fixes 
Fix typo for initial_prompt_value and too many values to unpack error
 2023-11-16 07:55:53 -08:00
David Christian
461115330b updated utils for bedrock.meta streaming 2023-11-16 07:12:27 -08:00
Krrish Dholakia
ef4e5b9636 test: set request timeout at request level 2023-11-15 17:42:31 -08:00
Rodney Rodriguez
f2d8bfd40d bugfixes for ollama 2023-11-15 19:27:06 -06:00
Krrish Dholakia
b42cf80585 fix(utils): fixing exception mapping 2023-11-15 15:51:17 -08:00
Krrish Dholakia
0ede0e836e feat(get_max_tokens): get max tokens for huggingface hub models 2023-11-15 15:25:40 -08:00
Krrish Dholakia
e35ce15a89 refactor(huggingface_restapi.py): moving async completion + streaming to real async calls 2023-11-15 15:14:21 -08:00
Krrish Dholakia
04ce14e404 fix(utils.py): fix langfuse integration 2023-11-15 14:05:40 -08:00
Krrish Dholakia
e324388520 fix(utils.py): check for none params 2023-11-15 13:39:09 -08:00
Krrish Dholakia
8eaa1eb37f fix(utils.py): azure streaming initial format 2023-11-15 13:30:08 -08:00
Krrish Dholakia
e5929f2f7e fix(azure.py-+-proxy_server.py): fix function calling response object + support router on proxy 2023-11-15 13:15:16 -08:00
Krrish Dholakia
29a0c29eb3 fix(utils.py): await async function in client wrapper 2023-11-14 22:07:28 -08:00
Krrish Dholakia
0f6713993d fix(router.py): enabling retrying with expo backoff (without tenacity) for router 2023-11-14 20:57:51 -08:00
ishaan-jaff
9585856b9f (feat) debug POST logs 2023-11-14 18:16:45 -08:00
ishaan-jaff
838cb3e20b (fix) debugging with POST request 2023-11-14 18:05:34 -08:00
ishaan-jaff
e0f7120459 (feat) improve logging of raw POST curl command 2023-11-14 17:54:09 -08:00
ishaan-jaff
c7fbbe8764 (feat) add ability to view POST requests from litellm.completion() 2023-11-14 17:27:20 -08:00
Krrish Dholakia
9b582b2c85 fix(main.py): keep client consistent across calls + exponential backoff retry on ratelimit errors 2023-11-14 16:26:05 -08:00
Krrish Dholakia
526eb99ade fix(palm.py): exception mapping bad requests / filtered responses 2023-11-14 11:53:13 -08:00
Jack Collins
abbf19bce2 Provide response to ServiceUnavailableError where needed 2023-11-13 21:20:40 -08:00
Krrish Dholakia
34fea89fb0 fix(utils.py): streaming 2023-11-13 18:15:14 -08:00
Krrish Dholakia
c86be7665d test(utils.py): adding logging for azure streaming 2023-11-13 17:53:15 -08:00
Krrish Dholakia
40f5805386 test(utils.py): test logging 2023-11-13 17:41:45 -08:00
Krrish Dholakia
b572e9fe3a test(utils.py): add logging and fix azure streaming 2023-11-13 17:24:13 -08:00
Krrish Dholakia
63daffb91b test(utils.py): additional logging 2023-11-13 17:13:41 -08:00
Krrish Dholakia
97e8fc640c test(utils.py): additional logging 2023-11-13 17:06:24 -08:00
Krrish Dholakia
e984122117 test(utils.py): additional logging 2023-11-13 16:59:04 -08:00
Krrish Dholakia
39e784fb8b test(utils.py): adding more logging for streaming test 2023-11-13 16:54:16 -08:00
Krrish Dholakia
777a924e6b fix(utils.py): fix response object mapping 2023-11-13 15:58:25 -08:00
David Christian
9c4afd87ed added support for bedrock llama models 2023-11-13 15:41:21 -08:00
Krrish Dholakia
11b63bfba7 fix(promptlayer.py): fixing promptlayer logging integration 2023-11-13 15:04:15 -08:00
Krrish Dholakia
6ca8528c25 fix(main.py): fix linting errors 2023-11-13 14:52:37 -08:00
Krrish Dholakia
330708e7ef fix(tests): fixing response objects for testing 2023-11-13 14:39:30 -08:00