Commit Graph
15397 Commits
Author SHA1 Message Date
Krish DholakiaandGitHub 653aefde40 Merge branch 'main' into litellm_async_cohere_calls 2024-07-30 15:35:20 -07:00
Krish DholakiaandGitHub 3a70849ce0 Merge pull request #4976 from BerriAI/litellm_huggingface_embedding_fixes
feat(huggingface_restapi.py): Support multiple hf embedding types + async hf embeddings
2024-07-30 15:34:44 -07:00
Krrish Dholakia 84513c0254 test(test_streaming.py): move to mock implementation for sagemaker streaming tests 2024-07-30 15:34:27 -07:00
Krrish Dholakia e1cbb397fe test(test_streaming.py): handle predibase instability 2024-07-30 15:32:36 -07:00
Krrish Dholakia ec6db03c41 fix(router.py): gracefully handle scenario where completion response doesn't have total tokens
Closes https://github.com/BerriAI/litellm/issues/4968
2024-07-30 15:14:03 -07:00
Krrish Dholakia 311521e56e fix(ollama.py): correctly raise ollama streaming error
Fixes https://github.com/BerriAI/litellm/issues/4974
2024-07-30 15:01:26 -07:00
Krrish Dholakia 9b2eb1702b fix(cohere.py): support async cohere embedding calls 2024-07-30 14:49:07 -07:00
Krrish Dholakia 43958907bf fix(huggingface_restapi.py): fix linting errors 2024-07-30 14:33:08 -07:00
Krrish Dholakia 185a6857f9 fix(utils.py): fix cost tracking for vertex ai partner models 2024-07-30 14:20:52 -07:00
Krrish Dholakia 99dc7d2e97 fix(main.py): fix linting error 2024-07-30 13:55:04 -07:00
Krrish Dholakia 250f28b3a2 style(cohere.py): point to cohere_chat docs for updated doc info 2024-07-30 13:47:15 -07:00
Krrish Dholakia d0971dd50e docs(supported_embedding.md): add specifying input_type for huggingface embedding calls 2024-07-30 13:45:38 -07:00
Ishaan JaffandGitHub 6b17e84204 Merge pull request #4975 from BerriAI/ui_switch_off_console_logs_in_prod
Proxy Admin UI - switch off console logs in production mode
2024-07-30 13:34:59 -07:00
Ishaan Jaff d5593a9106 ui new build 2024-07-30 13:33:34 -07:00
Krrish Dholakia 69afbc6091 feat(huggingface_restapi.py): Support multiple hf embedding types + async hf embeddings
Closes https://github.com/BerriAI/litellm/issues/3261
2024-07-30 13:32:03 -07:00
Ishaan JaffandGitHub e0d0d45e87 Merge pull request #4973 from BerriAI/litellm_return_code_as_str
[Fix-Proxy] ProxyException code as str - Make OpenAI Compatible
2024-07-30 13:27:33 -07:00
Ishaan JaffandGitHub afad69b147 Merge pull request #4969 from BerriAI/litellm_get_batches
[Feature]: GET /v1/batches to return list of batches
2024-07-30 13:27:22 -07:00
Ishaan Jaff 896026c468 switch off prod logs on ui 2024-07-30 13:23:45 -07:00
Ishaan Jaff 7f847f194d swithc off console log in prod 2024-07-30 13:02:55 -07:00
Ishaan Jaff 66211b42db fix linting errors 2024-07-30 12:51:39 -07:00
Ishaan Jaff e7b78a3337 add docs on status code from exceptions 2024-07-30 12:38:33 -07:00
Ishaan Jaff 74c4e3def8 return ProxyException code as str 2024-07-30 12:35:46 -07:00
Krrish Dholakia f1b7d2318c docs(input.md): update docs to show ollama tool calling 2024-07-30 09:56:24 -07:00
Ishaan Jaff 1e1bce4594 docs LIST batches 2024-07-30 09:49:11 -07:00
Ishaan Jaff 563d59a305 test batches endpoint on proxy 2024-07-30 09:46:30 -07:00
Ishaan Jaff 4206354ee7 test - list batches 2024-07-30 08:19:25 -07:00
Ishaan Jaff 43a06f408c feat add support for alist_batches 2024-07-30 08:18:52 -07:00
Ishaan JaffandGitHub 36dca6bcce Merge pull request #4956 from BerriAI/litellm_add_finetuning_Endpoints
[Feat] Add `litellm.create_fine_tuning_job()` , `litellm.list_fine_tuning_jobs()`, `litellm.cancel_fine_tuning_job()` finetuning endpoints
2024-07-30 07:47:29 -07:00
Ishaan Jaff c64b44aa0e bump: version 1.42.5 → 1.42.6 2024-07-29 21:39:29 -07:00
Krrish Dholakia 259e3b1245 fix(cohere_chat.py): handle tool_result + user message being passed in 2024-07-29 21:38:45 -07:00
Ishaan Jaff 6f34998cab ui new build 2024-07-29 21:20:27 -07:00
Krrish Dholakia 7d5022b0e0 docs(scheduler.md): update docs with request timeout 2024-07-29 21:18:12 -07:00
Ishaan Jaff 19d57314ee fix inc langfuse flish time 2024-07-29 20:14:45 -07:00
Ishaan Jaff dff8163f2c fix type errors 2024-07-29 20:10:33 -07:00
Ishaan Jaff f18827cbc0 fix type errors 2024-07-29 20:10:03 -07:00
Ishaan Jaff 6abc49c611 fix linting 2024-07-29 20:01:12 -07:00
Ishaan Jaff c9bea3a879 test - async ft jobs 2024-07-29 19:52:14 -07:00
Ishaan Jaff 106626f224 test - list_fine_tuning_jobs 2024-07-29 19:47:14 -07:00
Ishaan Jaff 4849df03ff add list fine tune endpoints 2024-07-29 19:46:55 -07:00
Krrish Dholakia 76f4aa80e3 docs(deploy.md): support running litellm docker container without internet connection 2024-07-29 19:40:12 -07:00
Ishaan Jaff 46772436f1 async cancel ft job 2024-07-29 19:25:36 -07:00
Ishaan Jaff 8e6df89f8a fix doc string 2024-07-29 19:23:35 -07:00
Ishaan Jaff 16d595c4ff test cancel cancel_fine_tuning_job 2024-07-29 19:22:41 -07:00
Ishaan Jaff 3802eaa6b5 feat - add cancel_fine_tuning_job 2024-07-29 19:22:23 -07:00
Ishaan Jaff 3e3f9e3f0c add test_create_fine_tune_job 2024-07-29 18:59:55 -07:00
Ishaan Jaff 5123bf4e75 add types for FineTuningJobCreate OpenAI 2024-07-29 18:59:44 -07:00
Ishaan Jaff 1202e1c645 add acreate_fine_tuning_job 2024-07-29 18:59:29 -07:00
Ishaan Jaff 59fc3ba649 add create_fine_tuning 2024-07-29 18:57:29 -07:00
Ishaan Jaff 130815bb93 add litellm.create_fine_tuning_job 2024-07-29 18:42:42 -07:00
Krrish Dholakia 528741a809 fix(factory.py): handle special keys for mistral chat template 2024-07-29 17:47:44 -07:00