Commit graph

962 commits

Author SHA1 Message Date
ishaan-jaff
823a932377 (feat) support extra body for Azure, OpenAI 2024-01-13 14:32:11 -08:00
ishaan-jaff
e67ac90796 (fix) check if custom_llm_provider is not None 2024-01-13 12:54:03 -08:00
ishaan-jaff
8e6d170da9 (feat) use custom_llm_provider in completion_cost 2024-01-13 12:29:51 -08:00
Krrish Dholakia
f08bb7e41f fix(utils.py): exclude s3 caching from individual item caching for embedding list
can't bulk upload to s3, so this will slow down calls

https://github.com/BerriAI/litellm/pull/1417
2024-01-13 16:19:30 +05:30
Krrish Dholakia
79cc739b53 fix(caching.py): fix async in-memory caching 2024-01-13 15:33:57 +05:30
Krrish Dholakia
cdadac1649 fix(caching.py): return updated kwargs from get_cache helper function 2024-01-13 15:04:34 +05:30
Krrish Dholakia
880f829013 fix(caching.py): use bulk writes and blockconnectionpooling for reads from Redis 2024-01-13 11:50:50 +05:30
ishaan-jaff
69552146f9 (feat) return custom_llm_provider in streaming response 2024-01-12 17:14:43 -08:00
Krrish Dholakia
813fb19620 fix: support async redis caching 2024-01-12 21:46:41 +05:30
David Leen
1660e4ab72 improve bedrock exception granularity 2024-01-12 16:38:55 +01:00
Krish Dholakia
7ecfc09221 Merge branch 'main' into litellm_embedding_caching_updates 2024-01-11 23:58:51 +05:30
Ishaan Jaff
8b0f93dd2d Merge pull request #1422 from dleen/httpx
(fix) create httpx.Request instead of httpx.request
2024-01-11 22:31:55 +05:30
David Leen
3cd5ef9a02 (fix) create httpx.Request instead of httpx.request
fixes #1420
2024-01-11 16:22:26 +01:00
Krrish Dholakia
107ba5aece fix(utils.py): use preset cache key for async calls as well 2024-01-11 19:30:28 +05:30
Krrish Dholakia
4ed9f2b712 fix(utils.py): bug fixes 2024-01-11 19:02:17 +05:30
Krrish Dholakia
63298d6c75 fix(utils.py): bug fixes 2024-01-11 18:14:22 +05:30
ishaan-jaff
50aeec537c (feat) improve litellm verbose logs 2024-01-11 18:13:08 +05:30
ishaan-jaff
859eb0d98e (feat) show args passed to litellm.completion, acompletion on call 2024-01-11 17:56:27 +05:30
Krrish Dholakia
66addb1a01 fix(utils.py): support caching individual items in embedding input list
https://github.com/BerriAI/litellm/issues/1350
2024-01-11 16:51:34 +05:30
Ishaan Jaff
6e1be43595 Merge pull request #1200 from MateoCamara/explicit-args-acomplete
feat: added explicit args to acomplete
2024-01-11 10:39:05 +05:30
ishaan-jaff
426ce91481 (fix) working s3 logging 2024-01-11 08:57:32 +05:30
Krrish Dholakia
3ed296e2dd fix(utils.py): raise correct error for azure content blocked error 2024-01-10 23:31:51 +05:30
Mateo Cámara
fb37ea291e Merge branch 'main' into explicit-args-acomplete 2024-01-09 13:07:37 +01:00
Ishaan Jaff
b09f38e835 Merge pull request #1381 from BerriAI/litellm_content_policy_violation_exception
[Feat] Add litellm.ContentPolicyViolationError
2024-01-09 17:18:29 +05:30
ishaan-jaff
650a6a8640 (chore) remove deprecated completion_with_config() tests 2024-01-09 17:13:06 +05:30
ishaan-jaff
1a4b522fbb (feat) add ContentPolicyViolationError for azure 2024-01-09 16:58:09 +05:30
ishaan-jaff
a6c45be9f2 (fix) ContentPolicyViolationError 2024-01-09 16:53:15 +05:30
Mateo Cámara
fb4b5eb4c1 Added test to check if acompletion is using the same parameters as CompletionRequest attributes. Added functools to client decorator to expose acompletion parameters from outside. 2024-01-09 12:06:49 +01:00
ishaan-jaff
66b23ecbb5 (v0) add ContentPolicyViolationError 2024-01-09 16:33:03 +05:30
ishaan-jaff
3081dc525a (feat) litellm.completion - support ollama timeout 2024-01-09 10:34:41 +05:30
Krrish Dholakia
5a7d2d9c80 fix(utils.py): error handling for litellm --model mistral edge case 2024-01-08 15:09:01 +05:30
Krrish Dholakia
5daa3ce237 fix(main.py): support cost calculation for text completion streaming object 2024-01-08 12:41:43 +05:30
Krrish Dholakia
f79113a7ac fix(utils.py): fix logging for text completion streaming 2024-01-08 12:05:28 +05:30
Krrish Dholakia
9cbb796874 fix(utils.py): fix exception raised 2024-01-08 07:42:17 +05:30
Krrish Dholakia
d8a2675643 fix(utils.py): map optional params for gemini 2024-01-08 07:38:55 +05:30
Krrish Dholakia
4c385a8cf5 bump: version 1.16.16 → 1.16.17 2024-01-08 07:16:37 +05:30
Krish Dholakia
67ecab4b38 Merge pull request #1344 from BerriAI/litellm_speed_improvements
Litellm speed improvements
2024-01-06 22:38:10 +05:30
Krrish Dholakia
2d1871a1ae fix(factory.py): support gemini-pro-vision on google ai studio
https://github.com/BerriAI/litellm/issues/1329
2024-01-06 22:36:22 +05:30
Krrish Dholakia
9c4cc06e64 fix(utils.py): handle original_response being a json 2024-01-06 17:02:50 +05:30
ishaan-jaff
eb8dba100d (fix) caching use same "created" in response_object 2024-01-05 16:03:56 +05:30
ishaan-jaff
9dc0074613 (feat) completion_cost: improve model=None error 2024-01-05 15:26:04 +05:30
ishaan-jaff
9313bda4c8 (feat) completion_cost - embeddings + raise Exception 2024-01-05 13:11:23 +05:30
Krrish Dholakia
52b78dc074 fix(utils.py): fix check for if cached response should be returned 2024-01-04 21:49:19 +05:30
Krrish Dholakia
6f7c764d5e fix(utils.py): raise a bad request error if litellm client raises a model /provider not found error 2024-01-04 15:50:43 +05:30
Krrish Dholakia
5aecbced99 feat(proxy_server.py): abstract config update/writing and support persisting config in db
allows user to opt into writing to db (SAVE_CONFIG_TO_DB) and removes any api keys before sending to db

 https://github.com/BerriAI/litellm/issues/1322
2024-01-04 14:44:59 +05:30
Krrish Dholakia
176af67aac fix(caching.py): support ttl, s-max-age, and no-cache cache controls
https://github.com/BerriAI/litellm/issues/1306
2024-01-03 12:42:43 +05:30
ishaan-jaff
f67b56ddf5 (fix) azure+stream: count completion tokens 2024-01-03 12:06:39 +05:30
ishaan-jaff
f582ef666f (fix) counting response tokens+streaming 2024-01-03 12:06:39 +05:30
Krrish Dholakia
adef0d9410 bump: version 1.16.10 → 1.16.11 2024-01-02 22:26:47 +05:30
ishaan-jaff
0e8809abf2 (feat) add xinference as an embedding provider 2024-01-02 15:32:26 +05:30