Commit graph

506 commits

Author SHA1 Message Date
Krrish Dholakia
37de964da4 fix(ollama_chat.py): fix the way optional params are passed in 2024-01-30 15:48:48 -08:00
Ishaan Jaff
dd9c78819a
Merge pull request #1689 from BerriAI/litellm_set_organization_on_config.yaml
[Feat] Set OpenAI organization for litellm.completion, Proxy Config
2024-01-30 11:47:42 -08:00
ishaan-jaff
e011c4a989 (fix) use OpenAI organization in ahealth_check 2024-01-30 11:45:22 -08:00
ishaan-jaff
ae4e273db7 (feat) OpenAI set organization 2024-01-30 10:54:56 -08:00
Ishaan Jaff
2686ec0f9f
Merge pull request #1685 from BerriAI/litellm_bedrock_emb_input
[Fix] Graceful rejection of token input for AWS Embeddings API
2024-01-30 10:32:14 -08:00
Krish Dholakia
c53ad878b3
Merge pull request #1657 from eslamkarim/patch-1
Change quota project to the correct project being used for the call
2024-01-30 08:40:09 -08:00
ishaan-jaff
f941c57688 (fix) use isinstance to check types 2024-01-30 08:31:21 -08:00
ishaan-jaff
b9a117fa1d (feat) Bedrock embedding - raise correct exception BadRequest 2024-01-30 08:14:35 -08:00
Krrish Dholakia
03961bb8c6 fix(factory.py): fix mistral prompt template - doesn't support <<sys>> tokens 2024-01-30 07:42:59 -08:00
Samay Kapadia
7d7107cbe1
fix mistral's prompt template 2024-01-29 12:28:58 +01:00
Eslam karim gaber
2b3965dbf5
imports 2024-01-28 23:14:06 +02:00
Eslam karim gaber
48dbdaa73e
Change quota project to the correct project being used for the call
if not set it will use the default project in the ADC to set that quota project which is usually different 
https://github.com/googleapis/python-aiplatform/issues/2557#issuecomment-1709284744
2024-01-28 19:55:01 +02:00
Krish Dholakia
ba4089824d
Merge pull request #1646 from BerriAI/litellm_image_gen_cost_tracking_proxy
Litellm image gen cost tracking proxy
2024-01-26 22:30:14 -08:00
Krrish Dholakia
d755d50901 fix(openai.py): fix openai image gen logging 2024-01-26 21:05:49 -08:00
Krrish Dholakia
f5da95685a feat(utils.py): support region based pricing for bedrock + use bedrock's token counts if given 2024-01-26 14:53:58 -08:00
Krrish Dholakia
09ec6d6458 fix(utils.py): fix sagemaker async logging for sync streaming
https://github.com/BerriAI/litellm/issues/1592
2024-01-25 12:49:45 -08:00
Krrish Dholakia
43f139fafd fix(ollama_chat.py): fix default token counting for ollama chat 2024-01-24 20:09:17 -08:00
Krrish Dholakia
f19f0dad89 fix(router.py): fix client init 2024-01-22 22:15:39 -08:00
Ishaan Jaff
6d105754d7
Merge pull request #1561 from BerriAI/litellm_sagemaker_streaming
[Feat] Add REAL Sagemaker streaming
2024-01-22 22:10:20 -08:00
ishaan-jaff
802fd6cebf v0 add TokenIterator, stream support 2024-01-22 21:49:44 -08:00
Krrish Dholakia
5e0d99b2ef fix(router.py): fix order of dereferenced dictionaries 2024-01-22 21:42:25 -08:00
Krish Dholakia
bedb08bdef
Merge pull request #1557 from BerriAI/litellm_emit_spend_logs
feat(utils.py): emit response cost as part of logs
2024-01-22 21:02:40 -08:00
Krrish Dholakia
3e8c8ef507 fix(openai.py): fix linting issue 2024-01-22 18:20:15 -08:00
Krrish Dholakia
06f6f128b6 refactor(__init__.py): adds init.py file in tokenizers 2024-01-22 15:33:16 -08:00
Krrish Dholakia
29800d1e01 fix(azure_dall_e_2.py): handle azure not returning a 'retry-after' param 2024-01-22 12:02:02 -08:00
Krrish Dholakia
b07677c6be fix(gemini.py): support streaming 2024-01-19 20:21:34 -08:00
Krrish Dholakia
1ec5083542 fix(anthropic.py): fix pr for anthropic headers 2024-01-19 17:06:24 -08:00
Keegan McCallum
3b719b2afd
Allow overriding headers for anthropic 2024-01-18 20:12:59 -08:00
puffo
becff369dc fix(ollama_chat.py): use tiktoken as backup for prompt token counting 2024-01-18 10:47:24 -06:00
Krrish Dholakia
8e9dc09955 fix(bedrock.py): add support for sts based boto3 initialization
https://github.com/BerriAI/litellm/issues/1476
2024-01-17 12:08:59 -08:00
ishaan-jaff
5a8a5fa0fd (fix) using base_url Azure 2024-01-17 10:12:55 -08:00
ishaan-jaff
7178d01c8f (feat) support base_url with /openai passed for Azure 2024-01-17 10:03:25 -08:00
ishaan-jaff
b95d6ec207 (v0) fixes for Azure GPT Vision enhancements 2024-01-17 09:57:16 -08:00
Krrish Dholakia
7cb49ee509 fix(vertex_ai.py): raise exception if vertex ai missing required dependendencies 2024-01-16 16:23:29 -08:00
ishaan-jaff
0e26ef858b (feat) sagemaker - map status code and message 2024-01-15 21:43:16 -08:00
ishaan-jaff
069d060ec9 (feat) provisioned throughput - bedrock embedding models 2024-01-13 21:07:38 -08:00
ishaan-jaff
5e03c9c637 (feat) bedrock support provisioned throughput 2024-01-13 15:39:54 -08:00
Krish Dholakia
554080804f
Merge pull request #1429 from dleen/data
[bug] unbound variable in bedrock
2024-01-12 22:16:11 +05:30
David Leen
a674de8f36 improve bedrock exception granularity 2024-01-12 16:38:55 +01:00
David Leen
8b021fc4cd [bug] unbound variable in bedrock
note: the code was written as `json.dumps({})` even though it is more verbose in order to facilitate easier refactoring in the future

fixes #1428
2024-01-12 12:33:00 +01:00
Krrish Dholakia
a7f182b8ec fix(azure.py): support health checks to text completion endpoints 2024-01-12 00:13:01 +05:30
ishaan-jaff
a9d812eb8d (fix) bedrock - embedding - support str input 2024-01-11 23:02:12 +05:30
ishaan-jaff
a876748bf5 v0 2024-01-11 22:56:18 +05:30
Krrish Dholakia
ebe752fb61 build(pyproject.toml): drop certifi dependency (unused) 2024-01-10 08:09:03 +05:30
Krrish Dholakia
ed6ae8600f fix(openai.py): fix exception raising logic 2024-01-09 11:58:30 +05:30
Krrish Dholakia
be1e101b5f fix(azure.py,-openai.py): raise the correct exceptions for image generation calls 2024-01-09 11:55:38 +05:30
ishaan-jaff
5f2cbfc711 (feat) litellm.completion - support ollama timeout 2024-01-09 10:34:41 +05:30
Krrish Dholakia
88d498a54a fix(ollama.py): use tiktoken as backup for prompt token counting 2024-01-09 09:47:18 +05:30
Krrish Dholakia
3d0ea08f77 refactor(gemini.py): fix linting issue 2024-01-08 11:43:33 +05:30
Krrish Dholakia
b1fd0a164b fix(huggingface_restapi.py): support timeouts for huggingface + openai text completions
https://github.com/BerriAI/litellm/issues/1334
2024-01-08 11:40:56 +05:30