phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
16623 commits 2497 branches 897 tags 550 MiB
Commit graph

16623 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ishaan Jaff
b93152e978 assume index is not always in stream chunk 2024-08-15 19:42:03 -07:00
Ishaan Jaff
fa569aaf6f feat add support for aws_region_name 2024-08-15 19:32:59 -07:00
Ishaan Jaff
b4ba12e22c show bedrock, sagemaker creds in verbose mode 2024-08-15 19:10:11 -07:00
Ishaan Jaff
b96a27b230 add verbose logging on test 2024-08-15 19:05:23 -07:00
Ishaan Jaff
40dc27e72c fix sagemaker tests 2024-08-15 18:34:20 -07:00
Ishaan Jaff
0d374fb7c0 fix sagemaker test 2024-08-15 18:23:41 -07:00
Ishaan Jaff
df4ea8fba6 refactor sagemaker to be async 2024-08-15 18:18:02 -07:00
Krrish Dholakia
28d7de30de fix(litellm_logging.py): wrap function to safely fail 2024-08-15 18:05:06 -07:00
Krrish Dholakia
f6dba82882 feat(litellm_logging.py): cleanup payload + add response cost to logged payload 2024-08-15 17:53:25 -07:00
Krrish Dholakia
3ddeb3297d fix(litellm_logging.py): fix standard payload 2024-08-15 17:33:40 -07:00
Krrish Dholakia
cda50e5d47 fix(s3.py): fix s3 logging payload to have valid json values 
Previously pydantic objects were being stringified, making them unparsable
 2024-08-15 17:09:02 -07:00
Ishaan Jaff
e4638ee4e4
Merge pull request #5233 from BerriAI/litellm_make_sagemaker_async 
[Fix] use BaseAWSLLM for bedrock, sagemaker
 2024-08-15 15:13:29 -07:00
Ishaan Jaff
b1aed699ea test sync sagemaker calls 2024-08-15 15:12:31 -07:00
Ishaan Jaff
2c9e3e9bd7 run mock tests for test_completion_sagemaker 2024-08-15 14:49:21 -07:00
Ishaan Jaff
b58c2bef1c add non-stream mock tests for sagemaker 2024-08-15 14:48:24 -07:00
Ishaan Jaff
c32cb365d0
Merge pull request #5226 from BerriAI/litellm_always_log_cache_key 
[Fix-Proxy + Langfuse] Always log cache_key on hits/misses
 2024-08-15 14:01:15 -07:00
Ishaan Jaff
e217eda303 use BaseAWSLLM for bedrock getcredentials 2024-08-15 13:58:47 -07:00
Ishaan Jaff
5c1c9f7616 fix ImportError 2024-08-15 13:02:44 -07:00
Paul Lang
97fce022e4 Fixes the tool_use chunk mapping 2024-08-15 15:44:09 -04:00
Ishaan Jaff
5f693971f7 fix - don't require boto3 on the cli 2024-08-15 12:36:38 -07:00
Ishaan Jaff
08922041da
Merge pull request #5224 from BerriAI/litellm_use_common_helper_llm_call 
[Feat-Proxy] - user common helper to `route_request` for making llm call
 2024-08-15 11:49:29 -07:00
Ishaan Jaff
a59ed00fd3 litellm always log cache_key on hits/misses 2024-08-15 09:59:58 -07:00
Ishaan Jaff
7a17b2132f fix /moderations endpoint 2024-08-15 08:58:28 -07:00
Ishaan Jaff
c50a60004f fix test proxy exception mapping 2024-08-15 08:52:28 -07:00
Ishaan Jaff
58828403ea refactor use 1 util for llm routing 2024-08-15 08:42:20 -07:00
Ishaan Jaff
d50f26d73d simplify logic for routing llm request 2024-08-15 08:29:28 -07:00
Ishaan Jaff
fdd6664420 use route_request for making llm call 2024-08-15 08:16:44 -07:00
Kyrylo Yefimenko
e3cd8e169b Use sepecific llama2 and llama3 model names in Ollama 2024-08-15 12:27:51 +01:00
lidongming
e1f53fcc80 Fix incorrect message length check in cost calculator 2024-08-15 16:59:38 +08:00
Krrish Dholakia
eb6a0a32f1 docs(bedrock.md): add guardrails on config.yaml to docs 2024-08-14 22:11:19 -07:00
Krrish Dholakia
c7fd626805 docs(team_logging.md): add key-based logging to docs 2024-08-14 21:49:55 -07:00
Krrish Dholakia
3487d84fcc docs(pass_through.md): add doc on using langfuse client sdk w/ litellm proxy 2024-08-14 21:43:31 -07:00
Krrish Dholakia
28faafadb1 feat(pass_through_endpoints.py): initial commit of crud endpoints for pass through endpoints 2024-08-14 21:36:07 -07:00
Krrish Dholakia
a020563149 feat(proxy_server.py): support returning available fields for pass_through_endpoints via `/config/field/list 2024-08-14 19:07:10 -07:00
Ishaan Jaff
d8ef882905 fix langfuse log_provider_specific_information_as_span 2024-08-14 17:54:18 -07:00
Krish Dholakia
970892fea7
Merge pull request #5209 from BerriAI/litellm_azure_ai_openai_support 
fix(utils.py): support calling openai models via `azure_ai/`
 2024-08-14 17:53:33 -07:00
Krish Dholakia
435d39bb24
Merge branch 'main' into litellm_azure_ai_openai_support 2024-08-14 17:53:27 -07:00
Ishaan Jaff
9c039a9064 bump: version 1.43.12 → 1.43.13 2024-08-14 17:47:20 -07:00
Ishaan Jaff
1f631606a5
Merge pull request #5210 from BerriAI/litellm_add_prompt_caching_support 
[Feat] Add Anthropic API Prompt Caching Support
 2024-08-14 17:43:01 -07:00
Ishaan Jaff
912acb1cae docs using proxy with context caaching anthropic 2024-08-14 17:42:48 -07:00
Krish Dholakia
c5647ac596
Merge pull request #5211 from msabramo/use-AZURE_API_VERSION-as-default-azure-openai-version 
Use `AZURE_API_VERSION` env var as default azure openai version
 2024-08-14 17:37:55 -07:00
Ishaan Jaff
2267b8a59f docs add examples with litellm proxy 2024-08-14 17:13:26 -07:00
Ishaan Jaff
fd122aa7a3 docs add examples doing context caching anthropic sdk 2024-08-14 17:07:51 -07:00
Ishaan Jaff
78a2013e51 add test for large context in system message for anthropic 2024-08-14 17:03:10 -07:00
Ishaan Jaff
76a5f5d433 move claude prompt caching to diff file 2024-08-14 16:28:12 -07:00
Ishaan Jaff
e0ff4823d0 add test for caching tool calls 2024-08-14 16:19:14 -07:00
Marc Abramowitz
ac9aa1ab67 Use AZURE_API_VERSION as default azure openai version 
Without this change, the default version of the Azure OpenAI API is hardcoded in
the code as an old version, `"2024-02-01"`. This change allows the user to set
the default version of the Azure OpenAI API by setting the environment variable
`AZURE_API_VERSION` or by using the command-line parameter `--api_version`.
 2024-08-14 15:47:57 -07:00
Krrish Dholakia
6333b04be3 fix(factory.py): handle assistant null content 2024-08-14 15:44:38 -07:00
Ishaan Jaff
fccc6dc928 fix bedrock test 2024-08-14 15:27:20 -07:00
Ishaan Jaff
45e367d4d4 docs Caching - Continuing Multi-Turn Convo 2024-08-14 15:26:25 -07:00