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
16339 commits 2497 branches 897 tags 550 MiB
Commit graph

3884 commits

Author SHA1 Message Date
Krrish Dholakia
2f773d9cb6 fix(litellm_cost_calc/google.py): support meta llama vertex ai cost tracking 2024-07-25 22:12:07 -07:00
Ishaan Jaff
079a41fbe1
Merge branch 'main' into litellm_proxy_support_all_providers 2024-07-25 20:15:37 -07:00
Krrish Dholakia
826bb125e8 test(test_router.py): handle azure api instability 2024-07-25 19:54:40 -07:00
Krrish Dholakia
a2fd8459fc fix(utils.py): don't raise error on openai content filter during streaming - return as is 
Fixes issue where we would raise an error vs. openai who return the chunk with finish reason as 'content_filter'
 2024-07-25 19:50:52 -07:00
Krrish Dholakia
a190bc750f fix(custom_llm.py): pass input params to custom llm 2024-07-25 19:35:52 -07:00
Krrish Dholakia
3b8f357af4 feat(utils.py): support async streaming for custom llm provider 2024-07-25 19:35:48 -07:00
Krrish Dholakia
8c12f7f820 feat(utils.py): support sync streaming for custom llm provider 2024-07-25 19:35:48 -07:00
Krrish Dholakia
7a5c1e7599 fix(custom_llm.py): support async completion calls 2024-07-25 19:35:48 -07:00
Krrish Dholakia
b9b0612c79 feat(custom_llm.py): initial working commit for writing your own custom LLM handler 
Fixes https://github.com/BerriAI/litellm/issues/4675

 Also Addresses https://github.com/BerriAI/litellm/discussions/4677
 2024-07-25 19:35:48 -07:00
Krrish Dholakia
86973d6aca fix(main.py): fix calling openai gpt-3.5-turbo-instruct via /completions 
Fixes https://github.com/BerriAI/litellm/issues/749
 2024-07-25 19:35:40 -07:00
Krrish Dholakia
11cdb79fc0 test: cleanup testing 2024-07-25 19:35:29 -07:00
Krrish Dholakia
2c71f6dd04 feat(auth_check.py): support using redis cache for team objects 
Allows team update / check logic to work across instances instantly
 2024-07-25 19:35:29 -07:00
Krish Dholakia
c2086300b7
Merge branch 'main' into litellm_redis_team_object 2024-07-25 19:31:52 -07:00
Krrish Dholakia
41abd51240 fix(custom_llm.py): pass input params to custom llm 2024-07-25 19:03:52 -07:00
Ishaan Jaff
9863520376 support using */* 2024-07-25 18:48:56 -07:00
Krrish Dholakia
060249c7e0 feat(utils.py): support async streaming for custom llm provider 2024-07-25 17:11:57 -07:00
Krrish Dholakia
b4e3a77ad0 feat(utils.py): support sync streaming for custom llm provider 2024-07-25 16:47:32 -07:00
Krrish Dholakia
9f97436308 fix(custom_llm.py): support async completion calls 2024-07-25 15:51:39 -07:00
Krrish Dholakia
6bf1b9353b feat(custom_llm.py): initial working commit for writing your own custom LLM handler 
Fixes https://github.com/BerriAI/litellm/issues/4675

 Also Addresses https://github.com/BerriAI/litellm/discussions/4677
 2024-07-25 15:33:05 -07:00
Krrish Dholakia
4e51f712f3 fix(main.py): fix calling openai gpt-3.5-turbo-instruct via /completions 
Fixes https://github.com/BerriAI/litellm/issues/749
 2024-07-25 09:57:19 -07:00
Krrish Dholakia
3cd3491920 test: cleanup testing 2024-07-24 19:47:50 -07:00
Krish Dholakia
e6963217ba
Merge branch 'main' into litellm_parallel_requests 2024-07-24 19:25:56 -07:00
Krrish Dholakia
f35af3bf1c test(test_completion.py): update azure extra headers 2024-07-24 18:42:50 -07:00
Krrish Dholakia
6ab2527fdc feat(auth_check.py): support using redis cache for team objects 
Allows team update / check logic to work across instances instantly
 2024-07-24 18:14:49 -07:00
Ishaan Jaff
53dd47c5cb
Merge pull request #4862 from BerriAI/litellm_fix_unsupported_params_Error 
[Fix-litellm python] Raise correct error for UnsupportedParams Error
 2024-07-24 14:26:25 -07:00
Krrish Dholakia
65705fde25 test(test_embedding.py): add simple azure embedding ad token test 
Addresses https://github.com/BerriAI/litellm/issues/4859#issuecomment-2248838617
 2024-07-24 13:38:03 -07:00
Krrish Dholakia
77ffee4e2e test(test_completion.py): add basic test to confirm azure ad token flow works as expected 2024-07-24 13:07:25 -07:00
Ishaan Jaff
30c27b3f92 test UnsupportedParamsError 2024-07-24 12:21:22 -07:00
Krrish Dholakia
d9539e518e build(docker-compose.yml): add prometheus scraper to docker compose 
persists prometheus data across restarts
 2024-07-24 10:09:23 -07:00
Ishaan Jaff
ac7f6598f3
Merge pull request #4853 from BerriAI/litellm_support_tags 
[Feat] - Support Logging tags on langsmith
 2024-07-24 09:51:56 -07:00
David Manouchehri
ced03d9d7f
(test_embedding.py) - Re-enable embedding test with Azure OIDC. 2024-07-24 16:41:24 +00:00
Krish Dholakia
035d03c7f2
Merge pull request #4856 from msabramo/fix-test_prompt_factory-flake8-warning 
Fix `test_prompt_factory` flake8 warning
 2024-07-24 09:38:48 -07:00
Marc Abramowitz
a50fe3e1ca Fix test_prompt_factory flake8 warning 
```shell
$ poetry run flake8 litellm/tests/test_prompt_factory.py
<unknown>:215: SyntaxWarning: invalid escape sequence '\/'
litellm/tests/test_prompt_factory.py:215:21: W605 invalid escape sequence '\/'
```

Fixed by making the string a raw string, which is equivalent:

```
$ python
Python 3.11.6 (main, Oct 25 2023, 19:49:20) [Clang 14.0.0 (clang-1400.0.29.202)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> "data:image\/jpeg;base64,1234" == r"data:image\/jpeg;base64,1234"
True
```

See: https://stackoverflow.com/questions/52335970/how-to-fix-syntaxwarning-invalid-escape-sequence-in-python
 2024-07-24 09:14:22 -07:00
David Manouchehri
c364a3129e
(test_secret_manager.py) - Improve and add CircleCI v1 test with Amazon. 2024-07-24 16:05:58 +00:00
David Manouchehri
4b89397136
(tests) - Skip embedding Azure AD test for now. 2024-07-24 15:42:57 +00:00
David Manouchehri
af3a900b4d
(tests) - Try azure AD auth directly. 2024-07-24 15:42:40 +00:00
Krrish Dholakia
41fda47587 test(test_embedding.py): fix base url 2024-07-24 08:04:27 -07:00
Ishaan Jaff
cea8fcc3fc test - logging langsmith tags 2024-07-24 07:12:45 -07:00
Krish Dholakia
6c580ac8dc
Merge pull request #4845 from BerriAI/litellm_vertex_ai_llama3_1_api 
feat(vertex_ai_llama.py): vertex ai llama3.1 api support
 2024-07-23 21:51:46 -07:00
Krrish Dholakia
fb0a13c8bb fix(anthropic.py): support openai system message being a list 2024-07-23 21:45:56 -07:00
Krrish Dholakia
7df94100e8 build(model_prices_and_context_window.json): add model pricing for vertex ai llama 3.1 api 2024-07-23 17:36:07 -07:00
Krrish Dholakia
83ef52e180 feat(vertex_ai_llama.py): vertex ai llama3.1 api support 
Initial working commit for vertex ai llama 3.1 api support
 2024-07-23 17:07:30 -07:00
Krish Dholakia
cb4c42e061
Merge pull request #4839 from Manouchehri/azure-oidc-test-1 
Add test for Azure OIDC auth
 2024-07-23 17:01:00 -07:00
Ishaan Jaff
c3d90f9aee test_anthropic_completion_input_translation_with_metadata 2024-07-23 15:23:58 -07:00
David Manouchehri
2dcd9a5567
(test - azure): Add test for Azure OIDC auth. 2024-07-23 19:12:40 +00:00
Krrish Dholakia
f64a3309d1 fix(utils.py): support raw response headers for streaming requests 2024-07-23 11:58:58 -07:00
Krrish Dholakia
dcb974dd1e feat(utils.py): support passing openai response headers to client, if enabled 
Allows openai/openai-compatible provider response headers to be sent to client, if 'return_response_headers' is enabled
 2024-07-23 11:30:52 -07:00
Krrish Dholakia
9d10881f3d test: re-run ci/cd 2024-07-23 07:55:42 -07:00
Krish Dholakia
e770ac48a2
Merge branch 'main' into litellm_braintrust_integration 2024-07-22 22:40:39 -07:00
Krish Dholakia
c4db6aa15e
Merge pull request #4810 from BerriAI/litellm_team_modify_guardrails 
feat(auth_checks.py): Allow admin to disable team from turning on/off guardrails
 2024-07-22 22:32:24 -07:00