phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-28 04:04:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
11735 commits 2497 branches 898 tags 558 MiB
Commit graph

7142 commits

Author SHA1 Message Date
Krish Dholakia
f68eb6f74e
Merge pull request #3704 from BerriAI/litellm_replicate_async_fxi 
fix(replicate.py): move replicate calls to being async
 2024-05-16 17:27:12 -07:00
Krrish Dholakia
709373b15c fix(replicate.py): move replicate calls to being completely async 
Closes https://github.com/BerriAI/litellm/issues/3128
 2024-05-16 17:24:08 -07:00
Ishaan Jaff
bd63af395f ui - new build 2024-05-16 17:08:36 -07:00
Ishaan Jaff
a292583ff1 fix - allow users to opt into specific alert types 2024-05-16 16:52:44 -07:00
Krrish Dholakia
a2a5884df1 fix(utils.py): allow passing in custom pricing to completion_cost as params 2024-05-16 16:24:44 -07:00
Ishaan Jaff
97324800ec
Merge pull request #3694 from BerriAI/litellm_allow_setting_anthropic_beta 
[Feat] Support Anthropic `tools-2024-05-16` - Set Custom Anthropic Custom Headers
 2024-05-16 15:48:26 -07:00
Krrish Dholakia
bc23365acc fix(utils.py): update completion_cost docstring 2024-05-16 15:47:40 -07:00
Krrish Dholakia
ce4dffb7cb fix(utils.py): fix logging level of error message 2024-05-16 15:44:08 -07:00
Krish Dholakia
acf95e978d
Merge pull request #3575 from BerriAI/litellm_end_user_obj 
fix(proxy_server.py): check + get end-user obj even for master key calls
 2024-05-16 15:34:06 -07:00
Krrish Dholakia
48714805bd fix(proxy_server.py): fix code 2024-05-16 15:02:39 -07:00
Ishaan Jaff
e19e475c9f test - setting extra headers for anthropic tool use 2024-05-16 14:41:26 -07:00
Ishaan Jaff
23bcd03904 feat: Anthropic allow users to set anthropic-beta in headers 2024-05-16 14:40:31 -07:00
Ishaan Jaff
1fc9bcb184 feat use OpenAI extra_headers param 2024-05-16 14:38:17 -07:00
Ishaan Jaff
2179598d1d
Merge pull request #3693 from BerriAI/litellm_fix_gemini_responses 
[Fix] AI Studio (Gemini API) returns invalid 1 index instead of 0 when "stream": false
 2024-05-16 14:21:55 -07:00
Krish Dholakia
0a775821db
Merge branch 'main' into litellm_end_user_obj 2024-05-16 14:16:09 -07:00
Krish Dholakia
92729478c3
Merge pull request #3645 from paneru-rajan/issue-3627-timeout-support 
Timeout param: custom_llm_provider needs to be set before setting timeout
 2024-05-16 14:15:34 -07:00
Krrish Dholakia
a7b9a03991 docs(billing.md): add tutorial on billing with litellm + lago to docs 2024-05-16 14:13:39 -07:00
Ishaan Jaff
a2ef089667 fix - choices index for gemini/ provider 2024-05-16 13:52:46 -07:00
Ishaan Jaff
e9358684fb feat add gemini-1.5-flash-latest 2024-05-16 13:48:51 -07:00
Ishaan Jaff
0a816b2c45
Merge pull request #3682 from BerriAI/litellm_token_counter_endpoint 
[Feat] `token_counter` endpoint
 2024-05-16 13:39:23 -07:00
Krrish Dholakia
3acb31fa49 docs(lago.md): add lago usage-based billing quick-start to docs 2024-05-16 13:24:04 -07:00
Ishaan Jaff
4a5e6aa43c test - token count response 2024-05-16 13:20:01 -07:00
Krish Dholakia
d43f75150a
Merge pull request #3685 from BerriAI/litellm_lago_integration 
feat(lago.py): Enable Usage-based billing with lago
 2024-05-16 13:09:48 -07:00
Ishaan Jaff
d16a6c03a2 feat - include model name in cool down alerts 2024-05-16 12:52:15 -07:00
Ishaan Jaff
8c3657bad0
Merge pull request #3686 from msabramo/msabramo/fix-datetime-utcnow-deprecation-warnings 
Fix `datetime.datetime.utcnow` `DeprecationWarning`
 2024-05-16 12:19:06 -07:00
Krish Dholakia
ea976d8c30
Merge pull request #3663 from msabramo/msabramo/allow-non-admins-to-use-openai-routes 
Allow non-admins to use `/engines/{model}/chat/completions`
 2024-05-16 12:17:50 -07:00
Marc Abramowitz
4af6638be6 Fix datetime.datetime.utcnow DeprecationWarning 
Eliminates these warning when running tests:

```
$ cd litellm/tests
pytest test_key_generate_prisma.py -x -vv
...
====================================================================== warnings summary =======================================================================
...
test_key_generate_prisma.py::test_generate_and_call_with_expired_key
test_key_generate_prisma.py::test_key_with_no_permissions
  /Users/abramowi/Code/OpenSource/litellm/litellm/proxy/proxy_server.py:2934: DeprecationWarning: datetime.datetime.utcnow() is deprecated and scheduled for removal in a future version. Use timezone-aware objects to represent datetimes in UTC: datetime.datetime.now(datetime.UTC).
    expires = datetime.utcnow() + timedelta(seconds=duration_s)
...
```
 2024-05-16 11:56:02 -07:00
Marc Abramowitz
4194bafae0 Add nicer test ids when using pytest -v 
Replace:

```
test_key_generate_prisma.py::test_generate_and_call_with_valid_key[api_route0] PASSED
test_key_generate_prisma.py::test_generate_and_call_with_valid_key[api_route10] PASSED
test_key_generate_prisma.py::test_generate_and_call_with_valid_key[api_route11] PASSED
test_key_generate_prisma.py::test_generate_and_call_with_valid_key[api_route12] PASSED
test_key_generate_prisma.py::test_generate_and_call_with_valid_key[api_route13] PASSED
test_key_generate_prisma.py::test_generate_and_call_with_valid_key[api_route14] PASSED
````

with:

```
litellm/tests/test_key_generate_prisma.py::test_generate_and_call_with_valid_key[{'route': 'audio_transcriptions', 'path': '/audio/transcriptions'}] PASSED
litellm/tests/test_key_generate_prisma.py::test_generate_and_call_with_valid_key[{'route': 'audio_transcriptions', 'path': '/v1/audio/transcriptions'}] PASSED
litellm/tests/test_key_generate_prisma.py::test_generate_and_call_with_valid_key[{'route': 'chat_completion', 'path': '/chat/completions'}] PASSED
litellm/tests/test_key_generate_prisma.py::test_generate_and_call_with_valid_key[{'route': 'chat_completion', 'path': '/engines/{model}/chat/completions'}] PASSED
litellm/tests/test_key_generate_prisma.py::test_generate_and_call_with_valid_key[{'route': 'chat_completion', 'path': '/openai/deployments/{model}/chat/completions'}] PASSED
litellm/tests/test_key_generate_prisma.py::test_generate_and_call_with_valid_key[{'route': 'chat_completion', 'path': '/v1/chat/completions'}] PASSED
```
 2024-05-16 11:34:22 -07:00
Ishaan Jaff
22ba5fa186 feat - try using hf tokenizer 2024-05-16 10:59:29 -07:00
Krrish Dholakia
e273e66618 feat(lago.py): adding support for usage-based billing with lago 
Closes https://github.com/BerriAI/litellm/issues/3639
 2024-05-16 10:54:18 -07:00
Marc Abramowitz
cf71857354 Add more routes to test_generate_and_call_with_valid_key 2024-05-16 10:44:36 -07:00
Marc Abramowitz
dc52c83b88 Add more routes to test_generate_and_call_with_valid_key 2024-05-16 10:05:35 -07:00
Marc Abramowitz
c427ea3781 Add "/engines/{model}/chat/completions" to openai_routes 
I don't think that this helps with the issue that I'm seeing, but I
think it might be nice to have this model listed in the openai_routes
list so that it's documented that it's a valid chat_completion route.
 2024-05-16 10:03:23 -07:00
Ishaan Jaff
c646b809a6 fix token counter endpoint 2024-05-16 10:03:21 -07:00
Ishaan Jaff
b790d65d28 fix make token counter a /utils/token_counter 2024-05-16 10:00:34 -07:00
Ishaan Jaff
d42e5fcbd5 working token counter endpoint 2024-05-16 09:58:22 -07:00
Marc Abramowitz
d5b2e8e7e8 Make test_generate_and_call_with_valid_key parametrized 
This allows us to test the same code with different routes.
For example, it lets us test the `/engines/{model}/chat/completions`
route, which https://github.com/BerriAI/litellm/pull/3663 fixes.
 2024-05-16 09:54:10 -07:00
Ishaan Jaff
e50284bc72 dev - token_counter endpoint 2024-05-16 09:47:07 -07:00
Ishaan Jaff
5310706d1d
Merge pull request #3681 from BerriAI/litellm_fix_langfuse_flush_on_shutdown 
[Fix] Flush langfuse logs on proxy shutdown
 2024-05-16 09:45:33 -07:00
Ishaan Jaff
579bc09c37 fix - flush langfuse logs on proxy shutdown 2024-05-16 09:21:48 -07:00
Ishaan Jaff
848561a8a7 fix - router show better client side errors 2024-05-16 09:01:27 -07:00
Marc Abramowitz
b079f4cb79 model_info_v{1,2} (LiteLLM) => model_list (OpenAI) 2024-05-16 07:54:09 -07:00
Krish Dholakia
152946e910
Merge branch 'main' into litellm_end_user_cost_tracking 2024-05-15 22:27:04 -07:00
Krish Dholakia
57d425aed7
Merge pull request #3666 from BerriAI/litellm_jwt_fix 
feat(proxy_server.py): JWT-Auth improvements
 2024-05-15 22:22:44 -07:00
Krrish Dholakia
600b6f7e1d feat(proxy_server.py): support 'user_id_upsert' flag for jwt_auth 2024-05-15 22:19:59 -07:00
Krrish Dholakia
99653d2d3e feat(handle_jwt.py): add support for 'team_id_default 
allows admin to set a default team id for spend-tracking + permissions
 2024-05-15 21:33:35 -07:00
Ishaan Jaff
bb86d2510f (ci/cd) run again 2024-05-15 21:07:55 -07:00
Krrish Dholakia
f48cd87cf3 feat(proxy_server.py): make team_id optional for jwt token auth (only enforced, if set) 
Allows users to use jwt auth for internal chat apps
 2024-05-15 21:05:14 -07:00
Ishaan Jaff
ac71a89b0e ui - new build 2024-05-15 21:04:09 -07:00
Ishaan Jaff
5300a4c9b3 fix model prices 2024-05-15 21:00:56 -07:00