Commit graph

3617 commits

Author SHA1 Message Date
Ishaan Jaff
db316dd097
Merge pull request #4760 from skucherlapati/bug_4757_add_medlm_to_cost_calc
Add Medlm cost calc
2024-07-17 18:01:03 -07:00
Ishaan Jaff
3110abc832 shorten predibase streaming test 2024-07-17 17:50:42 -07:00
Ishaan Jaff
b94ba48ccc ci/cd run again 2024-07-17 17:43:47 -07:00
Ishaan Jaff
613bbe306f fix triton embedding test 2024-07-17 17:29:22 -07:00
Ishaan Jaff
ee53b9093b
Merge pull request #4758 from BerriAI/litellm_langsmith_async_support
[Feat] Use Async Httpx client for langsmith logging
2024-07-17 16:54:40 -07:00
Ishaan Jaff
a77536b202 test_langsmith_logging_with_streaming_and_metadata 2024-07-17 16:51:26 -07:00
Krish Dholakia
0faa3510a7
Merge pull request #4756 from BerriAI/litellm_fix_async_caching
fix(litellm_logging.py): don't run async caching for sync streaming calls
2024-07-17 16:44:48 -07:00
Ishaan Jaff
bf793598b5
Merge pull request #4757 from BerriAI/litellm_langsmith_log_user_id
[Feat] Proxy + Langsmith - Log user_api_key_user_id, user_api_key_team_alias
2024-07-17 16:40:42 -07:00
Ishaan Jaff
8cb228bf16
Merge pull request #4754 from BerriAI/litellm_fix_langsmith_api_key_logged
[Fix] Langsmith - Don't Log Provider API Keys
2024-07-17 16:40:32 -07:00
Ishaan Jaff
f945e7009b test streaming logs to langsmith 2024-07-17 16:25:32 -07:00
Ishaan Jaff
f21a92cadc test langsmith 2024-07-17 16:08:55 -07:00
Ishaan Jaff
ed533bab34 fix testing langsmith logging 2024-07-17 15:14:57 -07:00
skucherlapati
db3d6925c6 add medlm cost calc 2024-07-17 14:54:54 -07:00
Ishaan Jaff
8955d783d1 test correct fields are logged on langsmith 2024-07-17 11:29:29 -07:00
Krrish Dholakia
d2e64f21f3 fix(litellm_logging.py): fix async caching for sync streaming calls (don't do it)
Checks if call is async before running async caching for streaming call

Fixes https://github.com/BerriAI/litellm/issues/4511#issuecomment-2233211808
2024-07-17 11:15:30 -07:00
Ishaan Jaff
df446c52e4 test api_key not logged on langsmith 2024-07-17 10:56:33 -07:00
Ishaan Jaff
0890299f65 test langmsith logging 2024-07-17 10:08:29 -07:00
Krrish Dholakia
e7f8ee2aba fix(test_key_generate_prisma.py): pass user_api_key_dict to test call 2024-07-17 08:29:21 -07:00
Krish Dholakia
606466d5fc
Merge pull request #4746 from BerriAI/litellm_anthropic_translation
fix(factory.py): use stronger typing for anthropic translation
2024-07-16 22:15:51 -07:00
Ishaan Jaff
3ef8d0c97e test - raise correct Auth exception for anthropic API 2024-07-16 21:43:17 -07:00
davidschuler-8451
9293305895 feat: enables batch embedding support for triton 2024-07-16 21:43:17 -07:00
Ishaan Jaff
6c872fea1d test_custom_api_key_header_name 2024-07-16 21:43:17 -07:00
Krrish Dholakia
9771edb302 fix(factory.py): use stronger typing for anthropic translation
Fixes https://github.com/BerriAI/litellm/issues/4738
2024-07-16 19:58:27 -07:00
Krrish Dholakia
ec03e675c9 fix(proxy/utils.py): fix failure logging for rejected requests. + unit tests 2024-07-16 17:15:20 -07:00
Vinnie Giarrusso
b83f47e941 refactor a bit 2024-07-16 12:19:31 -07:00
Krish Dholakia
0fb88e527c
Merge pull request #4716 from pamelafox/countfuncs
Add token counting for OpenAI tools/tool_choice
2024-07-16 07:21:31 -07:00
Vinnie Giarrusso
6ff863ee00 Add enabled_roles to Guardrails configuration, Update Lakera guardrail moderation hook 2024-07-16 01:52:08 -07:00
Ishaan Jaff
a99cb5deeb run ci/cd again 2024-07-15 22:09:17 -07:00
Krrish Dholakia
a4b0740c4a fix(test_custom_callback_input.py): fix unit test for embedding logging 2024-07-15 21:47:05 -07:00
Ishaan Jaff
2cfafdc7c3 fix test tg - they are a very unstable provider 2024-07-15 21:40:06 -07:00
Krish Dholakia
74e263b8de
Merge pull request #4723 from BerriAI/litellm_add_dynamic_api_base
fix(utils.py): allow passing dynamic api base for openai-compatible endpoints (Fireworks AI, etc.)
2024-07-15 21:35:22 -07:00
Krrish Dholakia
d136f2b8a7 fix(litellm_logging.py): fix circular reference 2024-07-15 21:28:33 -07:00
Krrish Dholakia
155ee7e99c fix(factory.py): allow converting pdf url to base64 2024-07-15 21:11:53 -07:00
Ishaan Jaff
4aa98dcbe9 test_amazing_sync_embedding 2024-07-15 20:53:13 -07:00
Ishaan Jaff
4baa48ba4b fix test_sync_embedding 2024-07-15 20:51:29 -07:00
Krrish Dholakia
a15ba2592a fix(utils.py): allow passing dynamic api base for openai-compatible endpoints 2024-07-15 20:00:44 -07:00
Krrish Dholakia
023f10cf1c fix(vertex_httpx.py): return grounding metadata 2024-07-15 19:43:37 -07:00
Krrish Dholakia
959c627dd3 fix(litellm_logging.py): log response_cost=0 for failed calls
Fixes https://github.com/BerriAI/litellm/issues/4604
2024-07-15 19:25:56 -07:00
Pamela Fox
0c98cc6a86 New line 2024-07-15 11:13:14 -07:00
Pamela Fox
d43dbc756b Count tokens for tools 2024-07-15 11:07:52 -07:00
Krrish Dholakia
82ca7af6df fix(vertex_httpx.py): google search grounding fix 2024-07-14 08:06:17 -07:00
Krish Dholakia
6bf60d773e
Merge pull request #4696 from BerriAI/litellm_guardrail_logging_only
Allow setting `logging_only` in guardrails config
2024-07-13 21:50:43 -07:00
Krish Dholakia
7bc9a189e7
Merge branch 'main' into litellm_add_azure_ai_pricing 2024-07-13 21:50:26 -07:00
Krrish Dholakia
d475311eb3 test(test_presidio_pii_masking.py): fix presidio test 2024-07-13 21:44:22 -07:00
Krrish Dholakia
fde434be66 feat(proxy_server.py): return 'retry-after' param for rate limited requests
Closes https://github.com/BerriAI/litellm/issues/4695
2024-07-13 17:15:20 -07:00
Krrish Dholakia
b1be355d42 build(model_prices_and_context_window.json): add azure ai jamba instruct pricing + token details
Adds jamba instruct, mistral, llama3 pricing + token info for azure_ai
2024-07-13 16:34:31 -07:00
Krish Dholakia
bc58e44d8f
Merge pull request #4701 from BerriAI/litellm_rpm_support_passthrough
Support key-rpm limits on pass-through endpoints
2024-07-13 15:22:29 -07:00
Ishaan Jaff
1206b0b6a9
Merge pull request #4693 from BerriAI/litellm_bad_req_error_mapping
fix -  Raise `BadRequestError` when passing the wrong role
2024-07-13 15:05:54 -07:00
Krrish Dholakia
da4bd47e3e test: test fixes 2024-07-13 15:04:13 -07:00
Krrish Dholakia
77325358b4 fix(pass_through_endpoints.py): fix client init 2024-07-13 14:46:56 -07:00