phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
17692 commits 2484 branches 894 tags 537 MiB
Commit graph

29 commits

Author SHA1 Message Date
Ishaan Jaff
85acdb9193
[Feat] Add max_completion_tokens param (#5691) 
* add max_completion_tokens

* add max_completion_tokens

* add max_completion_tokens support for OpenAI models

* add max_completion_tokens param

* add max_completion_tokens for bedrock converse models

* add test for converse maxTokens

* fix openai o1 param mapping test

* move test optional params

* add max_completion_tokens for anthropic api

* fix conftest

* add max_completion tokens for vertex ai partner models

* add max_completion_tokens for fireworks ai

* add max_completion_tokens for hf rest api

* add test for param mapping

* add param mapping for vertex, gemini + testing

* predibase is the most unstable and unusable llm api in prod, can't handle our ci/cd

* add max_completion_tokens to openai supported params

* fix fireworks ai param mapping
 2024-09-14 14:57:01 -07:00
Krish Dholakia
60709a0753
LiteLLM Minor Fixes and Improvements (09/13/2024) (#5689) 
* refactor: cleanup unused variables + fix pyright errors

* feat(health_check.py): Closes https://github.com/BerriAI/litellm/issues/5686

* fix(o1_reasoning.py): add stricter check for o-1 reasoning model

* refactor(mistral/): make it easier to see mistral transformation logic

* fix(openai.py): fix openai o-1 model param mapping

Fixes https://github.com/BerriAI/litellm/issues/5685

* feat(main.py): infer finetuned gemini model from base model

Fixes https://github.com/BerriAI/litellm/issues/5678

* docs(vertex.md): update docs to call finetuned gemini models

* feat(proxy_server.py): allow admin to hide proxy model aliases

Closes https://github.com/BerriAI/litellm/issues/5692

* docs(load_balancing.md): add docs on hiding alias models from proxy config

* fix(base.py): don't raise notimplemented error

* fix(user_api_key_auth.py): fix model max budget check

* fix(router.py): fix elif

* fix(user_api_key_auth.py): don't set team_id to empty str

* fix(team_endpoints.py): fix response type

* test(test_completion.py): handle predibase error

* test(test_proxy_server.py): fix test

* fix(o1_transformation.py): fix max_completion_token mapping

* test(test_image_generation.py): mark flaky test
 2024-09-14 10:02:55 -07:00
Krish Dholakia
f9e6507cd1
LiteLLM Minor Fixes + Improvements (#5474) 
* feat(proxy/_types.py): add lago billing to callbacks ui

Closes https://github.com/BerriAI/litellm/issues/5472

* fix(anthropic.py): return anthropic prompt caching information

Fixes https://github.com/BerriAI/litellm/issues/5364

* feat(bedrock/chat.py): support 'json_schema' for bedrock models

Closes https://github.com/BerriAI/litellm/issues/5434

* fix(bedrock/embed/embeddings.py): support async embeddings for amazon titan models

* fix: linting fixes

* fix: handle key errors

* fix(bedrock/chat.py): fix bedrock ai21 streaming object

* feat(bedrock/embed): support bedrock embedding optional params

* fix(databricks.py): fix usage chunk

* fix(internal_user_endpoints.py): apply internal user defaults, if user role updated

Fixes issue where user update wouldn't apply defaults

* feat(slack_alerting.py): provide multiple slack channels for a given alert type

multiple channels might be interested in receiving an alert for a given type

* docs(alerting.md): add multiple channel alerting to docs
 2024-09-02 14:29:57 -07:00
Krish Dholakia
9c8f1d7815
anthropic prompt caching cost tracking (#5453) 
* fix(utils.py): support 'drop_params' for embedding requests

Fixes https://github.com/BerriAI/litellm/issues/5444

* feat(anthropic/cost_calculation.py): Support calculating cost for prompt caching on anthropic

* feat(types/utils.py): allows us to migrate to openai's equivalent, once that comes out

* fix: fix linting errors

* test: mark flaky test
 2024-08-31 14:09:35 -07:00
Krrish Dholakia
3007f0344d fix(utils.py): only filter additional properties if gemini/vertex ai 2024-08-23 14:22:59 -07:00
Krrish Dholakia
93ed8c7216 fix(utils.py): handle additionalProperties is False for vertex ai / gemini calls 
Fixes https://github.com/BerriAI/litellm/issues/5338

Also adds together ai json mode support
 2024-08-23 09:21:32 -07:00
Krrish Dholakia
3c99ad19fa feat(utils.py): support global vertex ai safety settings param 2024-08-21 17:37:50 -07:00
Krrish Dholakia
a4f9ba4a88 fix(azure.py): fix optional param elif statement 2024-08-20 12:24:51 -07:00
Krrish Dholakia
dd3d97ace6 test(test_optional_params.py): use num_retries instead of 'max_retries' if given 2024-08-09 17:02:29 -07:00
Krrish Dholakia
51ccfa9e77 fix(huggingface_restapi.py): fixes issue where 'wait_for_model' was not being passed as expected 2024-08-09 08:36:35 -07:00
Ishaan Jaff
4e90a25417 fix all optional param tests 2024-08-07 17:52:40 -07:00
Ishaan Jaff
341e098c32 fix test_drop_params_parallel_tool_calls 2024-08-07 16:26:56 -07:00
Krrish Dholakia
ed8b20fa18 fix(utils.py): parse out aws specific params from openai call 
Fixes https://github.com/BerriAI/litellm/issues/5009
 2024-08-03 12:04:44 -07:00
Krrish Dholakia
5b71421a7b feat(vertex_ai_partner.py): initial working commit for calling vertex ai mistral 
Closes https://github.com/BerriAI/litellm/issues/4874
 2024-07-27 12:54:14 -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
bb905d7243 fix(utils.py): support 'drop_params' for 'parallel_tool_calls' 
Closes https://github.com/BerriAI/litellm/issues/4584

 OpenAI-only param
 2024-07-08 07:36:41 -07:00
Krrish Dholakia
16941eee43 fix(utils.py): re-integrate separate gemini optional param mapping (google ai studio) 
Fixes https://github.com/BerriAI/litellm/issues/4333
 2024-06-21 09:01:32 -07:00
Krrish Dholakia
a0f08e0dad fix(utils.py): allow dropping specific openai params 2024-06-20 11:48:06 -07:00
Krrish Dholakia
162f9400d2 feat(utils.py): support dynamically setting 'drop_params' 
Allows user to turn this on/off for individual calls by passing in as a completion arg
 2024-06-05 08:44:04 -07:00
Krrish Dholakia
7efac4d36c fix(azure.py): support dropping 'tool_choice=required' for older azure API versions 
Closes https://github.com/BerriAI/litellm/issues/3876
 2024-06-01 18:44:50 -07:00
Krrish Dholakia
3d32b00821 fix(openai.py): only allow 'user' as optional param if openai model 2024-05-29 15:15:02 -07:00
Krrish Dholakia
43353c28b3 feat(databricks.py): add embedding model support 2024-05-23 18:22:03 -07:00
Krrish Dholakia
50be25d11a test(test_optional_params.py): fix optional params 2024-05-10 14:08:47 -07:00
Krrish Dholakia
8249c986bf fix(main.py): support new 'supports_system_message=False' param 
Fixes https://github.com/BerriAI/litellm/issues/3325
 2024-05-03 21:31:45 -07:00
Krrish Dholakia
097714e02f fix(anthropic.py): handle whitespace characters for anthropic calls 2024-05-03 17:31:34 -07:00
ishaan-jaff
3c8b58bd80 (feat) support extra_headers 2024-02-23 08:48:21 -08:00
ishaan-jaff
fffb077cf6 (test) get optional_params Azure 2024-01-13 14:32:41 -08:00
Krrish Dholakia
4905929de3 refactor: add black formatting 2023-12-25 14:11:20 +05:30
Krrish Dholakia
51d62189f1 test(test_optional_params.py): unit tests for get_optional_params_embeddings() 2023-12-14 14:32:36 -08:00