Commit graph

3588 commits

Author SHA1 Message Date
Krrish Dholakia
cf5334fe8a refactor(azure.py): refactor sync azure calls to httpx 2024-07-02 17:06:48 -07:00
Peter Muller
47c97e1fa2
Fix test name typo in comment 2024-07-02 15:38:15 -07:00
Krrish Dholakia
589c1c6280 refactor(azure.py): replaces the custom transport logic for just using our httpx client
Done to fix all the http/https proxy issues people are facing with proxy.
2024-07-02 15:32:53 -07:00
Peter Muller
d9e9a8645b
Add tests for SageMaker region selection 2024-07-02 15:30:39 -07:00
Krrish Dholakia
79670ab82e fix(main.py): get the region name from boto3 client if dynamic var not set 2024-07-02 09:24:07 -07:00
Krrish Dholakia
6b529d4e0e fix(dynamic_rate_limiter.py): support setting priority + reserving tpm/rpm 2024-07-01 23:08:54 -07:00
Ishaan Jaff
e2a2c2bde1 ci/cd run again 2024-07-01 21:36:30 -07:00
Ishaan Jaff
665d8fb250 test - test_azure_embedding_exceptions 2024-07-01 21:19:47 -07:00
Krrish Dholakia
460c33f70f test(test_dynamic_rate_limit_handler.py): add unit tests for dynamic rpm limits 2024-07-01 20:20:24 -07:00
Krrish Dholakia
0781014706 test(test_dynamic_rate_limit_handler.py): refactor tests for rpm suppprt 2024-07-01 20:16:10 -07:00
Ishaan Jaff
8b1b79e15b ci/cd run again 2024-06-29 20:56:29 -07:00
Ishaan Jaff
d25b079caf fix img gen test 2024-06-29 20:54:22 -07:00
Krish Dholakia
06eb361820
Merge branch 'main' into litellm_vertex_anthropic_json_mode 2024-06-29 20:18:41 -07:00
Krish Dholakia
58d0330cd7
Merge pull request #4478 from BerriAI/litellm_support_response_schema_param_vertex_ai_old
feat(vertex_httpx.py): support the 'response_schema' param for older vertex ai models
2024-06-29 20:17:39 -07:00
Ishaan Jaff
eac42bb473 ci/cd run again 2024-06-29 20:13:32 -07:00
Krrish Dholakia
2ab6f2be63 style: trigger new build 2024-06-29 19:58:02 -07:00
Krrish Dholakia
5df940c54d test(test_amazing_vertex_completion.py): reduce vertex tests - quota exhaustion 2024-06-29 19:58:01 -07:00
Krrish Dholakia
3f9859e638 fix(utils.py): add 'enforce_validation' param 2024-06-29 19:57:41 -07:00
Ishaan Jaff
03dbc29c85 fix test_completion_replicate_llama3_streaming 2024-06-29 19:51:07 -07:00
Ishaan Jaff
bad49a270d fix test test_provisioned_throughput 2024-06-29 19:41:05 -07:00
Krrish Dholakia
25b1463920 style: trigger new build 2024-06-29 19:26:21 -07:00
Krrish Dholakia
b78043f904 test(test_amazing_vertex_completion.py): reduce vertex tests - quota exhaustion 2024-06-29 19:14:19 -07:00
Krrish Dholakia
7670c5bd13 fix(utils.py): add 'enforce_validation' param 2024-06-29 19:12:00 -07:00
Krrish Dholakia
4b1e85f54e fix(vertex_ai_anthropic.py): support pre-filling "{" for json mode 2024-06-29 18:54:10 -07:00
Ishaan Jaff
588f0e50d2 ci/cd run again 2024-06-29 18:48:13 -07:00
Ishaan Jaff
c6fda7fb7e
Merge pull request #4480 from BerriAI/litellm_fix_image_gen_issue
[Fix] DALL-E connection error bug on litellm proxy
2024-06-29 17:45:57 -07:00
Ishaan Jaff
19014dd931
Merge pull request #4477 from BerriAI/litellm_fix_exception_mapping
[Fix]  - Error str in OpenAI, Azure exception
2024-06-29 17:37:26 -07:00
Ishaan Jaff
0bda80ddea test- router when using openai prefix 2024-06-29 17:28:08 -07:00
Brian Schultheiss
632b7ce17d Resolve merge conflicts 2024-06-29 15:53:02 -07:00
Krrish Dholakia
b699d9a8b9 fix(utils.py): support json schema validation 2024-06-29 15:05:52 -07:00
Ishaan Jaff
2f741bdcff test - correct error str on exceptions 2024-06-29 13:29:28 -07:00
Krrish Dholakia
05dfc63b88 feat(vertex_httpx.py): support the 'response_schema' param for older vertex ai models - pass as prompt (user-controlled)
if 'response_schema' is not supported for vertex model (e.g. gemini-1.5-flash) pass in prompt
2024-06-29 13:25:27 -07:00
Ishaan Jaff
d131380563 fix test router debug logs 2024-06-29 13:24:57 -07:00
Krish Dholakia
6271e21bcb
Merge pull request #4476 from BerriAI/litellm_support_response_schema
fix(utils.py): new `supports_response_schema()` function to check if provider/model supports the param
2024-06-29 13:21:13 -07:00
Krrish Dholakia
5718d1e205 fix(utils.py): new helper function to check if provider/model supports 'response_schema' param 2024-06-29 12:40:29 -07:00
Ishaan Jaff
f06feca377
Merge pull request #4470 from BerriAI/litellm_test_pass_through_endpoints
tests - pass through endpoint
2024-06-29 12:02:05 -07:00
Krrish Dholakia
e73e9e12bc fix(vertex_httpx.py): support passing response_schema to gemini 2024-06-29 11:33:19 -07:00
Ishaan Jaff
f860cbca34 test test_pass_through_endpoint_rerank 2024-06-29 10:49:10 -07:00
Ishaan Jaff
d085ce2d97 test - pass through endpoint 2024-06-29 09:36:51 -07:00
Krrish Dholakia
4f32f283a3 fix(vertex_httpx.py): fix streaming for cloudflare proxy calls 2024-06-29 09:09:56 -07:00
Krrish Dholakia
831745e710 test(test_streaming.py): try-except replicate api instability 2024-06-28 22:19:44 -07:00
Krrish Dholakia
c9a424d28d fix(router.py): fix get_router_model_info for azure models 2024-06-28 22:13:29 -07:00
Krrish Dholakia
ca04244a0a fix(utils.py): correctly raise openrouter error 2024-06-28 21:50:21 -07:00
Ishaan Jaff
1ee18ce671 ci/cd run again 2024-06-28 18:05:03 -07:00
Ishaan Jaff
0223e52b21 test - lakera ai detection 2024-06-28 16:14:26 -07:00
Krrish Dholakia
0001683036 fix(cost_calculator.py): handle unexpected error in cost_calculator.py 2024-06-28 14:53:00 -07:00
Krrish Dholakia
aa6f7665c4 fix(router.py): only return 'max_tokens', 'input_cost_per_token', etc. in 'get_router_model_info' if base_model is set 2024-06-28 10:45:31 -07:00
Krrish Dholakia
a7122f91a1 fix(support-'alt=sse'-param): Fixes https://github.com/BerriAI/litellm/issues/4459 2024-06-28 10:40:47 -07:00
Krish Dholakia
7b54c9d5bc
Merge pull request #4446 from BerriAI/litellm_get_max_modified_tokens
fix(token_counter.py): New `get_modified_max_tokens' helper func
2024-06-27 21:43:23 -07:00
Krish Dholakia
1223b2b111
Merge pull request #4449 from BerriAI/litellm_azure_tts
feat(azure.py): azure tts support
2024-06-27 21:33:38 -07:00