Krrish Dholakia
|
a8e181369d
|
fix(cohere.py): fix message parsing to handle tool calling correctly
|
2024-07-04 11:13:07 -07:00 |
|
Krrish Dholakia
|
d4577fe476
|
fix(factory.py): fix linting
|
2024-07-04 08:21:19 -07:00 |
|
Krish Dholakia
|
3184640291
|
Merge pull request #4522 from andrewmjc/matchingToolMessageSpec
[Bug Fix] Use OpenAI Tool Response Spec When Converting To Gemini/VertexAI Tool Response
|
2024-07-04 08:03:38 -07:00 |
|
Simon Sanchez Viloria
|
e4014d3e0e
|
fix linting error
|
2024-07-04 14:26:17 +02:00 |
|
Simon Sanchez Viloria
|
574de1d7fd
|
(fix) fixed watsonx embedding returning a coroutine
|
2024-07-04 14:12:14 +02:00 |
|
Krrish Dholakia
|
19c982d0f9
|
fix: linting fixes
|
2024-07-03 21:55:00 -07:00 |
|
Krish Dholakia
|
5e47970eed
|
Merge branch 'main' into litellm_anthropic_tool_calling_streaming_fix
|
2024-07-03 20:43:51 -07:00 |
|
Krrish Dholakia
|
2e5a81f280
|
fix(utils.py): stream_options working across all providers
|
2024-07-03 20:40:46 -07:00 |
|
Krrish Dholakia
|
344268e053
|
fix(anthropic.py): support *real* anthropic tool calling + streaming
Parses each chunk and translates to openai format
|
2024-07-03 19:48:35 -07:00 |
|
Krish Dholakia
|
1078c0f77a
|
Merge pull request #4533 from UsableMachines/nick/fix-granite-prompt-template
Fix Granite Prompt template
|
2024-07-03 18:45:25 -07:00 |
|
Krrish Dholakia
|
ed5fc3d1f9
|
fix(utils.py): fix vertex anthropic streaming
|
2024-07-03 18:43:46 -07:00 |
|
Krish Dholakia
|
6c5c8bbb28
|
Revert "fix(vertex_anthropic.py): Vertex Anthropic tool calling - native params "
|
2024-07-03 17:55:37 -07:00 |
|
nick-rackauckas
|
ce595027ad
|
Fix LiteLlm Granite Prompt template
|
2024-07-03 17:52:28 -07:00 |
|
Krish Dholakia
|
318077edea
|
Merge pull request #4531 from BerriAI/litellm_vertex_anthropic_tools
fix(vertex_anthropic.py): Vertex Anthropic tool calling - native params
|
2024-07-03 17:25:32 -07:00 |
|
Krrish Dholakia
|
7007ace6c2
|
fix(vertex_anthropic.py): Updates the vertex anthropic endpoint to do tool calling with the anthropic api params
|
2024-07-03 15:28:31 -07:00 |
|
Krish Dholakia
|
944f22a089
|
Merge pull request #4499 from petermuller/main
Allow calling SageMaker endpoints from different regions
|
2024-07-03 13:09:21 -07:00 |
|
andrewmjc
|
95dc480204
|
unit test
|
2024-07-03 12:23:26 -06:00 |
|
Krrish Dholakia
|
d18dc2648c
|
fix(replicate.py): correctly handly invalid replicate response
|
2024-07-03 10:09:46 -07:00 |
|
Krish Dholakia
|
2116dbcdc1
|
Merge pull request #4089 from paneru-rajan/ollama-func-calls
Fix: Output Structure of Ollama chat
|
2024-07-03 08:57:31 -07:00 |
|
Peter Muller
|
d8fc8252fa
|
Revert imports changes, update tests to match
|
2024-07-02 19:09:22 -07:00 |
|
Krrish Dholakia
|
ac00639301
|
fix(azure.py): fix httpx call for dall e 3
|
2024-07-02 18:30:21 -07:00 |
|
Krrish Dholakia
|
0647278a69
|
refactor: remove custom transport logic
Not needed after azure dall-e-2 refactor
|
2024-07-02 17:35:27 -07:00 |
|
Krrish Dholakia
|
cf5334fe8a
|
refactor(azure.py): refactor sync azure calls to httpx
|
2024-07-02 17:06:48 -07:00 |
|
andrewmjc
|
e07b110b47
|
matching openai tool result spec
|
2024-07-02 16:57:13 -06:00 |
|
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 |
|
Krish Dholakia
|
612af8f5be
|
Merge pull request #4492 from Manouchehri/gemini-context-caching-1
feat(vertex_httpx.py): Support cachedContent.
|
2024-07-02 14:09:25 -07:00 |
|
Tiger Yu
|
26630cd263
|
Merge branch 'main' into litellm-fix-vertexaibeta
|
2024-07-02 09:49:44 -07:00 |
|
Ishaan Jaff
|
4033302656
|
feat - return headers for openai audio transcriptions
|
2024-07-01 20:27:27 -07:00 |
|
Ishaan Jaff
|
568245b5c0
|
feat - set response headers in azure requests
|
2024-07-01 20:12:39 -07:00 |
|
Ishaan Jaff
|
04a975d486
|
feat - add response_headers in litellm_logging_obj
|
2024-07-01 17:25:15 -07:00 |
|
Ishaan Jaff
|
140f7fe254
|
return azure response headers
|
2024-07-01 17:09:06 -07:00 |
|
Ishaan Jaff
|
4b7feb3261
|
feat - return response headers for async openai requests
|
2024-07-01 17:01:42 -07:00 |
|
Peter Muller
|
c6be8326db
|
Allow calling SageMaker endpoints from different regions
|
2024-07-01 16:00:42 -07:00 |
|
David Manouchehri
|
5572494801
|
feat(vertex_httpx.py): Support cachedContent.
|
2024-07-01 16:59:35 +00:00 |
|
David Manouchehri
|
9a74364baa
|
fix(bedrock_httpx.py): Add anthropic.claude-3-5-sonnet-20240620-v1:0 to the converse list.
|
2024-07-01 14:18:23 +00:00 |
|
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 |
|
Krrish Dholakia
|
824e0c5e39
|
build(pyproject.toml): remove ijson dep. add jsonschema dep.
|
2024-06-29 19:58:01 -07:00 |
|
Ishaan Jaff
|
46698ae01f
|
fix param mapping for bedrock claude
|
2024-06-29 19:33:51 -07:00 |
|
Krrish Dholakia
|
dc0218d34c
|
build(pyproject.toml): remove ijson dep. add jsonschema dep.
|
2024-06-29 19:24:00 -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
|
f9ba3cf668
|
fix bedrock claude test
|
2024-06-29 18:46:06 -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
|
8a4cffa06e
|
fix _api_version check on CustomHttpTransport
|
2024-06-29 17:25:41 -07:00 |
|
Brian Schultheiss
|
632b7ce17d
|
Resolve merge conflicts
|
2024-06-29 15:53:02 -07:00 |
|
Ishaan Jaff
|
457689c31a
|
fix image gen connection error
|
2024-06-29 15:51:28 -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 |
|
Krrish Dholakia
|
e73e9e12bc
|
fix(vertex_httpx.py): support passing response_schema to gemini
|
2024-06-29 11:33:19 -07:00 |
|
Krrish Dholakia
|
4f32f283a3
|
fix(vertex_httpx.py): fix streaming for cloudflare proxy calls
|
2024-06-29 09:09:56 -07:00 |
|