Simon Sanchez Viloria
83a274b54b
(feat) support for async stream to watsonx provider
2024-05-06 17:08:40 +02:00
Simon Sanchez Viloria
62b3f25398
(fix) fix ibm_granite_pt and use hf_chat_template for llama-3 instruct prompts
2024-05-06 17:08:40 +02:00
Ishaan Jaff
e0001a9121
docs - add using vertex embedding models
2024-05-06 07:56:17 -07:00
Ishaan Jaff
c762e60ae5
stash ui changes
2024-05-06 07:53:55 -07:00
Rajan Paneru
2347cb2247
bring back the to be depricated mistral-medium
2024-05-07 00:19:19 +09:30
Krish Dholakia
9f58583888
Merge pull request #3299 from themrzmaster/main
...
Allowing extra headers for bedrock
2024-05-06 07:45:53 -07:00
Krrish Dholakia
b5f3f198f2
fix(utils.py): anthropic error handling
2024-05-06 07:25:12 -07:00
Krrish Dholakia
d83f0b02da
test: fix local tests
2024-05-06 07:14:33 -07:00
Krish Dholakia
5f119f2abb
Merge pull request #3469 from jackmpcollins/fix-ollama-streamed-tool-calls
...
Fix Ollama streamed tool calls. Set finish_reason to tool_calls for all tool_calls responses
2024-05-06 07:13:37 -07:00
Ishaan Jaff
817a77b23f
Merge pull request #3463 from RoniGurvichCycode/main
...
gunicorn version bump
2024-05-06 07:11:01 -07:00
Lucca Zenóbio
b22517845e
Merge branch 'main' into main
2024-05-06 09:40:23 -03:00
Jack Collins
07b13ff7c5
Remove unused ModelResponse import
2024-05-06 00:16:58 -07:00
Jack Collins
51c02fdadf
Add tests for ollama + ollama chat tool calls +/- stream
2024-05-06 00:13:42 -07:00
Rajan Paneru
d0d063e25a
Synced the model with the Mistral
...
* Ordered them based on previous order
* Excluded to be depricated models
* Use the model name, instead of the slug in the first column as referred by the name of the column
2024-05-06 13:16:24 +09:30
Mehmet Bektas
64a64c68c5
update ollama test file
2024-05-05 20:25:43 -07:00
Mehmet Bektas
3acad270e5
support sync ollama embeddings
2024-05-05 19:44:25 -07:00
Jack Collins
bb6132eee1
Fix: get format from data not optional_params ollama non-stream completion
2024-05-05 18:59:26 -07:00
Jack Collins
81b1c46c6f
Add missing import itertools.chain
2024-05-05 18:54:08 -07:00
Jack Collins
03b82b78c1
Fix: Set finish_reason to tool_calls for non-stream responses in ollama
2024-05-05 18:52:31 -07:00
Jack Collins
297543e3e5
Parse streamed function calls as single delta in ollama
2024-05-05 18:52:20 -07:00
Jack Collins
dffe616267
Make newline same in async function
2024-05-05 18:51:53 -07:00
Jack Collins
c217a07d5e
Fix: Set finish_reason to tool_calls for non-stream responses
2024-05-05 18:47:58 -07:00
Jack Collins
107a77368f
Parse streamed function calls as single delta
2024-05-05 18:47:16 -07:00
Alex Epstein
b82162832a
Update support for langfuse metadata
...
- Added ability to set trace release, version, metadata
- Added ability to update fields during a trace continuation
- Added ability to update input and output during a trace continuation
- Wrote new test for verifying metadata is set correctly
- Small improvement to setting secret boolean, prevent unnecessary literal_eval
- Small improvements to langfuse tests
2024-05-05 14:56:36 -04:00
Roni Gurvich
32a085accf
gunicorn update
2024-05-05 13:25:59 +03:00
Krrish Dholakia
918367cc7b
test: skip hanging test
2024-05-05 00:27:38 -07:00
Krrish Dholakia
e95be13f10
fix(router.py): fix router retry policy logic
2024-05-04 23:02:50 -07:00
Krrish Dholakia
0529d7eaa3
bump: version 1.35.38 → 1.36.0
2024-05-04 22:23:20 -07:00
Krish Dholakia
6be20f5fc6
Merge pull request #3455 from BerriAI/litellm_assistants_support
...
feat(openai.py): add support for openai assistants
2024-05-04 22:21:44 -07:00
ffreemt
2713272bba
Add return_exceptions to batch_completion (retry)
2024-05-05 13:11:21 +08:00
Ishaan Jaff
1b9c799a93
ui - show retry on Admin UI
2024-05-04 22:06:43 -07:00
Ishaan Jaff
d4c2eb1797
fix post call rule test
2024-05-04 22:04:53 -07:00
Krrish Dholakia
06ae584473
fix(types/openai.py): fix python3.8 typing issue
2024-05-04 22:04:17 -07:00
Krrish Dholakia
66129bc921
fix(typing/openai.py): fix openai typing error (version-related)
2024-05-04 22:02:43 -07:00
Ishaan Jaff
87bd499d11
add save button on admin ui
2024-05-04 22:00:57 -07:00
Ishaan Jaff
281e92d0a8
ui - show default retries
2024-05-04 21:58:36 -07:00
Krrish Dholakia
2deac08ff1
fix(types/openai.py): fix typing import
2024-05-04 21:53:08 -07:00
Ishaan Jaff
3175be6303
get correct settings on router
2024-05-04 21:51:25 -07:00
Krrish Dholakia
1195bf296b
fix(openai.py): fix typing import for python 3.8
2024-05-04 21:49:30 -07:00
Krrish Dholakia
f2bf6411d8
fix(openai.py): fix linting error
2024-05-04 21:48:42 -07:00
Krish Dholakia
47078f4d84
Merge pull request #3452 from tothandras/fix/openmeter
...
Fix OpenMeter sync logger
2024-05-04 21:41:44 -07:00
Ishaan Jaff
43b50b7151
ui - show retry policy for errors
2024-05-04 21:39:23 -07:00
Ishaan Jaff
4d1806bc95
fix - vertex ai exceptions
2024-05-04 21:32:10 -07:00
Krrish Dholakia
5406205e4b
test(test_assistants.py): cleanup tests
2024-05-04 21:31:07 -07:00
Krrish Dholakia
8fe6c9b401
feat(assistants/main.py): support litellm.get_assistants() and litellm.get_messages()
2024-05-04 21:30:28 -07:00
Ishaan Jaff
e62d8e9bc9
stash ui changes
2024-05-04 21:24:07 -07:00
Krrish Dholakia
cad01fb586
feat(assistants/main.py): support 'litellm.get_threads'
2024-05-04 21:14:03 -07:00
Ishaan Jaff
157b2b3a06
fix python 3.8 install
2024-05-04 21:00:39 -07:00
Ishaan Jaff
c1a215b955
fix set router retry policy on ui
2024-05-04 21:00:03 -07:00
Ishaan Jaff
4dcb4b81f1
fix - python 3.8 error
2024-05-04 20:44:40 -07:00
