Ishaan Jaff
3dbb547af0
catch gemini 429 errors
2024-04-05 14:02:01 -07:00
Ishaan Jaff
34a9b8648d
fix gemini rate limit errors
2024-04-05 14:01:32 -07:00
Krish Dholakia
762f68db85
Merge pull request #2859 from cheahjs/feat/vertex-gemini-experimental
...
feat: add gemini-experimental to vertex ai
2024-04-05 13:55:50 -07:00
Krrish Dholakia
834f363b6a
docs(vertex.md): add safety settings tutorial to docs
2024-04-05 13:55:05 -07:00
Ishaan Jaff
22ac95b834
docs azure_ai command r
2024-04-05 13:50:56 -07:00
Krrish Dholakia
645fd62c15
refactor(main.py): trigger new build
2024-04-05 13:42:56 -07:00
Krrish Dholakia
f662dac5c9
fix(vertex_ai_anthropic.py): fix import
2024-04-05 13:38:05 -07:00
Ishaan Jaff
3b2c34d587
ci/cd - skip 429 errors from google gemini
2024-04-05 13:36:29 -07:00
Krrish Dholakia
8f45f5afe9
bump: version 1.34.27 → 1.34.28
2024-04-05 12:50:40 -07:00
Krrish Dholakia
591bd9fcdd
test(test_openai_endpoints.py): add response header test - make sure it's always <4kb
2024-04-05 12:49:29 -07:00
Krrish Dholakia
7949f4849e
fix(proxy_server.py): remove original response from headers - causing nginx to fail
...
response headers > 4kb cause nginx to fail
2024-04-05 12:36:14 -07:00
Krrish Dholakia
695eb129ad
fix(router.py): fix client init for streaming timeouts
2024-04-05 12:30:15 -07:00
Jun Siang Cheah
2b326ce6fd
feat: add gemini-experimental to vertex ai
2024-04-05 18:44:05 +01:00
Ishaan Jaff
6b9c04618e
fix use azure_ai/mistral
2024-04-05 10:07:43 -07:00
Zihao Li
f16d0c06fd
Add backward compatibility to support xml tool use for bedrock and vertex
2024-04-06 00:34:33 +08:00
Ishaan Jaff
5ce80d82d3
fix support azure/mistral models
2024-04-05 09:32:39 -07:00
Krrish Dholakia
f0c4ff6e60
fix(vertex_ai_anthropic.py): support streaming, async completion, async streaming for vertex ai anthropic
2024-04-05 09:27:48 -07:00
Ishaan Jaff
ab60d7c8fb
docs azure ai command-r plust
2024-04-05 09:24:27 -07:00
Ishaan Jaff
cfe358abaa
simplify calling azure/commmand-r-plus
2024-04-05 09:18:11 -07:00
Ishaan Jaff
1ba1c84d83
skip vertex test for this PR
2024-04-05 09:06:15 -07:00
Ishaan Jaff
b25db0443a
docs - using command r on azure
2024-04-05 09:04:38 -07:00
Ishaan Jaff
5d196ff300
test - azure/command-r-plus
2024-04-05 08:56:05 -07:00
Ishaan Jaff
71352b1b36
fix add azure/command-r-plus
2024-04-05 08:53:24 -07:00
Ishaan Jaff
65b1a7be73
add azure command_r_plust
2024-04-05 08:51:39 -07:00
lazyhope
596d50a72a
Merge branch 'BerriAI:main' into anthropic-tools-use-2024-04-04
2024-04-05 23:51:03 +08:00
Caixiaopig
3d96e810b0
Updating the default Anthropic Officlal Claude 3 max_tokens to 4096
...
fix bug
2024-04-05 09:45:57 -05:00
Zihao Li
342073c212
Clean up imports of XML processing functions
2024-04-05 22:36:18 +08:00
Krish Dholakia
eb34306099
Merge pull request #2665 from BerriAI/litellm_claude_vertex_ai
...
[WIP] feat(vertex_ai_anthropic.py): Add support for claude 3 on vertex ai
2024-04-05 07:06:04 -07:00
Krish Dholakia
4ce8227e70
Merge pull request #2841 from Manouchehri/nuke-gemini-1.5-pro-vision
...
Fix: Remove non-existent gemini-1.5-pro-vision model.
2024-04-05 07:03:38 -07:00
Zihao Li
71fdf31790
Refactor tool result submission and tool invoke conversion
2024-04-05 17:11:35 +08:00
Zihao Li
d2cf9d2cf1
Move tool definitions from system prompt to parameter and refactor tool calling parse
2024-04-05 16:01:40 +08:00
Caixiaopig
09463bc584
Updating the default Anthropic Claude 3 max_tokens to 4096
...
The default value of max_tokens used to be 256. If the client does not set a larger value, the model's output may be truncated, so the default value has been changed to 4096. This value is also the maximum output value described in the official interface.
see: https://docs.anthropic.com/claude/reference/messages_post
2024-04-05 14:44:40 +08:00
Krrish Dholakia
b0d80de14d
docs(vertex.md): fix import routes
2024-04-04 21:32:44 -07:00
Krrish Dholakia
003cd3b102
docs(vertex.md): add tutorial for using vertex ai with gcp service account
2024-04-04 21:28:28 -07:00
Ishaan Jaff
d313f5bd61
Merge pull request #2847 from themrzmaster/feat/add_command_r_plus
...
Add command-r-plus
2024-04-04 21:06:42 -07:00
Krrish Dholakia
e1aa536ea6
bump: version 1.34.26 → 1.34.27
2024-04-04 20:02:41 -07:00
Krish Dholakia
b5f74bf6b7
Merge pull request #2851 from BerriAI/litellm_add_model_api_fix
...
feat(ui): add models via ui
2024-04-04 19:43:58 -07:00
Krish Dholakia
24e2535441
Merge branch 'main' into litellm_add_model_api_fix
2024-04-04 19:43:52 -07:00
Krrish Dholakia
1ee78c39e9
fix(proxy_server.py): skip to next model if invalid model (raise logger.error)
2024-04-04 19:22:17 -07:00
Krrish Dholakia
fbfcd57798
fix(proxy_server.py): fix linting issue
2024-04-04 19:15:57 -07:00
Krrish Dholakia
e3c2bdef4d
feat(ui): add models via ui
...
adds ability to add models via ui to the proxy. also fixes additional bugs around new /model/new endpoint
2024-04-04 18:56:20 -07:00
Ishaan Jaff
eaf81ed31c
fix github stable releases
2024-04-04 18:26:47 -07:00
Ishaan Jaff
ab368fcfc7
fix use stable / latest tags correctly
2024-04-04 18:15:53 -07:00
Ishaan Jaff
28d55cb511
stable releases
2024-04-04 18:07:36 -07:00
Ishaan Jaff
66f579f923
stable releases - ci/cd
2024-04-04 18:06:17 -07:00
Ishaan Jaff
280a3d580b
set release type
2024-04-04 18:02:37 -07:00
Ishaan Jaff
0dd7ab44ed
set release type on releases
2024-04-04 18:00:22 -07:00
Ishaan Jaff
7f50b80917
(ci/cd) aws suspended account
2024-04-04 17:43:16 -07:00
Ishaan Jaff
0b748f2eb0
ui - new build
2024-04-04 17:36:26 -07:00
Ishaan Jaff
31e98aa90e
Merge pull request #2850 from BerriAI/litellm_track_cost_tag
...
[UI] Show Usage Per Tag
2024-04-04 17:31:36 -07:00
