Krrish Dholakia
|
015d1a4fd9
|
fix(vertex_httpx.py): google search grounding fix
|
2024-07-14 08:06:17 -07:00 |
|
Krish Dholakia
|
f01298bec9
|
Merge pull request #4588 from Manouchehri/vertex-seed-2973
feat(vertex_httpx.py): Add seed parameter
|
2024-07-11 22:02:13 -07:00 |
|
Krrish Dholakia
|
789d2dab15
|
fix(vertex_httpx.py): add sync vertex image gen support
Fixes https://github.com/BerriAI/litellm/issues/4623
|
2024-07-09 13:33:54 -07:00 |
|
Krrish Dholakia
|
f98c819d4b
|
fix(vertex_httpx.py): fix gtool handling
|
2024-07-09 08:01:49 -07:00 |
|
Krrish Dholakia
|
71ad281c0a
|
feat(vertex_httpx.py): add support for gemini 'grounding'
Adds support for https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/grounding#rest
|
2024-07-08 21:37:07 -07:00 |
|
David Manouchehri
|
3f993699c0
|
feat(vertex_httpx.py): Add undocumented seed parameter.
|
2024-07-07 23:32:04 +00:00 |
|
Krrish Dholakia
|
9f900a1bed
|
fix(vertex_httpx.py): support tool calling w/ streaming for vertex ai + gemini
|
2024-07-06 14:02:25 -07:00 |
|
Krrish Dholakia
|
56410cfcd0
|
fix(proxy_server.py): support langfuse logging for rejected requests on /v1/chat/completions
|
2024-07-05 13:07:09 -07:00 |
|
Krrish Dholakia
|
8a8dde6622
|
fix(vertex_httpx.py): fix assumptions on usagemetadata
|
2024-07-05 11:01:51 -07:00 |
|
Krrish Dholakia
|
d0862697b8
|
fix(vertex_httpx.py): fix supported vertex params
|
2024-07-04 21:17:52 -07:00 |
|
Krish Dholakia
|
2fa9a1f3cf
|
Merge pull request #4461 from t968914/litellm-fix-vertexaibeta
fix: Include vertex_ai_beta in vertex_ai param mapping/Do not use google auth project_id
|
2024-07-04 15:27:20 -07:00 |
|
Krish Dholakia
|
4e1b247c1d
|
Revert "fix(vertex_anthropic.py): Vertex Anthropic tool calling - native params "
|
2024-07-03 17:55:37 -07:00 |
|
Krrish Dholakia
|
46800ba20a
|
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 |
|
Tiger Yu
|
58bd8a4afb
|
Merge branch 'main' into litellm-fix-vertexaibeta
|
2024-07-02 09:49:44 -07:00 |
|
David Manouchehri
|
760b1dd5fa
|
feat(vertex_httpx.py): Support cachedContent.
|
2024-07-01 16:59:35 +00:00 |
|
Krrish Dholakia
|
c2bc344ff8
|
build(pyproject.toml): remove ijson dep. add jsonschema dep.
|
2024-06-29 19:24:00 -07:00 |
|
Krrish Dholakia
|
ad6625ae47
|
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
|
d9177f189e
|
fix(vertex_httpx.py): support passing response_schema to gemini
|
2024-06-29 11:33:19 -07:00 |
|
Krrish Dholakia
|
510826c457
|
fix(vertex_httpx.py): fix streaming for cloudflare proxy calls
|
2024-06-29 09:09:56 -07:00 |
|
Ishaan Jaff
|
9c2baac28c
|
fix gemini tool calling issue
|
2024-06-28 18:03:33 -07:00 |
|
Krrish Dholakia
|
66e3a4f30e
|
fix(support-'alt=sse'-param): Fixes https://github.com/BerriAI/litellm/issues/4459
|
2024-06-28 10:40:47 -07:00 |
|
Tiger Yu
|
6893c836c5
|
Include vertex_ai_beta in vertex_ai param mapping
|
2024-06-28 10:36:58 -07:00 |
|
Krrish Dholakia
|
1d690fd3f3
|
fix(vertex_httpx.py): only use credential project id, if user project id not given
|
2024-06-27 22:08:14 -07:00 |
|
John HU
|
a48b2799bd
|
Do not resolve project id from creds
|
2024-06-27 15:26:36 -07:00 |
|
Ishaan Jaff
|
8398065404
|
fix gemini test
|
2024-06-26 19:00:30 -07:00 |
|
Krrish Dholakia
|
cdf56dd320
|
fix(vertex_httpx.py): Return empty model response for content filter violations
|
2024-06-24 19:22:20 -07:00 |
|
Krrish Dholakia
|
62ff12c0b6
|
fix(vertex_httpx.py): cover gemini content violation (on prompt)
|
2024-06-24 19:13:56 -07:00 |
|
Krrish Dholakia
|
14fdbf26a6
|
fix(vertex_httpx.py): flush remaining chunks from stream
|
2024-06-22 20:33:54 -07:00 |
|
Krrish Dholakia
|
2d8135231f
|
fix(vertex_httpx.py): ignore vertex finish reason - wait for stream to end
Fixes https://github.com/BerriAI/litellm/issues/4339
|
2024-06-22 20:21:01 -07:00 |
|
Krrish Dholakia
|
80f405780f
|
fix(vertex_httpx.py): cleanup docstring
|
2024-06-21 09:11:11 -07:00 |
|
Krrish Dholakia
|
60b4249767
|
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
|
c88c3002a4
|
fix(vertex_httpx.py): allow passing extra headers
Closes https://github.com/BerriAI/litellm/pull/4327
|
2024-06-20 21:14:44 -07:00 |
|
Krrish Dholakia
|
1f87f45709
|
fix(vertex_httpx.py): support setting custom api base for vertex ai calls
Closes https://github.com/BerriAI/litellm/issues/4317
|
2024-06-20 16:33:37 -07:00 |
|
Krrish Dholakia
|
0a96865c48
|
fix(vertex_httpx.py): fix supports system message check for vertex_ai_beta
Fixes https://github.com/BerriAI/litellm/issues/4283
|
2024-06-19 13:17:22 -07:00 |
|
Krish Dholakia
|
4c5eb58fc9
|
Merge pull request #4266 from BerriAI/litellm_gemini_image_url
Support 'image url' to vertex ai / google ai studio gemini models
|
2024-06-18 20:39:25 -07:00 |
|
Krrish Dholakia
|
71e882f4a2
|
fix(vertex_httpx.py): re-raise vertex content policy violation error
Fixes https://github.com/BerriAI/litellm/issues/4270
|
2024-06-18 19:00:35 -07:00 |
|
Krrish Dholakia
|
27f7c69df7
|
fix(vertex_httpx.py): add better debug logging for vertex httpx
|
2024-06-18 18:00:29 -07:00 |
|
Krrish Dholakia
|
72c6c47fa3
|
fix(vertex_httpx.py): support safety settings on vertex ai
Fixes https://github.com/BerriAI/litellm/issues/4267
|
2024-06-18 11:43:07 -07:00 |
|
Krrish Dholakia
|
f745245ad5
|
fix(support-passing-image-url-to-gemini-via-vertex-ai): Closes https://github.com/BerriAI/litellm/issues/4262
|
2024-06-18 10:55:58 -07:00 |
|
Krrish Dholakia
|
cc1ec55e5b
|
fix(vertex_httpx.py): check if model supports system messages before sending separately
|
2024-06-17 17:32:38 -07:00 |
|
Krrish Dholakia
|
d4ce17b87c
|
fix(vertex_httpx.py): support async streaming for google ai studio gemini
|
2024-06-17 14:59:30 -07:00 |
|
Krrish Dholakia
|
e31465d940
|
feat(main.py): initial commit - refactoring google ai studio to just use vertex httpx
Uses the same calling logic for google ai studio/vertex ai. Simplifies logic, gives google ai studio integration all of vertex
ai features.
|
2024-06-17 13:31:46 -07:00 |
|
Krrish Dholakia
|
9d7f5d503c
|
refactor(utils.py): refactor Logging to it's own class. Cut down utils.py to <10k lines.
Easier debugging
Reference: https://github.com/BerriAI/litellm/issues/4206
|
2024-06-15 10:57:20 -07:00 |
|
Krrish Dholakia
|
ab4b1d931b
|
fix(vertex_httpx.py): support json schema
|
2024-06-12 21:46:43 -07:00 |
|
Krrish Dholakia
|
e60b0e96e4
|
fix(vertex_httpx.py): add function calling support to httpx route
|
2024-06-12 21:11:00 -07:00 |
|
Krrish Dholakia
|
afebf867f6
|
fix(vertex_httpx.py): support async completion calls
|
2024-06-12 20:15:03 -07:00 |
|
Krrish Dholakia
|
1dac2aa59f
|
fix(vertex_httpx.py): support streaming via httpx client
|
2024-06-12 19:55:14 -07:00 |
|
Krrish Dholakia
|
29169b3039
|
feat(vertex_httpx.py): Moving to call vertex ai via httpx (instead of their sdk). Allows us to support all their api updates.
|
2024-06-12 16:47:00 -07:00 |
|
Ishaan Jaff
|
6fef49d1f6
|
fix vertex httpx client
|
2024-05-20 13:43:54 -07:00 |
|
Ishaan Jaff
|
883a9eb69a
|
add parameter mapping with vertex ai
|
2024-05-20 13:28:20 -07:00 |
|