Krrish Dholakia
|
ec2c70e362
|
fix(vertex_ai.py): fix streaming logic
|
2024-04-22 19:15:20 -07:00 |
|
Krrish Dholakia
|
0bb8a4434e
|
fix(vertex_ai.py): remove ExtendedGenerationConfig usage
|
2024-04-22 18:23:21 -07:00 |
|
David Manouchehri
|
c643e04ada
|
improve(vertex_ai.py): Add frequency_penalty and presence_penalty.
|
2024-04-22 18:02:59 +00:00 |
|
David Manouchehri
|
1a7eec5786
|
improve(vertex_ai.py): Switch to simpler dict type.
|
2024-04-22 17:00:37 +00:00 |
|
Krrish Dholakia
|
c47b39c032
|
fix(vertex_ai.py): fix faulty async completion function call tool check
|
2024-04-17 16:30:28 -07:00 |
|
Krrish Dholakia
|
32d94feddd
|
refactor(utils.py): make it clearer how vertex ai params are handled '
'
|
2024-04-17 16:20:56 -07:00 |
|
Krrish Dholakia
|
060ac995d6
|
fix(vertex_ai.py): accept credentials as a json string
|
2024-04-16 17:34:25 -07:00 |
|
Krrish Dholakia
|
1ec7118e1f
|
fix(vertex_ai_anthropic.py): set vertex_credentials for vertex ai anthropic calls
allows setting vertex credentials as a json string for vertex ai anthropic calls
|
2024-04-15 14:16:28 -07:00 |
|
Krrish Dholakia
|
77d6b882b8
|
fix(vertex_ai.py): check if 'response_mime_type' in generation config before passing it in
|
2024-04-11 23:10:59 -07:00 |
|
David Manouchehri
|
05350037be
|
(feat) - Extreme dirty hack for response_mime_type in Vertex AI.
|
2024-04-12 00:03:31 +00:00 |
|
David Manouchehri
|
d08674bf2f
|
(feat) - Dirty hack to get response_mime_type working before it's released in the Python SDK.
|
2024-04-12 00:03:30 +00:00 |
|
David Manouchehri
|
649c3bb0dd
|
(feat) - Add support for JSON mode in Vertex AI
|
2024-04-12 00:03:29 +00:00 |
|
Krrish Dholakia
|
67b1ad622f
|
feat(gemini.py): support google-genai system instruction
|
2024-04-09 17:23:14 -07:00 |
|
Krrish Dholakia
|
84a540f2d6
|
build: fix mypy build issues
|
2024-03-21 08:27:23 -07:00 |
|
Krrish Dholakia
|
cdb960eb34
|
fix(vertex_ai.py): correctly parse optional params and pass vertex ai project
|
2024-03-06 14:00:50 -08:00 |
|
Krrish Dholakia
|
2fac06de08
|
refactor(vertex_ai.py): add more logging for the vertex_ai file
|
2024-03-01 08:33:26 -08:00 |
|
ishaan-jaff
|
8d76df6a5e
|
(test) vertex - detect mime type
|
2024-02-29 15:38:25 -08:00 |
|
ishaan-jaff
|
8a96aa4ef0
|
(feat) add support for gemini base64 images
|
2024-02-29 14:42:20 -08:00 |
|
Krrish Dholakia
|
6352c8869c
|
refactor(vertex_ai.py): add more logging to show the vertex ai client init params
|
2024-02-27 18:35:15 -08:00 |
|
Krrish Dholakia
|
e48fff47dd
|
test(test_custom_callback_input.py): assert async success called only once during vertex ai streaming
|
2024-02-26 09:18:46 -08:00 |
|
Krrish Dholakia
|
9d17a0789f
|
fix(vertex_ai.py): fix vertex ai function calling
|
2024-02-22 21:28:24 -08:00 |
|
Krish Dholakia
|
851473b71a
|
Merge pull request #1969 from kan-bayashi/fix/support-multiple-tools-in-gemini
fix: fix the issues when using tools in gemini
|
2024-02-21 11:46:26 -08:00 |
|
Krish Dholakia
|
9b60ef9a3c
|
Merge pull request #1916 from RenaLu/main
Add support for Vertex AI custom models deployed on private endpoint
|
2024-02-15 22:47:36 -08:00 |
|
Rena Lu
|
02c58a9760
|
update request strings
|
2024-02-14 17:15:16 -05:00 |
|
Rena Lu
|
8c39a631d3
|
update request string
|
2024-02-14 22:11:55 +00:00 |
|
Krrish Dholakia
|
fe1fe70c64
|
fix(vertex_ai.py): map finish reason
|
2024-02-14 11:42:13 -08:00 |
|
kan-bayashi
|
90775910e2
|
fix if-else condition when function_call exits but empty
|
2024-02-14 17:38:00 +09:00 |
|
kan-bayashi
|
917525ee43
|
fix args=None case
|
2024-02-14 14:49:42 +09:00 |
|
Rena Lu
|
ce7ce3b719
|
fix optional params
|
2024-02-13 20:50:26 +00:00 |
|
Rena Lu
|
3fc0d8fda9
|
delete print
|
2024-02-13 18:49:56 +00:00 |
|
Rena Lu
|
e011f8022a
|
update private async
|
2024-02-13 18:33:52 +00:00 |
|
Rena Lu
|
60c0bec7b3
|
refactor to separate private mode with custom mode
|
2024-02-12 18:20:48 -05:00 |
|
Rena Lu
|
6833f37986
|
remove prints
|
2024-02-09 16:25:29 -05:00 |
|
Rena Lu
|
0e8a0aefd5
|
add vertex ai private endpoint support
|
2024-02-09 16:19:26 -05:00 |
|
Krrish Dholakia
|
0ffdf57dec
|
fix(vertex_ai.py): add async embedding support for vertex ai
|
2024-02-03 10:35:17 -08:00 |
|
Krrish Dholakia
|
d9ba8668f4
|
feat(vertex_ai.py): vertex ai gecko text embedding support
|
2024-02-03 09:48:29 -08:00 |
|
Krrish Dholakia
|
0072d796f6
|
fix(vertex_ai.py): fix params
|
2024-02-01 18:09:49 -08:00 |
|
Krrish Dholakia
|
0f9e793daf
|
feat(vertex_ai.py): add support for custom models via vertex ai model garden
|
2024-02-01 17:47:34 -08:00 |
|
Eslam karim gaber
|
2b3965dbf5
|
imports
|
2024-01-28 23:14:06 +02:00 |
|
Eslam karim gaber
|
48dbdaa73e
|
Change quota project to the correct project being used for the call
if not set it will use the default project in the ADC to set that quota project which is usually different
https://github.com/googleapis/python-aiplatform/issues/2557#issuecomment-1709284744
|
2024-01-28 19:55:01 +02:00 |
|
Krrish Dholakia
|
7cb49ee509
|
fix(vertex_ai.py): raise exception if vertex ai missing required dependendencies
|
2024-01-16 16:23:29 -08:00 |
|
ishaan-jaff
|
739d9e7a78
|
(fix) vertex ai - use usage from response
|
2023-12-29 16:30:25 +05:30 |
|
Krrish Dholakia
|
86403cd14e
|
fix(vertex_ai.py): support function calling for gemini
|
2023-12-28 19:07:04 +05:30 |
|
Krrish Dholakia
|
4905929de3
|
refactor: add black formatting
|
2023-12-25 14:11:20 +05:30 |
|
Graham Neubig
|
2362544344
|
Update the request_str
|
2023-12-21 09:58:06 -05:00 |
|
Graham Neubig
|
6e9267ca66
|
Make vertex_chat work with generate_content
|
2023-12-20 15:32:44 -05:00 |
|
Graham Neubig
|
482b3b5bc3
|
Add a default for safety settings in vertex AI
|
2023-12-20 13:12:50 -05:00 |
|
Graham Neubig
|
2d15e5384b
|
Add partial support of vertexai safety settings
|
2023-12-19 22:26:55 -05:00 |
|
ishaan-jaff
|
5ee6b87f2e
|
(fix) vertexai - gemini
|
2023-12-16 22:15:41 +05:30 |
|
ishaan-jaff
|
764f31c970
|
(feat) add async, async+stream for gemini
|
2023-12-16 18:58:12 +05:30 |
|