Krrish Dholakia
|
0b06a76cf9
|
fix(router.py): don't cooldown on apiconnectionerrors
Fixes issue where model would be in cooldown due to api connection errors
|
2024-08-24 09:53:05 -07:00 |
|
Krrish Dholakia
|
6e9f048618
|
fix: move to using pydantic obj for setting values
|
2024-07-11 13:18:36 -07:00 |
|
Krrish Dholakia
|
54c31e5af7
|
fix(factory.py): check if assistant message content is not none before translating
|
2024-07-09 07:48:12 -07:00 |
|
Krrish Dholakia
|
c425cba93a
|
fix(vertex_httpx.py): fix supported vertex params
|
2024-07-04 21:17:52 -07:00 |
|
andrewmjc
|
e07b110b47
|
matching openai tool result spec
|
2024-07-02 16:57:13 -06:00 |
|
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 |
|
Ishaan Jaff
|
80d8bf5d8f
|
fix raise better error message on reaching failed vertex import
|
2024-06-27 12:02:19 -07:00 |
|
Krrish Dholakia
|
4c5f077bd3
|
fix(vertex_ai.py): check if message length > 0 before merging
|
2024-06-19 18:47:43 -07:00 |
|
Krrish Dholakia
|
3f7252c422
|
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
|
115adc7c30
|
fix(init.py): fix imports
|
2024-06-15 11:31:09 -07:00 |
|
Krrish Dholakia
|
4f91205530
|
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 |
|
Krish Dholakia
|
05e21441a6
|
Merge branch 'main' into litellm_vertex_completion_httpx
|
2024-06-12 21:19:22 -07:00 |
|
Krrish Dholakia
|
3b913443fe
|
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
|
9aa4b6e98c
|
vertex embeddings optional_params
|
2024-06-12 10:56:36 -07:00 |
|
Ishaan Jaff
|
aaa4a32d65
|
feat - support vertex text input
|
2024-06-12 10:11:44 -07:00 |
|
Ishaan Jaff
|
f09158504b
|
feat - support vertex ai dimensions
|
2024-06-12 09:29:51 -07:00 |
|
nick-rackauckas
|
4747fda47f
|
Fix
|
2024-06-06 16:57:42 -07:00 |
|
nick-rackauckas
|
cc36d906a9
|
Remove unused function
|
2024-06-06 16:30:23 -07:00 |
|
nick-rackauckas
|
6dac7d43a1
|
Fix to work with all supported Gemini file types
|
2024-06-06 16:15:01 -07:00 |
|
Ishaan Jaff
|
422b4b1728
|
Merge pull request #4039 from themrzmaster/main
fix tool usage null content using vertexai
|
2024-06-06 12:41:25 -07:00 |
|
Krrish Dholakia
|
58bd2b4ea6
|
fix(vertex_ai.py): support video + pdf for vertex ai
|
2024-06-06 08:06:20 -07:00 |
|
lucca
|
5e25979596
|
improve
|
2024-06-06 11:15:56 -03:00 |
|
lucca
|
1122a40374
|
fix function calling
|
2024-06-06 11:09:35 -03:00 |
|
Rajan Paneru
|
2e25416c02
|
Table format fix and Typo
* Fixed marked down table formats because they were looking ugly in pycharm
* Typos Fixes.
|
2024-06-06 22:29:59 +09:30 |
|
Ishaan Jaff
|
f52bf5976b
|
fix - vertex ai cache clients
|
2024-05-30 21:22:32 -07:00 |
|
Krrish Dholakia
|
281906ff33
|
fix(vertex_ai.py): handle nested content dictionary for assistant message
openai allows the assistant content message to also be a list of dictionaries, handle that
|
2024-05-24 22:47:47 -07:00 |
|
Krrish Dholakia
|
49b71c8118
|
fix(vertex_ai.py): revert system instructions - unable to find supported vertex version
|
2024-05-20 06:30:11 -07:00 |
|
Krrish Dholakia
|
45c46a84d0
|
fix(vertex_ai.py): support passing system instructions to vertex ai
|
2024-05-20 06:18:19 -07:00 |
|
Krrish Dholakia
|
65aacc0c1a
|
fix(vertex_ai.py): use chat_messages_with_history for async + streaming calls
|
2024-05-19 12:30:24 -07:00 |
|
Krrish Dholakia
|
f9ab72841a
|
fix(vertex_ai.py): passing all tests on 'test_amazing_vertex_completion.py
|
2024-05-19 12:22:21 -07:00 |
|
Krrish Dholakia
|
a2c66ed4fb
|
fix(vertex_ai.py): support passing in result of tool call to vertex
Fixes https://github.com/BerriAI/litellm/issues/3709
|
2024-05-19 11:34:07 -07:00 |
|
Krrish Dholakia
|
04ae285001
|
fix(vertex_ai.py): support tool call list response async completion
|
2024-05-13 10:42:31 -07:00 |
|
Krrish Dholakia
|
6714854bb7
|
feat(router.py): support region routing for bedrock, vertex ai, watsonx
|
2024-05-11 11:04:00 -07:00 |
|
Krrish Dholakia
|
c12af219af
|
fix: fix linting
|
2024-05-10 20:23:33 -07:00 |
|
Krrish Dholakia
|
94f3d361b0
|
fix(vertex_ai.py): fix list tool call responses
Closes https://github.com/BerriAI/litellm/issues/3147
|
2024-05-10 20:05:58 -07:00 |
|
Krrish Dholakia
|
6575143460
|
feat(proxy_server.py): return litellm version in response headers
|
2024-05-08 16:00:08 -07:00 |
|
Krish Dholakia
|
1841b74f49
|
Merge branch 'main' into litellm_common_auth_params
|
2024-04-28 08:38:06 -07:00 |
|
Krrish Dholakia
|
463b1aff24
|
fix(vertex_ai.py): support safety settings for async streaming calls
|
2024-04-27 11:43:22 -07:00 |
|
Krrish Dholakia
|
48f19cf839
|
feat(utils.py): unify common auth params across azure/vertex_ai/bedrock/watsonx
|
2024-04-27 11:06:18 -07:00 |
|
pwm
|
6fedcb873b
|
add safety_settings parameters to Vertex vision async_completion function
|
2024-04-26 14:35:01 +08:00 |
|
Krrish Dholakia
|
5f8d88d363
|
fix(vertex_ai.py): handle stream=false
also adds unit testing for vertex ai calls with langchain
|
2024-04-25 13:59:37 -07:00 |
|
Krish Dholakia
|
435a4b5ed4
|
Merge pull request #3267 from BerriAI/litellm_openai_streaming_fix
fix(utils.py): fix streaming to not return usage dict
|
2024-04-24 21:08:33 -07:00 |
|
Krrish Dholakia
|
b918f58262
|
fix(vertex_ai.py): raise explicit error when image url fails to download - prevents silent failure
|
2024-04-24 09:23:15 -07:00 |
|
Krrish Dholakia
|
48c2c3d78a
|
fix(utils.py): fix streaming to not return usage dict
Fixes https://github.com/BerriAI/litellm/issues/3237
|
2024-04-24 08:06:07 -07:00 |
|
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 |
|