Krish Dholakia
|
c5fe467cdd
|
Merge pull request #5025 from jcheng5/streaming-tools-anthropic
Handle bedrock tool calling in stream_chunk_builder
|
2024-08-03 20:31:05 -07:00 |
|
Krish Dholakia
|
bd227f7b57
|
Merge pull request #5036 from BerriAI/litellm_loadbalancing_test
feat(router.py): add flag for mock testing loadbalancing for rate limit errors
|
2024-08-03 20:30:01 -07:00 |
|
Krish Dholakia
|
9ba8e3047f
|
Merge branch 'main' into litellm_loadbalancing_test
|
2024-08-03 20:29:54 -07:00 |
|
Ishaan Jaff
|
22bc70633e
|
docs add when to use litellm
|
2024-08-03 19:10:16 -07:00 |
|
Ishaan Jaff
|
93b0d23997
|
fix fine tune api tests
|
2024-08-03 19:02:11 -07:00 |
|
Ishaan Jaff
|
7fae2aa394
|
ci/cd run again
|
2024-08-03 18:48:10 -07:00 |
|
Ishaan Jaff
|
009697425d
|
fix fine tuning tests
|
2024-08-03 18:34:26 -07:00 |
|
Ishaan Jaff
|
1c1631222c
|
fix test test_aimage_generation_vertex_ai
|
2024-08-03 18:32:52 -07:00 |
|
Ishaan Jaff
|
b6cf433ed9
|
bump: version 1.42.11 → 1.42.12
|
2024-08-03 18:12:53 -07:00 |
|
Ishaan Jaff
|
bbd11e61bf
|
Merge pull request #5037 from BerriAI/litellm_support_native_vertex_endpoint
[Feat] support all native vertex ai endpoints - Gemini API, Embeddings API, Imagen API, Batch prediction API, Tuning API, CountTokens API
|
2024-08-03 18:12:03 -07:00 |
|
Ishaan Jaff
|
e73eb19678
|
docs default vertex
|
2024-08-03 18:09:48 -07:00 |
|
Ishaan Jaff
|
3a94aac343
|
docs - fix merge conflicts
|
2024-08-03 17:59:46 -07:00 |
|
Ishaan Jaff
|
9d2eab555b
|
docs tuning api
|
2024-08-03 17:58:20 -07:00 |
|
Ishaan Jaff
|
7f95a865fe
|
docs add example curl command
|
2024-08-03 17:56:41 -07:00 |
|
Ishaan Jaff
|
bef5a8b61f
|
Merge branch 'main' into litellm_support_native_vertex_endpoint
|
2024-08-03 17:47:35 -07:00 |
|
Ishaan Jaff
|
50c9fa38f9
|
docs link to vertex ai endpoints
|
2024-08-03 17:44:28 -07:00 |
|
Ishaan Jaff
|
94e5d0f734
|
docs add vertex ai endpoints
|
2024-08-03 17:41:45 -07:00 |
|
Ishaan Jaff
|
c8438715af
|
add vertex ai countTokens endpoint
|
2024-08-03 17:34:10 -07:00 |
|
Ishaan Jaff
|
2d5c57e545
|
add vertex embeddings endpoints
|
2024-08-03 17:26:49 -07:00 |
|
Ishaan Jaff
|
c98733863a
|
add vertex generateContent
|
2024-08-03 17:17:54 -07:00 |
|
Ishaan Jaff
|
8051781af0
|
working code for vertex ai routes
|
2024-08-03 16:56:33 -07:00 |
|
Ishaan Jaff
|
64c008045f
|
use native endpoints
|
2024-08-03 16:52:43 -07:00 |
|
Ishaan Jaff
|
af04bbecca
|
set native vertex endpoints
|
2024-08-03 16:52:03 -07:00 |
|
Ishaan Jaff
|
cfdbb3d237
|
docs secret manager
|
2024-08-03 12:54:07 -07:00 |
|
Krrish Dholakia
|
58de3f9486
|
fix(vertex_httpx.py): fix linting error
|
2024-08-03 12:54:07 -07:00 |
|
Ishaan Jaff
|
203cc35abc
|
docs - use consistent name for LiteLLM proxy server
|
2024-08-03 12:54:07 -07:00 |
|
Ishaan Jaff
|
942e77dfa8
|
organize docs
|
2024-08-03 12:54:07 -07:00 |
|
Ishaan Jaff
|
1894aefd05
|
docs clean up organization
|
2024-08-03 12:54:07 -07:00 |
|
Ishaan Jaff
|
4a43f9f411
|
docs supported models / providers
|
2024-08-03 12:54:07 -07:00 |
|
Ishaan Jaff
|
39a98a2882
|
docs secret manager
|
2024-08-03 12:53:49 -07:00 |
|
Krrish Dholakia
|
641192e049
|
fix(vertex_httpx.py): fix linting error
|
2024-08-03 12:53:46 -07:00 |
|
Krrish Dholakia
|
7a0792c918
|
fix(router.py): move deployment cooldown list message to error log, not client-side
don't show user all deployments
|
2024-08-03 12:49:39 -07:00 |
|
Ishaan Jaff
|
5bc8b59b11
|
docs - use consistent name for LiteLLM proxy server
|
2024-08-03 12:49:35 -07:00 |
|
Ishaan Jaff
|
6faeac4cf6
|
organize docs
|
2024-08-03 12:47:22 -07:00 |
|
Krrish Dholakia
|
1d892a41d2
|
docs(proxy/reliability.md): add docs on testing if loadbalancing is working as expected
|
2024-08-03 12:44:04 -07:00 |
|
Ishaan Jaff
|
4052b0d4c4
|
docs clean up organization
|
2024-08-03 12:34:22 -07:00 |
|
Krrish Dholakia
|
6b8806b45f
|
feat(router.py): add flag for mock testing loadbalancing for rate limit errors
|
2024-08-03 12:34:11 -07:00 |
|
Ishaan Jaff
|
6377304d96
|
docs supported models / providers
|
2024-08-03 12:24:27 -07:00 |
|
Krrish Dholakia
|
ed8b20fa18
|
fix(utils.py): parse out aws specific params from openai call
Fixes https://github.com/BerriAI/litellm/issues/5009
|
2024-08-03 12:04:44 -07:00 |
|
Joe Cheng
|
b7be609d6e
|
Use correct key name
|
2024-08-03 11:58:46 -07:00 |
|
Ishaan Jaff
|
af91740fbb
|
docs native vertex ft endpoint
|
2024-08-03 11:56:43 -07:00 |
|
Krrish Dholakia
|
5add6687cc
|
fix(types/utils.py): fix linting errors
|
2024-08-03 11:48:33 -07:00 |
|
Ishaan Jaff
|
2e596c6c5b
|
add support for pass through vertex ai ft jobs
|
2024-08-03 11:47:43 -07:00 |
|
Ishaan Jaff
|
19474c3f0f
|
support v1/projects/tuningJobs
|
2024-08-03 11:46:39 -07:00 |
|
Krrish Dholakia
|
c982ec88d8
|
fix(bedrock.py): fix response format for bedrock image generation response
Fixes https://github.com/BerriAI/litellm/issues/5010
|
2024-08-03 09:46:49 -07:00 |
|
Ishaan Jaff
|
1d56c2f83e
|
fix ft api test
|
2024-08-03 09:38:02 -07:00 |
|
Ishaan Jaff
|
a70d112b98
|
Merge pull request #5035 from BerriAI/docs_add_example_doing_vtx_ft
Docs - Add example of Vertex AI fine tuning API
|
2024-08-03 09:36:37 -07:00 |
|
Ishaan Jaff
|
a44ff761ab
|
Merge pull request #5034 from BerriAI/litellm_vtx_ft_param_mapping
[Feat] Vertex AI fine tuning - support translating hyperparameters
|
2024-08-03 09:33:44 -07:00 |
|
Ishaan Jaff
|
e3bee177e5
|
docs create fine tuning jobs
|
2024-08-03 09:29:12 -07:00 |
|
Krrish Dholakia
|
d2569b1443
|
docs(github.md): cleanup docs
|
2024-08-03 09:21:36 -07:00 |
|