Shixian Sheng and GitHub
54e83ac8a8
Update all_caches.md
2025-03-26 15:29:58 -04:00
801ecb6517
Nova Canvas complete image generation tasks ( #9177 ) ( #9525 )
...
* Nova Canvas complete image generation tasks (#9177 )
* add initial support for Amazon Nova Canvas model
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* adjust name to AmazonNovaCanvas and map function variables to config
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* tighten model name check
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* fix quality mapping
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* add premium quality in config
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* support all Amazon Nova Canvas tasks
* remove unused import
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* add tests for image generation tasks and fix payload
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* add missing util file
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* update model prices backup file
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* remove image tasks other than text->image
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* add color guided generation task for Nova Canvas
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* fix merge
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* add nova canvas image generation documentation
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
* add nova canvas unit tests
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
---------
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com >
* ci(config.yml): bump ci config
* test: fix test
---------
Signed-off-by: omrishiv <327609+omrishiv@users.noreply.github.com >
Co-authored-by: omrishiv <327609+omrishiv@users.noreply.github.com >
2025-03-26 11:28:20 -07:00
Ishaan Jaff
8c845847cd
fix vertex embedding perf test
2025-03-26 10:25:50 -07:00
Ishaan Jaff
5f51228b72
DNS lookup for Redis host
2025-03-26 09:28:59 -07:00
Ishaan Jaff
d7884114d0
setup_google_dns
2025-03-26 09:26:33 -07:00
Ishaan Jaff
68665ea028
DNS lookup for Redis host
2025-03-26 09:25:14 -07:00
Krrish Dholakia
a97d0563b4
build(model_prices_and_context_window.json): add commercial rate limits for gemini 2.0 flash lite
2025-03-26 08:58:35 -07:00
Ishaan Jaff
c3dc4a2ecd
fix DNS resolution
2025-03-26 08:55:18 -07:00
Ishaan Jaff
e5a5dca777
fix load_testing
2025-03-26 08:46:23 -07:00
Ishaan Jaff
7123b69cca
fix caching unit tests
2025-03-26 08:42:55 -07:00
Ishaan Jaff
22dfc4dea9
fix user_api_key_auth example config
2025-03-26 08:36:11 -07:00
Ishaan Jaff
e7a8b5a809
run ci/cd again
2025-03-26 08:12:51 -07:00
Krish Dholakia and GitHub
6fd18651d1
Support litellm.api_base for vertex_ai + gemini/ across completion, embedding, image_generation ( #9516 )
...
* test(tests): add unit testing for litellm_proxy integration
* fix(cost_calculator.py): fix tracking cost in sdk when calling proxy
* fix(main.py): respect litellm.api_base on `vertex_ai/` and `gemini/` routes
* fix(main.py): consistently support custom api base across gemini + vertexai on embedding + completion
* feat(vertex_ai/): test
* fix: fix linting error
* test: set api base as None before starting loadtest
2025-03-25 23:46:20 -07:00
Ishaan Jaff
8657816477
fix gemini/gemini-2.0-flash-lite on model cost map
2025-03-25 23:20:43 -07:00
Krrish Dholakia
e0880734d9
docs(config_settings.md): cleanup docs
2025-03-25 23:11:45 -07:00
Krrish Dholakia
24b3e80eba
ci: update github action
2025-03-25 23:11:45 -07:00
Ishaan Jaff and GitHub
c61214dcf1
Merge pull request #9523 from BerriAI/litellm_add_gemini_flash_lite
...
[Feat - New Model] Add VertexAI `gemini-2.0-flash-lite` and Google AI Studio `gemini-2.0-flash-lite`
2025-03-25 23:11:44 -07:00
Ishaan Jaff
c473e2b1c2
setup_google_dns
2025-03-25 23:02:02 -07:00
Ishaan Jaff
3725ba4f63
setup_google_dns
2025-03-25 22:52:31 -07:00
Ishaan Jaff
61816dfd04
litellm_assistants_api_testing bump python
2025-03-25 22:31:16 -07:00
Ishaan Jaff
24a329ea5b
Set DNS
2025-03-25 22:29:40 -07:00
Ishaan Jaff
9aec7c3878
test_create_delete_assistants
2025-03-25 22:08:06 -07:00
Ishaan Jaff
79ef184345
run ci/cd again
2025-03-25 21:57:45 -07:00
Krish Dholakia and GitHub
6cd6ff801f
ci(publish-migrations.yml): add action for publishing prisma db migrations ( #9537 )
2025-03-25 17:55:59 -07:00
Krrish Dholakia
e8c4cd8c1a
docs: cleanup docs
2025-03-25 12:25:42 -07:00
Krrish Dholakia
1a58e8bfe5
docs(admin_ui_sso.md): add logout url
2025-03-25 12:25:16 -07:00
Krrish Dholakia
ff61ce6751
docs: update release note with patch
2025-03-25 10:17:34 -07:00
Ishaan Jaff
0af9a5e8d0
add gemini/gemini-2.0-flash-lite
2025-03-25 07:51:42 -07:00
Ishaan Jaff
62bb7d6605
add vertex gemini-2.0-flash-lite
2025-03-25 07:48:33 -07:00
Ishaan Jaff
b19529a46e
fix docker compose
2025-03-25 07:03:43 -07:00
92883560f0
fix vertex ai multimodal embedding translation ( #9471 )
...
* remove data:image/jpeg;base64, prefix from base64 image input
vertex_ai's multimodal embeddings endpoint expects a raw base64 string without `data:image/jpeg;base64,` prefix.
* Add Vertex Multimodal Embedding Test
* fix(test_vertex.py): add e2e tests on multimodal embeddings
* test: unit testing
* test: remove sklearn dep
* test: update test with fixed route
* test: fix test
---------
Co-authored-by: Jonarod <jonrodd@gmail.com >
Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com >
2025-03-24 23:23:28 -07:00
Krrish Dholakia
75994d0bf0
test: improve flaky test
2025-03-24 23:15:04 -07:00
superpoussin22 and GitHub
12fdd25841
Update model_prices_and_context_window.json ( #9459 )
...
add mistral-small for vertex_ai
2025-03-24 22:44:00 -07:00
a619580bf8
Add vertexai topLogprobs support ( #9518 )
...
* Added support for top_logprobs in vertex gemini models
* Testing for top_logprobs feature in vertexai
* Update litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
Co-authored-by: Tom Matthews <tomukmatthews@gmail.com >
* refactor(tests/): refactor testing to be in correct repo
---------
Co-authored-by: Aditya Thaker <adityathaker28@gmail.com >
Co-authored-by: Tom Matthews <tomukmatthews@gmail.com >
2025-03-24 22:42:38 -07:00
Ishaan Jaff
da16cef4ba
Expose MCP tools
2025-03-24 21:36:02 -07:00
Ishaan Jaff
18dfb70023
mcp docs, exposing tools now live
2025-03-24 21:35:29 -07:00
Ishaan Jaff
f1a8b1984a
fix mcp test deps
2025-03-24 21:34:18 -07:00
Krish Dholakia and GitHub
bd309a28c5
Merge pull request #9512 from BerriAI/litellm_dev_03_24_2025_p3
...
fix(invoke_handler.py): remove hard coded chunk on streaming usage
2025-03-24 21:21:36 -07:00
Ishaan Jaff
80f201ff15
bump: version 1.64.0 → 1.64.1
2025-03-24 21:21:18 -07:00
Ishaan Jaff
f2b9a7f2ea
pip install "langchain_mcp_adapters==0.0.5"
2025-03-24 21:20:11 -07:00
Ishaan Jaff
863fe3a4d2
fix import mcp router
2025-03-24 21:08:24 -07:00
Ishaan Jaff
fb3a67ba8d
fix code quality
2025-03-24 21:06:17 -07:00
Ishaan Jaff
dcc2edbd4d
fix mcp import
2025-03-24 21:02:54 -07:00
Ishaan Jaff and GitHub
df1789902d
Merge pull request #9426 from BerriAI/litellm_exp_mcp_server
...
[Feat] Support for exposing MCP tools on litellm proxy
2025-03-24 20:48:46 -07:00
Ishaan Jaff
4a675da0f9
fix setup
2025-03-24 19:10:59 -07:00
Ishaan Jaff
08a4ba1b7e
Merge branch 'main' into litellm_exp_mcp_server
2025-03-24 19:03:56 -07:00
Ishaan Jaff
395e4e73d0
langchain_mcp_adapters
2025-03-24 18:59:32 -07:00
Ishaan Jaff
ab1f87bb59
add "mcp==1.5.0" to optional pyproject for litellm proxy
2025-03-24 18:56:32 -07:00
Ishaan Jaff
002837f962
fix linting errors
2025-03-24 18:48:43 -07:00
Ishaan Jaff
ffce25cd94
bump deps
2025-03-24 18:44:24 -07:00
