Commit graph

  • ab7a8a515e
    Merge branch 'main' into update-completions-skipping-for-groq raghotham 2025-09-06 15:36:44 -07:00
  • d23607483f
    chore: update the groq inference impl to use openai-python for openai-compat functions (#3348) Matthew Farrellee 2025-09-06 18:36:27 -04:00
  • e8e0dbc108
    chore(ui-deps): bump sonner from 2.0.6 to 2.0.7 in /llama_stack/ui dependabot[bot] 2025-09-06 20:17:44 +00:00
  • daa078fdbf
    chore(ui-deps): bump lucide-react in /llama_stack/ui dependabot[bot] 2025-09-06 20:17:37 +00:00
  • f1dd39693e
    chore(ui-deps): bump @radix-ui/react-dropdown-menu in /llama_stack/ui dependabot[bot] 2025-09-06 20:17:18 +00:00
  • 94510c21af
    chore(ui-deps): bump react-dom and @types/react-dom in /llama_stack/ui dependabot[bot] 2025-09-06 20:17:08 +00:00
  • a12dafe798
    chore(python-deps): bump pytest from 8.4.1 to 8.4.2 dependabot[bot] 2025-09-06 20:16:15 +00:00
  • 1b80d5393c
    chore(python-deps): bump locust from 2.39.1 to 2.40.1 dependabot[bot] 2025-09-06 20:16:08 +00:00
  • f71412e48b
    chore(github-deps): bump astral-sh/setup-uv from 6.6.0 to 6.6.1 dependabot[bot] 2025-09-06 20:15:39 +00:00
  • 1efa5c4efc
    chore(github-deps): bump actions/setup-python from 5.6.0 to 6.0.0 dependabot[bot] 2025-09-06 20:15:36 +00:00
  • 8bb6424e37
    chore(github-deps): bump actions/setup-node from 4.4.0 to 5.0.0 dependabot[bot] 2025-09-06 20:15:32 +00:00
  • e542c105f4
    chore(github-deps): bump actions/stale from 9.1.0 to 10.0.0 dependabot[bot] 2025-09-06 20:15:27 +00:00
  • ae0b9d9528
    docs: Update changelog Yuan Tang 2025-09-06 13:43:12 -06:00
  • ecd9d8dc1a
    test: introduce api conformance test (#3257) Charlie Doern 2025-09-06 15:40:33 -04:00
  • 3ebf5bd407
    Merge branch 'main' into update-completions-skipping-for-groq raghotham 2025-09-06 12:36:17 -07:00
  • 9252d9fc01
    chore(groq test): skip with_n tests for groq, it is not supported server-side (#3346) Matthew Farrellee 2025-09-06 15:35:30 -04:00
  • 309f06829c
    Merge branch 'main' into fix/embedding-model-type raghotham 2025-09-06 12:29:54 -07:00
  • 75645c963f
    Merge branch 'main' into use-openai-for-groq raghotham 2025-09-06 12:27:48 -07:00
  • 9f6629a95c
    Merge branch 'main' into update-with-n-skipping-for-groq raghotham 2025-09-06 12:26:23 -07:00
  • bf02cd846f
    chore: update the sambanova inference impl to use openai-python for openai-compat functions (#3345) Matthew Farrellee 2025-09-06 15:25:13 -04:00
  • 4c28544c04
    chore(gemini, tests): add skips for n and completions, gemini api does not support them (#3350) Matthew Farrellee 2025-09-06 15:22:44 -04:00
  • d6c3b36390
    chore: update the gemini inference impl to use openai-python for openai-compat functions (#3351) Matthew Farrellee 2025-09-06 15:22:20 -04:00
  • af33a8c982
    Merge branch 'main' into prompt-api Francisco Arceo 2025-09-06 11:09:41 -06:00
  • 4746d83c71 chore: update the gemini inference impl to use openai-python for openai-compat functions Matthew Farrellee 2025-09-06 13:03:56 -04:00
  • 060733ff10 chore(gemini, tests): add skips for n and completions, gemini api does not support them Matthew Farrellee 2025-09-06 13:00:03 -04:00
  • 7cd1c2c238
    feat: Updating Rag Tool to use Files API and Vector Stores API (#3344) Francisco Arceo 2025-09-06 07:26:34 -06:00
  • df6ac3cd0c fix unit test mock Matthew Farrellee 2025-09-06 09:05:07 -04:00
  • 6911145263 chore: update the groq inference impl to use openai-python for openai-compat functions Matthew Farrellee 2025-09-06 08:08:08 -04:00
  • a78c09afcb chore(groq test): skip completions tests for groq, api is not supported server-side Matthew Farrellee 2025-09-06 08:12:59 -04:00
  • 6ba9010648 chore(groq test): skip with_n tests for groq, it is not supported server-side Matthew Farrellee 2025-09-06 07:05:21 -04:00
  • e03f1b61f3 chore: update the sambanova inference impl to use openai-python for openai-compat functions Matthew Farrellee 2025-09-06 05:05:05 -04:00
  • ab5ab6e979 feat: Updating Rag Tool to use Files API and Vector Stores API Francisco Javier Arceo 2025-09-06 00:44:44 -04:00
  • 3c221b4cc6 fix tests Francisco Javier Arceo 2025-09-05 17:21:52 -04:00
  • 5d610de5db
    Merge branch 'main' into prompt-api Francisco Arceo 2025-09-05 15:11:00 -06:00
  • da0367de54 isolating distros Francisco Javier Arceo 2025-09-05 17:07:37 -04:00
  • 47b640370e
    feat(tests): introduce a test "suite" concept to encompass dirs, options (#3339) Ashwin Bharambe 2025-09-05 13:58:49 -07:00
  • c9dc6e1249 ugh Ashwin Bharambe 2025-09-05 13:46:31 -07:00
  • bce479ee47 clean up, add some docs Ashwin Bharambe 2025-09-05 13:40:52 -07:00
  • 0c2757a05b
    chore(sambanova test): skip with_n tests for sambanova, it is not implemented server-side (#3342) Matthew Farrellee 2025-09-05 15:00:09 -04:00
  • df1526991f
    feat(batches, completions): add /v1/completions support to /v1/batches (#3309) Matthew Farrellee 2025-09-05 14:59:57 -04:00
  • 6a1f36e8c9 incorporate feedback Francisco Javier Arceo 2025-09-05 14:50:39 -04:00
  • 30f199a8df chore(sambanova test): skip with_n tests for sambanova, it is not implemented server-side (https://docs-legacy.sambanova.ai/sambastudio/latest/open-ai-api.html\#_example_requests_using_openai_client) Matthew Farrellee 2025-09-05 11:27:20 -04:00
  • e2fe39aee1
    feat!: Migrate Vector DB IDs to Vector Store IDs (breaking change) (#3253) Francisco Arceo 2025-09-05 07:40:34 -06:00
  • 48ff83b043
    Merge branch 'main' into prompt-api Francisco Arceo 2025-09-05 07:04:16 -06:00
  • 64b2977162
    fix: Fix locations of distrubution runtime directories (#3336) Derek Higgins 2025-09-05 13:09:36 +01:00
  • aea5f81618
    Merge branch 'main' into prompt-api Francisco Arceo 2025-09-05 05:53:00 -06:00
  • 1eaf25123f fix: Fix locations of distrubution runtime directories Derek Higgins 2025-09-04 16:36:15 +01:00
  • 0b00c68d59
    fix: use lambda pattern for bedrock config env vars (#3307) Sumanth Kamenani 2025-09-05 04:45:11 -04:00
  • 14f7b0d843
    Merge branch 'main' into prompt-api Francisco Arceo 2025-09-04 21:48:57 -06:00
  • 6cbb03d6c0 fixing paths Francisco Javier Arceo 2025-09-04 23:48:02 -04:00
  • 5c02661b79 adding GET /prompts/{prompt_id}/versions Francisco Javier Arceo 2025-09-04 21:45:04 -04:00
  • 0436c4c31d Release candidate 0.0.0.dev20250905001458 rc-0.0.0.dev20250905001458 github-actions[bot] 2025-09-05 00:15:37 +00:00
  • e23481e44a test: introduce api conformance test Charlie Doern 2025-08-25 16:00:07 -04:00
  • b54f10150e
    Merge branch 'main' into resp_to_ci Ashwin Bharambe 2025-09-04 15:14:15 -07:00
  • 3a7ac4227d
    chore: unbreak inference store test (#3340) ehhuang 2025-09-04 15:13:31 -07:00
  • b40e100a17 chore: unbreak inference store test Eric Huang 2025-09-04 14:18:10 -07:00
  • 99a2529909 feat(tests): introduce a test "suite" concept to encompass dirs, options Ashwin Bharambe 2025-09-03 14:10:05 -07:00
  • 55a8c5f439
    fix: show descriptive MCP server connection errors instead of generic 500s (#3256) Sumanth Kamenani 2025-09-04 16:25:02 -04:00
  • 561d2fc6b8
    fix: Move to older version for docker container failure [fireworks-ai] (#3338) slekkala1 2025-09-04 11:47:46 -07:00
  • bcc7f2c7d0
    chore: async inference store write (#3318) ehhuang 2025-09-04 11:37:46 -07:00
  • 770c051387 fix: Move to older version for docker container failure [fireworks-ai] Swapna Lekkala 2025-09-04 11:26:54 -07:00
  • 5bbca56cfc
    fix: Make SentenceTransformer embedding operations non-blocking (#3335) Derek Higgins 2025-09-04 18:58:41 +01:00
  • 5f3425bb1b
    Merge branch 'main' into prompt-api Francisco Arceo 2025-09-04 10:57:08 -06:00
  • 8b00883abd feat: Adding OpenAI Compatible Prompts API Francisco Javier Arceo 2025-09-03 14:14:54 -04:00
  • 52afb5f9e2
    Merge branch 'main' into fix/async-embedding-blocking Francisco Arceo 2025-09-04 10:52:02 -06:00
  • 85f33762d7
    refactor(server): remove hardcoded 409 and 404 status codes in server.py using httpx constants (#3333) IAN MILLER 2025-09-04 17:15:13 +01:00
  • 64d2306dd5
    fix: distro-codegen pre-commit hook file pattern (#3337) Derek Higgins 2025-09-04 16:56:32 +01:00
  • 77bf87c4ba fix: distro-codegen pre-commit hook file pattern Derek Higgins 2025-09-04 16:15:25 +01:00
  • e9579a8032 fix: Make SentenceTransformer embedding operations non-blocking Derek Higgins 2025-09-04 12:27:58 +01:00
  • 41948027df Merge branch 'main' into bugfix/model-type melonkernel 2025-09-04 16:35:20 +03:00
  • 1b75afb10f ensure embedding models have dimensions melonkernel 2025-09-04 14:01:51 +03:00
  • 1fd5da3817 Use model type from ProviderModelEntry when listing models melonkernel 2025-09-04 12:45:58 +03:00
  • 89739301dc
    refactor(server): remove hardcoded 409 and 404 status codes in server.py using httpx constants r3v5 2025-09-04 14:16:22 +01:00
  • 5d52e0d2c5
    chore: handle missing finish_reason (#3328) ehhuang 2025-09-04 04:23:18 -07:00
  • 27a6918834 ensure embedding models have dimensions melonkernel 2025-09-04 14:01:51 +03:00
  • 2a478fb1d5 Use model type from ProviderModelEntry when listing models melonkernel 2025-09-04 12:45:58 +03:00
  • df873b8b27 chore: handle missing finish_reason Eric Huang 2025-09-03 21:54:45 -07:00
  • 93e9dfdc7d fix: auto-detect Console width Doug Edgar 2025-09-03 17:05:55 -07:00
  • 02f6e0f531
    fix(tests): set inference mode to be replay by default (#3326) Ashwin Bharambe 2025-09-03 15:57:17 -07:00
  • cd60e4d46a fix(tests): set inference mode to be replay by default Ashwin Bharambe 2025-09-03 15:38:39 -07:00
  • c3d3a0b833
    feat(tests): auto-merge all model list responses and unify recordings (#3320) Ashwin Bharambe 2025-09-03 11:33:03 -07:00
  • 48f91f596b fix tests Ashwin Bharambe 2025-09-03 11:27:21 -07:00
  • 34f5da6cdc feat(tests): auto-merge all model list responses and unify recordings Ashwin Bharambe 2025-09-03 10:27:44 -07:00
  • 5bccb37301 fix mcp connection error handling skamenan7 2025-08-26 07:52:45 -04:00
  • d0626ac535 safety, chore: async inference store write Eric Huang 2025-09-03 06:06:02 -07:00
  • d2a88550b0 fix: use lambda pattern for bedrock config env vars skamenan7 2025-09-02 16:08:01 -04:00
  • d948e63340
    chore: Improve error message for missing provider dependencies (#3315) ehhuang 2025-09-03 07:11:59 -07:00
  • c3fa3e6333 base: 35 RPS; safety, 75 RPS Eric Huang 2025-09-02 14:00:23 -07:00
  • c55e416846 Improve error message for missing provider dependencies Eric Huang 2025-09-03 05:46:43 -07:00
  • ccaf6aaa51
    chore(python-deps): replace ibm_watson_machine_learning with ibm_watsonx_ai (#3302) Cesare Pompeiano 2025-09-03 11:33:35 +02:00
  • df79784e72 Updated watsonx dependencies are-ces 2025-09-01 10:30:56 +02:00
  • 8a59cb3707 Fixed issues with metadata are-ces 2025-09-03 10:52:29 +02:00
  • c59d8c5047
    fix: Fix mock vector DB schema in Qdrant tests (#3295) Varsha 2025-09-03 00:59:16 -07:00
  • bec5ef537d chore: standardize unsupported database error Nathan Weinberg 2025-07-30 16:44:01 -04:00
  • 6ae7509a47 feat(batches, completions): add /v1/completions support to /v1/batches Matthew Farrellee 2025-09-02 16:20:00 -04:00
  • faf891b40c
    refactor: use generic WeightedInMemoryAggregator for hybrid search in SQLiteVecIndex (#3303) IAN MILLER 2025-09-02 18:38:35 +01:00
  • 7fc14dd97e tested Kai Wu 2025-09-02 10:32:37 -07:00
  • 9cf73a6bdf Update langchain-llama-stack.py Omar Abdelwahab 2025-09-02 10:30:17 -07:00
  • ad9b12a950
    Merge branch 'llamastack:main' into crewai Kai Wu 2025-09-02 09:35:26 -07:00
  • f991f9ff1c chore(api): make version prefix optional Matthew Farrellee 2025-09-02 08:57:18 -04:00