Commit graph

  • 2c52ab8944
    Merge 309f06829c into a1301911e4 melonkernel 2025-09-22 16:52:03 +02:00
  • 26a490b7fc test: convert tests to use show Charlie Doern 2025-07-31 20:14:37 -04:00
  • 2584c73295 chore: remove llama stack build Charlie Doern 2025-07-30 19:45:01 -04:00
  • 3186cca09f feat: llama stack show Charlie Doern 2025-07-30 18:55:22 -04:00
  • 41431d8bdd refactor: convert providers to be installed via package Charlie Doern 2025-07-29 15:18:54 -04:00
  • 920c2a3e12 Pin weaviate-client version ChristianZaccaria 2025-09-08 09:35:50 +01:00
  • 980c7c244d Remove Weaviate unit tests ChristianZaccaria 2025-09-03 10:34:48 +01:00
  • c630a646e3 Add remote Weaviate in precomputed embeddings test ChristianZaccaria 2025-08-29 18:39:54 +01:00
  • 65a2f09a6f Add docstring to Weaviate query_vector() ChristianZaccaria 2025-08-29 18:13:45 +01:00
  • 0cd86e696c fix(weaviate): correct score calcuation for cosine distance ChristianZaccaria 2025-08-29 18:07:44 +01:00
  • f9794f8475 fix: update Weaviate fixtures in conftest.py and improve vector DB handling ChristianZaccaria 2025-08-29 17:29:50 +01:00
  • 4541b517c8 feat: implement keyword and hybrid search for Weaviate provider ChristianZaccaria 2025-08-27 12:24:38 +01:00
  • a1301911e4
    chore(ui-deps): bump jest-environment-jsdom from 29.7.0 to 30.1.2 in /llama_stack/ui (#3509) dependabot[bot] 2025-09-22 13:57:10 +02:00
  • 3bf1c32022
    Merge be81af962a into 7c4a740a08 dependabot[bot] 2025-09-22 11:57:04 +00:00
  • 7c4a740a08
    chore(ui-deps): bump @radix-ui/react-dialog from 1.1.13 to 1.1.15 in /llama_stack/ui (#3510) dependabot[bot] 2025-09-22 13:56:58 +02:00
  • 21f7667bb7
    chore(ui-deps): bump remeda from 2.30.0 to 2.32.0 in /llama_stack/ui (#3511) dependabot[bot] 2025-09-22 13:56:43 +02:00
  • 6ce2cf3e12
    chore(github-deps): bump astral-sh/setup-uv from 6.6.1 to 6.7.0 (#3502) dependabot[bot] 2025-09-22 13:54:35 +02:00
  • e2e42c8a37
    chore: remove duplicate OpenAI and Gemini data validators (#3513) Matthew Farrellee 2025-09-22 07:53:17 -04:00
  • 0e43be36e1
    fix: handle missing API keys gracefully in model refresh (#3493) Derek Higgins 2025-09-22 12:31:30 +01:00
  • 921b76836f fix: handle missing API keys gracefully in model refresh Derek Higgins 2025-09-19 16:04:02 +01:00
  • 65c4ffca28 feat(internal): add image_url download feature to OpenAIMixin Matthew Farrellee 2025-09-22 06:56:56 -04:00
  • 1a68f6446a
    Merge a772f0a42d into sapling-pr-archive-ehhuang ehhuang 2025-09-21 20:46:41 -07:00
  • a772f0a42d chore: introduce write queue for response_store Eric Huang 2025-09-21 20:46:34 -07:00
  • 08f4a52407 merge commit for archive created by Sapling Eric Huang 2025-09-21 20:40:48 -07:00
  • c0b6c9d717 chore: introduce write queue for response_store Eric Huang 2025-09-21 20:40:25 -07:00
  • 47ed732f7e merge commit for archive created by Sapling Eric Huang 2025-09-21 20:38:07 -07:00
  • ce9a62aa84 chore: introduce write queue for response_store Eric Huang 2025-09-21 20:37:58 -07:00
  • e3f77c1004
    fix: Update inference recorder to handle both Ollama and OpenAI model (#3470) Derek Higgins 2025-09-21 14:32:39 +01:00
  • 962385d9ae chore: remove duplicate OpenAI and Gemini data validators Matthew Farrellee 2025-09-21 03:36:49 -04:00
  • 011788f899 Release candidate 0.0.0.dev20250921001616 rc-0.0.0.dev20250921001616 github-actions[bot] 2025-09-21 00:16:54 +00:00
  • 142a38db8b
    chore: remove duplicate AnthropicProviderDataValidator (#3512) Matthew Farrellee 2025-09-20 19:09:27 -04:00
  • f48e129880 chore: remove duplicate AnthropicProviderDataValidator Matthew Farrellee 2025-09-20 18:04:51 -04:00
  • 236f003f7b
    chore(ui-deps): bump remeda from 2.30.0 to 2.32.0 in /llama_stack/ui dependabot[bot] 2025-09-20 20:06:07 +00:00
  • 111e3dc96d
    chore(ui-deps): bump @radix-ui/react-dialog in /llama_stack/ui dependabot[bot] 2025-09-20 20:05:58 +00:00
  • e1f5d3641a
    chore(ui-deps): bump jest-environment-jsdom in /llama_stack/ui dependabot[bot] 2025-09-20 20:05:47 +00:00
  • 33d3041bd3
    chore(ui-deps): bump @types/node in /llama_stack/ui dependabot[bot] 2025-09-20 20:05:34 +00:00
  • 83a7639ee5
    chore(python-deps): bump huggingface-hub from 0.34.4 to 0.35.0 dependabot[bot] 2025-09-20 20:04:48 +00:00
  • fd9b7499ec
    chore(python-deps): bump datasets from 4.0.0 to 4.1.1 dependabot[bot] 2025-09-20 20:04:42 +00:00
  • 21364d2942
    chore(python-deps): bump fastapi from 0.116.1 to 0.117.0 dependabot[bot] 2025-09-20 20:04:33 +00:00
  • 82de605721
    chore(python-deps): bump weaviate-client from 4.16.9 to 4.16.10 dependabot[bot] 2025-09-20 20:04:21 +00:00
  • 2314450cee
    chore(python-deps): bump openai from 1.107.0 to 1.108.1 dependabot[bot] 2025-09-20 20:04:13 +00:00
  • cb66268755
    chore(github-deps): bump astral-sh/setup-uv from 6.6.1 to 6.7.0 dependabot[bot] 2025-09-20 20:03:52 +00:00
  • c8623607f5 Merge branch 'main' into use-openai-for-databricks Matthew Farrellee 2025-09-20 06:16:54 -04:00
  • ae804ed5a8 feat: (re-)enable Databricks inference adapter Matthew Farrellee 2025-09-20 05:05:05 -04:00
  • 6fa3e7bc18 Release candidate 0.0.0.dev20250920001414 rc-0.0.0.dev20250920001414 github-actions[bot] 2025-09-20 00:14:57 +00:00
  • 4cc3e877ff
    add getting_started_v0_3_0.ipynb Kai Wu 2025-09-19 16:38:46 -07:00
  • f44eb935c4
    chore: simplify authorized sqlstore (#3496) ehhuang 2025-09-19 16:13:56 -07:00
  • 7e1dd9c939 merge commit for archive created by Sapling Eric Huang 2025-09-19 16:13:51 -07:00
  • 04fd837d2f chore: introduce write queue for response_store Eric Huang 2025-09-19 16:13:43 -07:00
  • 2778aa1959 merge commit for archive created by Sapling Eric Huang 2025-09-19 16:02:12 -07:00
  • 7660ba844f chore: introduce write queue for response_store Eric Huang 2025-09-19 16:02:02 -07:00
  • eaadcafb6f merge commit for archive created by Sapling Eric Huang 2025-09-19 15:59:43 -07:00
  • b0115674a4 chore: introduce write queue for response_store Eric Huang 2025-09-19 15:59:36 -07:00
  • d7a22e524e
    Merge b93b7798ad into sapling-pr-archive-ehhuang ehhuang 2025-09-19 15:53:34 -07:00
  • b93b7798ad chore: introduce write queue for response_store Eric Huang 2025-09-19 15:53:26 -07:00
  • b2144db2bb merge commit for archive created by Sapling Eric Huang 2025-09-19 15:49:50 -07:00
  • f0da887e79 chore: introduce write queue for response_store Eric Huang 2025-09-19 15:49:40 -07:00
  • b4974d411d chore: simplify authorized sqlstore Eric Huang 2025-09-19 14:59:30 -07:00
  • d3600b92d1
    fix: force milvus-lite installation for inline::milvus (#3488) Sébastien Han 2025-09-19 22:12:08 +02:00
  • 41e72d7d6a push updated docs from pre-commit Yuval Turgeman 2025-09-19 13:03:47 -04:00
  • 9378bdca43
    docs: Fix incorrect vector_db_id usage in RAG tutorial (#3444) adam-d-young 2025-09-19 10:41:26 -05:00
  • 8f0413e743 improve agent metrics integration test and cleanup fixtures skamenan7 2025-09-19 10:47:16 -04:00
  • 69b692af91 feat: add agent workflow metrics collection skamenan7 2025-08-06 17:08:03 -04:00
  • c71bcd5479
    Merge branch 'main' into chroma Bwook (Byoungwook) Kim 2025-09-19 22:53:03 +09:00
  • 3baca53eba Extend OpenAIResponseInput with MCP types Yuval Turgeman 2025-09-18 16:33:25 -04:00
  • a8f42d62f0
    fix: force milvus-lite installation for inline::milvus Sébastien Han 2025-09-19 10:04:38 +02:00
  • 7fe8fd4285
    Merge bec5ef537d into 4c2fcb6b51 Nathan Weinberg 2025-09-19 09:44:11 +02:00
  • 4c2fcb6b51
    chore: refactor server.main (#3462) ehhuang 2025-09-18 21:11:13 -07:00
  • a91f07aa25 Release candidate 0.0.0.dev20250919001445 rc-0.0.0.dev20250919001445 github-actions[bot] 2025-09-19 00:15:35 +00:00
  • 83a229554b feat: allow user to register model alias explicitly, tests Eric Huang 2025-09-18 15:47:20 -07:00
  • 20fd5ff54c docs: add an AI frameworks with common OpenAI API compatibility section to AI Application Examples gabemontero 2025-08-24 20:54:23 -04:00
  • d064c9e99e ran pre-commit Omar Abdelwahab 2025-09-18 14:03:43 -07:00
  • 875069f535 Update langchain-llama-stack.py Omar Abdelwahab 2025-09-18 13:57:14 -07:00
  • 6d68ece4ef
    Merge 49b729b30a into 8422bd102a Charlie Doern 2025-09-18 17:04:04 +02:00
  • 32930868de tightened vector store embedding model validation skamenan7 2025-09-18 10:46:53 -04:00
  • 534c227058 docs: improve vector store config documentation and fix test isolation skamenan7 2025-08-13 17:13:57 -04:00
  • ecb06a0384 Fix unit test to expect correct fallback model skamenan7 2025-08-12 13:24:48 -04:00
  • aa5618a7c2 Change default embedding model to all-MiniLM-L6-v2 skamenan7 2025-08-08 16:41:17 -04:00
  • e411099cbf Replace MissingEmbeddingModelError with IBM Granite default skamenan7 2025-08-04 13:01:10 -04:00
  • 8e2675f50c Replace MissingEmbeddingModelError with IBM Granite default skamenan7 2025-08-04 13:01:10 -04:00
  • 380bd1bb7a fix: update import path from distribution to core after upstream migration skamenan7 2025-07-31 08:55:53 -04:00
  • a368f4af40 Address review comments for global vector store configuration skamenan7 2025-07-30 13:40:33 -04:00
  • f9afad99f8 docs: update configuration documentation for global default embedding model skamenan7 2025-07-30 13:20:59 -04:00
  • 600c3d5188 fix(tests): remove @pytest.mark.asyncio decorators from unit tests skamenan7 2025-07-28 09:32:24 -04:00
  • b6c69f23ad feat(vector-io): implement global default embedding model configuration (Issue #2729) skamenan7 2025-07-25 17:06:43 -04:00
  • 17fbd21c0d feat(vector-io): implement global default embedding model configuration (Issue #2729) skamenan7 2025-07-25 17:06:43 -04:00
  • 8422bd102a
    feat: combine ProviderSpec datatypes (#3378) Charlie Doern 2025-09-18 10:10:00 -04:00
  • 52503490d8
    test: add tests for model not persistant models Ignas Baranauskas 2025-08-19 11:39:00 +01:00
  • 9e79e917f6
    fix: clear model cache when run.yaml model list changes Ignas Baranauskas 2025-08-19 09:43:07 +01:00
  • 686f87d138 feat: combine ProviderSpec datatypes Charlie Doern 2025-09-08 15:51:53 -04:00
  • e66103c09d
    fix: add missing files provider to NVIDIA distribution (#3479) Jiayi Ni 2025-09-18 04:49:46 -07:00
  • ea396a54cd
    chore: update the ollama inference impl to use OpenAIMixin for openai-compat functions (#3395) Matthew Farrellee 2025-09-18 07:09:57 -04:00
  • 1f7e87c647 feat: update Cerebras inference provider to support dynamic model listing Matthew Farrellee 2025-09-18 06:34:31 -04:00
  • 521865c388
    feat: include all models from provider's /v1/models (#3471) Matthew Farrellee 2025-09-18 05:17:11 -04:00
  • 4842145202
    feat: Add dynamic authentication token forwarding support for vLLM (#3388) Akram Ben Aissi 2025-09-18 10:13:55 +01:00
  • 941aad84a7 Release candidate 0.0.0.dev20250918001422 rc-0.0.0.dev20250918001422 github-actions[bot] 2025-09-18 00:15:02 +00:00
  • da0d114145 fix: add missing files provider to nvidia distribution Jiayi 2025-09-17 16:44:21 -07:00
  • 42c23b45f6
    feat: update qdrant hash function from SHA-1 to SHA-256 (#3477) Doug Edgar 2025-09-17 15:10:10 -07:00
  • 871802f489 feat(api): level v1beta APIs Charlie Doern 2025-09-17 12:43:13 -04:00
  • 0c631412b0 feat: update qdrant hash function from SHA-1 to SHA-256 Doug Edgar 2025-09-16 16:27:42 -07:00