Commit graph

  • ea80ea63ac
    chore: Updating chunk id generation to ensure uniqueness (#2618) Francisco Arceo 2025-07-04 00:56:35 -04:00
  • 4afd619c56
    chore: Add support for vector-stores files api for Milvus (#2582) Francisco Arceo 2025-07-03 15:15:33 -04:00
  • dae1fcd3c2
    ci: let pytest run the distro server (#2586) Sébastien Han 2025-07-03 19:51:46 +02:00
  • f4950f4ef0
    fix: AccessDeniedError leads to HTTP 500 instead of error 403 (#2595) Akram Ben Aissi 2025-07-03 19:50:49 +02:00
  • 3c43a2f529
    fix: store configs (#2593) ehhuang 2025-07-03 10:07:23 -07:00
  • aa273944fd
    fix: add mcp dependency to agent provider (#2587) Sébastien Han 2025-07-03 14:59:01 +02:00
  • b246b0660e
    docs: Add quick_start.ipynb notebook equivalent of index.md Quickstart guide (#2128) Christian Zaccaria 2025-07-03 12:55:43 +01:00
  • 577ec382e1
    fix(docs): update Agents101 notebook for builtin websearch (#2591) Sumanth Kamenani 2025-07-03 05:14:51 -04:00
  • 040424acf5
    docs: update full list of providers with matched APIs and dockerhub images (#2452) Wen Zhou 2025-07-03 10:12:56 +02:00
  • 5b07755556
    docs: Minor spelling fix (#2592) Nate Harada 2025-07-02 17:26:51 -07:00
  • 4d0d2d685f
    fix: Set parameter usedforsecurity=False when calling hashlib.md5 in order to fix rag_tool.insert on FIPS clusters (#2577) Jorge 2025-07-02 12:07:05 +02:00
  • fc735a414e
    test: Add one-step integration testing with server auto-start (#2580) ehhuang 2025-07-01 14:48:46 -07:00
  • 958600a5c1
    fix: update zero_to_hero package and README (#2578) Wen Zhou 2025-07-01 20:08:55 +02:00
  • d165000bbc
    docs: specify the ability to train non-Llama models (#2573) Nathan Weinberg 2025-07-01 09:59:06 -04:00
  • 25268854bc
    fix: allow default empty vars for conditionals (#2570) Sébastien Han 2025-07-01 14:42:05 +02:00
  • faaeccc6fd
    docs: update external provider guide and navigation (#2567) Nathan Weinberg 2025-07-01 03:42:32 -04:00
  • 0066135944
    chore: Enabling VectorIO Integration tests for Milvus (#2546) Francisco Arceo 2025-06-30 22:49:59 -04:00
  • 5785ccda35
    fix: Fixing Milvus sample config and updating documentation (#2568) Francisco Arceo 2025-06-30 22:25:23 -04:00
  • f6d91f45ba
    fix: update zero-to-hero guide for modern llama stack (#2555) Matthew Farrellee 2025-06-30 21:09:33 -04:00
  • 13aa367c8a
    fix: default api_key from env must be a SecretStr (#2565) Matthew Farrellee 2025-06-30 21:08:44 -04:00
  • ba9acce93b
    docs: fixed incorrect API list item (#2566) Nathan Weinberg 2025-06-30 21:08:19 -04:00
  • b333a3c03a
    fix(ollama): Download remote image URLs for Ollama (#2551) Ashwin Bharambe 2025-06-30 20:36:11 +05:30
  • c9a49a80e8
    docs: auto generated documentation for providers (#2543) Sébastien Han 2025-06-30 15:13:20 +02:00
  • 8d8e90d78e
    fix: add missing argument and methods (#2550) Sébastien Han 2025-06-30 14:55:37 +02:00
  • be9bf68246
    feat: Add webmethod for deleting openai responses (#2160) Krzysztof Malczuk 2025-06-30 10:28:02 +01:00
  • 6fa5271807
    docs: update document since container is not an option for "llama stack run" + update docs with current "usage" (#2531) Wen Zhou 2025-06-30 07:32:07 +02:00
  • dc1b4a84c3
    chore(github-deps): bump astral-sh/setup-uv from 6.3.0 to 6.3.1 (#2548) dependabot[bot] 2025-06-29 13:55:32 -04:00
  • 21669b14e7
    fix(docs): add setuptools explicitly (#2547) Ashwin Bharambe 2025-06-28 08:14:25 +05:30
  • 709eb7da33 build: Bump version to 0.2.13 github-actions[bot] 2025-06-27 23:56:14 +00:00
  • cc19b56c87
    chore: OpenAI compatibility for Milvus (#2470) Francisco Arceo 2025-06-27 17:00:36 -06:00
  • 65b4fae51d
    fix: proper checkpointing logic for HF trainer (#2429) Charlie Doern 2025-06-27 17:36:25 -04:00
  • 03e61e3fcc
    fix: ValueError in faiss vector database serialization (resolves #2519) (#2526) Ramakrishna Reddy Yekulla 2025-06-28 00:04:52 +05:30
  • 7cb5d3c60f
    chore: standardize unsupported model error #2517 (#2518) Rohan Awhad 2025-06-27 14:26:58 -04:00
  • 9baa16e498
    fix(security): Upgrade protobuf and aiohttp. Fixes CVE-2025-4565 (#2541) Yuan Tang 2025-06-27 09:58:38 -04:00
  • e7eb9f9adc
    fix: dataset metadata without provider_id (#2527) Juanma 2025-06-27 14:51:29 +02:00
  • 40fdce79b3
    fix(security): Upgrade urllib3 to v2.5.0. Fixes CVE-2025-50181 and CVE-2025-50182 (#2534) Yuan Tang 2025-06-27 04:46:47 -04:00
  • 8c3f2762fb
    build: update temp. created Containerfile (#2492) Wen Zhou 2025-06-27 10:23:12 +02:00
  • 0ddb293d77
    docs: Add recent releases to CHANGELOG.md (#2533) Yuan Tang 2025-06-26 23:04:13 -04:00
  • 0883944bc3
    fix: Some missed env variable changes from PR 2490 (#2538) Ben Browning 2025-06-26 20:59:15 -04:00
  • eb01a3f1c5
    ci: vector_io provider integration tests (#2537) Hardik Shah 2025-06-26 17:04:32 -07:00
  • 68d8f2186f
    fix: fix test of root span to match what is being set (#2494) grs 2025-06-26 16:41:35 +01:00
  • dbdc811d16
    chore: isolate bare minimum project dependencies (#2282) Sébastien Han 2025-06-26 10:14:27 +02:00
  • 43c1f39bd6
    refactor(env)!: enhanced environment variable substitution (#2490) Sébastien Han 2025-06-26 04:50:08 +02:00
  • 36d70637b9
    fix: finish conversion to StrEnum (#2514) Sébastien Han 2025-06-26 04:31:26 +02:00
  • ac5fd57387
    chore: remove nested imports (#2515) Sébastien Han 2025-06-26 04:31:05 +02:00
  • 2d9fd041eb
    fix: annotations list and web_search_preview in Responses (#2520) Ben Browning 2025-06-25 22:29:33 -04:00
  • 1d3f27fe5b
    fix: resume responses with tool call output (#2524) ehhuang 2025-06-25 14:43:37 -07:00
  • 82f13fe83e
    feat: Add ChunkMetadata to Chunk (#2497) Francisco Arceo 2025-06-25 13:55:23 -06:00
  • fa0b0c13d4
    fix: Ollama should be optional in starter distro (#2482) Ben Browning 2025-06-25 09:54:00 -04:00
  • cfee63bd0d
    feat: Add search_mode support to OpenAI vector store API (#2500) Varsha 2025-06-24 17:38:47 -07:00
  • 114946ae88
    chore: fix build script bug (#2507) ehhuang 2025-06-24 12:05:22 -07:00
  • 450ed920d6
    chore: do not build on auth ci test (#2505) Sébastien Han 2025-06-24 17:38:33 +02:00
  • 73c18feac4
    fix: update the signature of openai_list_files_in_vector_store in all VectorIO impls (#2503) Ashwin Bharambe 2025-06-24 18:55:56 +05:30
  • 7fa8f23555
    fix(ui): ensure initial data fetch only happens once (#2486) ehhuang 2025-06-24 03:22:55 -07:00
  • 9c8be89fb6
    chore: bump python supported version to 3.12 (#2475) Sébastien Han 2025-06-24 05:52:04 +02:00
  • d797f9aec1
    fix: #2495 FileNotFound Err in container image (#2498) Rohan Awhad 2025-06-23 23:38:08 -04:00
  • 929ac618ce
    chore(github-deps): bump astral-sh/setup-uv from 6.0.1 to 6.3.0 (#2488) dependabot[bot] 2025-06-23 11:21:06 +02:00
  • 6fde601765
    chore: upgrade hf hub dependency (#2487) ehhuang 2025-06-20 15:50:54 -07:00
  • 23b7dc7b37
    fix: stack build (#2485) ehhuang 2025-06-20 15:15:43 -07:00
  • d70573bd47 build: Bump version to 0.2.12 github-actions[bot] 2025-06-20 21:06:17 +00:00
  • d3b60507d7
    feat: support auth attributes in inference/responses stores (#2389) ehhuang 2025-06-20 10:24:45 -07:00
  • 7930c524f9
    docs: Fix spacing (#2481) Costa Shulyupin 2025-06-20 14:21:58 +03:00
  • 6832e8a658
    feat: remove score_threshold constraint (#2479) ehhuang 2025-06-19 20:47:42 -07:00
  • 747e594680
    feat: expand set of known gemini models (#2471) Eran Cohen 2025-06-19 19:19:37 +03:00
  • f394c7f2d9
    feat: Add missing Vector Store Files API surface (#2468) Ben Browning 2025-06-19 11:08:24 -04:00
  • a2f054607d
    fix: cancel scheduler tasks on shutdown (#2130) Ihar Hrachyshka 2025-06-19 11:01:33 -04:00
  • c20388c424
    ci: add python package build test (#2457) Sébastien Han 2025-06-19 15:27:32 +02:00
  • fa1d986f72
    fix: remove asyncio.TimeoutError since Python update (#2476) Sébastien Han 2025-06-19 15:22:41 +02:00
  • 6039d922c0
    fix: allow running vector tests with embedding dimension (#2467) Sébastien Han 2025-06-19 09:59:04 +02:00
  • d12f195f56
    feat: drop python 3.10 support (#2469) Charlie Doern 2025-06-19 02:37:14 -04:00
  • db2cd9e8f3
    feat: support filters in file search (#2472) ehhuang 2025-06-18 21:50:55 -07:00
  • fd37a50e6a
    chore: Remove @booxter from triagers (#2473) Ihar Hrachyshka 2025-06-18 22:30:09 -04:00
  • e6bfc717cb
    feat(ui): add infinite scroll pagination to chat completions/responses logs table (#2466) ehhuang 2025-06-18 15:28:39 -07:00
  • 90d03552d4
    feat: To add health check for faiss inline vector_io provider (#2319) Sumit Jaiswal 2025-06-18 21:26:25 +05:30
  • 7d812e3bf0 build: Bump version to 0.2.11 github-actions[bot] 2025-06-17 19:08:17 +00:00
  • 822307e6d5
    fix: Do not throw when listing vector stores (#2460) Hardik Shah 2025-06-17 11:19:43 -07:00
  • 53ac8532e4
    fix: clarify bash requirement in install flow (#2450) Dalton Flanagan 2025-06-17 03:33:28 -04:00
  • 94fcfb5674
    fix: broken links on nvidia distro docs when rendered (#2446) Ben Browning 2025-06-17 03:32:13 -04:00
  • 15f630e5da
    feat: support pagination in inference/responses stores (#2397) ehhuang 2025-06-16 22:43:35 -07:00
  • 6f1a935365
    chore: Add OpenAI compatiblity for vLLM embeddings (#2448) Varsha 2025-06-16 16:06:05 -07:00
  • 40e2c97915
    feat: Add Nvidia e2e beginner notebook and tool calling notebook (#1964) Jash Gulabrai 2025-06-16 11:29:01 -04:00
  • 436c7aa751
    feat: Add url field to PaginatedResponse and populate it using route … (#2419) Rohan Awhad 2025-06-16 05:19:48 -04:00
  • 985d0b156c
    feat: Add suffix to openai_completions (#2449) Hardik Shah 2025-06-13 16:06:06 -07:00
  • 2e8054bede
    feat: Implement hybrid search in SQLite-vec (#2312) Varsha 2025-06-13 12:54:06 -07:00
  • 941f505eb0
    feat: File search tool for Responses API (#2426) Ben Browning 2025-06-13 14:32:48 -04:00
  • 554ada57b0
    chore: Add OpenAI compatibility for Ollama embeddings (#2440) Francisco Arceo 2025-06-13 12:28:51 -06:00
  • e2e15ebb6c
    feat(auth): allow token to be provided for use against jwks endpoint (#2394) grs 2025-06-13 04:13:41 -04:00
  • ddaee42650
    test: Update integration-tests.yml (#2443) Hardik Shah 2025-06-13 01:04:08 -07:00
  • fef670b024
    feat: update openai tests to work with both clients (#2442) Hardik Shah 2025-06-12 16:30:23 -07:00
  • 0bc1747ed8
    feat: update search for vector_stores (#2441) Hardik Shah 2025-06-12 15:34:22 -07:00
  • 35c2817d0a
    fix(weaviate): handle case where distance is 0 by setting score to infinity (#2415) Ibrahim Haroon 2025-06-12 11:23:59 -04:00
  • eb04731750
    ci: fix external provider test (#2438) Sébastien Han 2025-06-12 16:14:32 +02:00
  • de37a04c3e
    fix: set appropriate defaults for params (#2434) Hardik Shah 2025-06-11 17:30:34 -07:00
  • d55100d9b7
    feat: OpenAIVectorIOMixin for vector_stores common logic (#2427) Hardik Shah 2025-06-11 15:40:57 -07:00
  • 4e37b49cdc
    fix: #1867 InferenceRouter has no attribute formatter (#2422) Rohan Awhad 2025-06-11 12:14:41 -04:00
  • 5ac43268e8
    feat: Add OpenAI compat /v1/vector_store APIs (#2423) Hardik Shah 2025-06-10 13:07:39 -07:00
  • ee57e58f29
    fix: loosen tool call checks in inference store (#2420) Ben Browning 2025-06-10 08:45:55 -04:00
  • 5639ad7466
    docs: Add recent releases (#2424) Yuan Tang 2025-06-09 22:13:02 -05:00
  • f6718b2408
    fix(security): Upgrade requests to 2.32.4. Fixes CVE-2024-47081 (#2425) Yuan Tang 2025-06-09 22:03:28 -05:00
  • 28ca00d0d9
    fix(pgvector): handle case where distance is 0 by setting score to infinity (#2416) Ibrahim Haroon 2025-06-07 16:31:30 -04:00