Commit graph

  • 9e3ae50306
    feat(server): construct the stack in a persistent event loop (#2818) Ashwin Bharambe 2025-07-18 10:29:19 -07:00
  • 2bb9039173
    docs: fix steps in the Quick Start Guide (#2800) Nathan Weinberg 2025-07-18 12:08:46 -04:00
  • e45543f7f3
    test: Measure and track code coverage (#2636) Christian Zaccaria 2025-07-18 18:08:36 +02:00
  • 1785a6b39c
    docs: add virtualenv instructions for running starter distro (#2780) Nathan Weinberg 2025-07-18 12:07:43 -04:00
  • 0eb0583cdf
    fix: amend integration test workflow (#2812) Charlie Doern 2025-07-18 09:23:36 -04:00
  • fe6af7dc8b
    chore(test): migrate unit tests from unittest to pytest nvidia test f… (#2794) Mustafa Elbehery 2025-07-18 12:32:19 +02:00
  • b78b8e1486
    chore: add mypy inference parallel utils (#2670) Mustafa Elbehery 2025-07-18 12:01:10 +02:00
  • ca7edcd6a4
    chore(api): add mypy coverage to chat_format (#2654) Mustafa Elbehery 2025-07-18 11:56:53 +02:00
  • 75480b01b8
    chore(test): migrate unit tests from unittest to pytest for system prompt (#2789) Mustafa Elbehery 2025-07-18 11:54:02 +02:00
  • 3cdf748a8e
    chore(test): migrate unit tests from unittest to pytest for nvidia datastore (#2790) Mustafa Elbehery 2025-07-18 11:52:47 +02:00
  • 55713abe7d
    chore(test): migrate unit tests from unittest to pytest nvidia test p… (#2792) Mustafa Elbehery 2025-07-18 11:49:45 +02:00
  • d7cc38e934
    fix: remove async test markers (fix pre-commit) (#2808) Charlie Doern 2025-07-18 00:35:28 -04:00
  • d64e096c5f
    fix(cli): image name should not default to CONDA_DEFAULT_ENV (#2806) Ashwin Bharambe 2025-07-17 16:40:35 -07:00
  • 910b017680
    chore: block asyncio marks in tests (#2744) Matthew Farrellee 2025-07-17 19:33:30 -04:00
  • bd8a3ae3cc
    chore(test): migrate unit tests from unittest to pytest for prompt adapter (#2788) Mustafa Elbehery 2025-07-18 01:31:38 +02:00
  • 3ae4aeb344
    test: add some tests for Telemetry API (#2787) ehhuang 2025-07-17 16:20:51 -07:00
  • 73868ce9e3
    chore(test): migrate unit tests from unittest to pytest for server en… (#2795) Mustafa Elbehery 2025-07-18 01:20:12 +02:00
  • 477bcd4d09
    feat: allow dynamic model registration for nvidia inference provider (#2726) Matthew Farrellee 2025-07-17 15:11:30 -04:00
  • 57745101be
    chore: internal change, make Model.provider_model_id non-optional (#2690) Matthew Farrellee 2025-07-17 11:26:57 -04:00
  • c2b64dce5b
    fix: Move sentence-transformers to the top (#2703) Derek Higgins 2025-07-17 15:31:30 +01:00
  • 51b179e1c5
    chore: update k8s template (#2786) ehhuang 2025-07-16 15:07:26 -07:00
  • b57db11bed
    feat: create dynamic model registration for OpenAI and Llama compat remote inference providers (#2745) IAN MILLER 2025-07-16 17:49:38 +01:00
  • 6c516d391b
    fix: de-clutter llama stack run logs (#2783) Charlie Doern 2025-07-16 12:44:26 -04:00
  • 919ee3199b
    docs: add missing bold title to match others (#2782) Nathan Weinberg 2025-07-16 12:05:48 -04:00
  • 30be1fd8b7
    fix: SQLiteVecIndex.create(..., bank_id="test_bank.123") - bank_id with a dot - leads to sqlite3.OperationalError (#2770) (#2771) Sergey Yedrikov 2025-07-16 11:25:44 -04:00
  • 72e606355d
    fix: add shutdown function for localfs provider (#2781) Nathan Weinberg 2025-07-16 11:24:57 -04:00
  • 3165197b75
    chore: remove 'gha_workflow_llama_stack_tests.yml' (#2767) Nathan Weinberg 2025-07-16 10:12:26 -04:00
  • a3e249807b
    chore: remove vision model URL workarounds and simplify client creation (#2775) Matthew Farrellee 2025-07-16 10:10:04 -04:00
  • fa1bb9ae00
    docs: fix typo and link self loop for index.html#running-tests (#2777) IAN MILLER 2025-07-16 15:09:44 +01:00
  • ff9d4d8a9d
    ci: do not pull model (#2776) Sébastien Han 2025-07-16 13:58:05 +02:00
  • f85189022c
    fix: re-hydrate requirement and fix package (#2774) Sébastien Han 2025-07-16 11:46:15 +02:00
  • 95fdc8ea94 build: Bump version to 0.2.15 Ashwin Bharambe 2025-07-15 20:29:08 -07:00
  • b096794959
    docs: Reorganize documentation on the webpage (#2651) Kelly Brown 2025-07-15 17:19:35 -04:00
  • e1755d1ed2
    chore: Adding OpenAI Vector Stores Files API compatibility for PGVector (#2755) Francisco Arceo 2025-07-15 15:46:49 -04:00
  • e64e4fc5a2
    test: add tests against published client (#2752) ehhuang 2025-07-15 12:25:31 -07:00
  • 65fcd03461
    docs: update outdated llama stack client documentation (#2758) Mark Campbell 2025-07-15 19:49:59 +01:00
  • b3d86ca926
    fix: stop image_name from being cast to an integer (#2759) Nathan Weinberg 2025-07-15 12:44:21 -04:00
  • 31b088978a
    fix: Fix /vector-stores/create API when vector store with duplicate name (#2617) Francisco Arceo 2025-07-15 11:24:41 -04:00
  • 5400a2e2b1
    chore: remove tests.yaml (#2754) ehhuang 2025-07-14 22:02:37 -07:00
  • 4ae5656c2f
    feat: Implement keyword search in milvus (#2231) Varsha 2025-07-14 16:39:55 -07:00
  • 33f0d83ad3
    chore: Move vector store kvstore implementation into openai_vector_store_mixin.py (#2748) Francisco Arceo 2025-07-14 18:10:35 -04:00
  • 6b8a8c1be9
    fix: Safety in starter (#2731) Hardik Shah 2025-07-14 15:07:40 -07:00
  • 6ad22c209f
    chore: add issue template for technical debt (#2753) Nathan Weinberg 2025-07-14 17:41:44 -04:00
  • aa0840c281
    docs: fix building distro link (#2750) ehhuang 2025-07-14 12:06:56 -07:00
  • f731f369a2
    feat: add infrastructure to allow inference model discovery (#2710) Matthew Farrellee 2025-07-14 14:38:53 -04:00
  • a7ed86181c
    fix(faiss): Delete file contents from kvstore (#2686) Derek Higgins 2025-07-14 18:58:23 +01:00
  • 77d2c8e95d
    docs: clarify run.yaml files are starting points for customization (#2746) Sumanth Kamenani 2025-07-14 12:53:13 -04:00
  • 618ccea090
    feat: add input validation for search mode of rag query config (#2275) Mark Campbell 2025-07-14 14:11:34 +01:00
  • 958fc92b1b
    feat: Add Vector stores UI (#2737) Francisco Arceo 2025-07-13 04:03:55 -04:00
  • 68e7978c88
    chore: block network access from unit tests (#2732) Matthew Farrellee 2025-07-12 19:53:54 -04:00
  • 8374d4cefd
    chore(github-deps): bump medyagh/setup-minikube from 0.0.19 to 0.0.20 (#2738) dependabot[bot] 2025-07-12 16:23:42 -04:00
  • 51d9fd4808
    fix: Don't cache clients for passthrough auth providers (#2728) Ben Browning 2025-07-11 16:38:27 -04:00
  • aa2595c7c3
    fix: sambanova shields and model validation (#2693) Jorge Piedrahita Ortiz 2025-07-11 15:29:15 -05:00
  • 30b2e6a495
    chore: default to pytest asyncio-mode=auto (#2730) Matthew Farrellee 2025-07-11 16:00:24 -04:00
  • 2ebc172f33
    fix: pin opentelemtry version (#2722) Sébastien Han 2025-07-11 16:25:51 +02:00
  • 2e4eedce14
    fix: container build on podman (#2723) Sébastien Han 2025-07-11 16:25:33 +02:00
  • d880c2df0e
    fix: auth sql store: user is owner policy (#2674) ehhuang 2025-07-10 14:40:32 -07:00
  • 4cf1952c32
    chore: update vllm k8s command to support tool calling (#2717) ehhuang 2025-07-10 14:40:17 -07:00
  • 5fe3027cbf
    chore: remove "rfc" directory and move original rfc to "docs" (#2718) Nathan Weinberg 2025-07-10 17:06:10 -04:00
  • 9f04bc6d1a
    chore: move "install.sh" script into "scripts" dir (#2719) Nathan Weinberg 2025-07-10 16:14:10 -04:00
  • 0bbff91c7e
    docs: fix a few broken things in the CONTRIBUTING.md (#2714) Nathan Weinberg 2025-07-10 14:47:54 -04:00
  • 6a6b66ae4f
    chore: Adding unit tests for OpenAI vector stores and migrating SQLite-vec registry to kvstore (#2665) Francisco Arceo 2025-07-10 14:22:13 -04:00
  • b18f4d1ccf
    ci: add config for pre-commit.ci (#2712) Nathan Weinberg 2025-07-10 11:24:10 -04:00
  • 83c6b20067
    chore(api): add mypy coverage to cli/stack (#2650) Mustafa Elbehery 2025-07-10 16:53:38 +02:00
  • bbe0199bb7
    chore: update pre-commit hook versions (#2708) Nathan Weinberg 2025-07-10 10:47:59 -04:00
  • 81ebaf6e9a
    fix: properly represent paths in server logs (#2698) Charlie Doern 2025-07-10 10:19:12 -04:00
  • 01c222e12f
    ci: run all APIs integration tests (#2646) Sébastien Han 2025-07-10 15:16:08 +02:00
  • 81109a0f72
    test: terminate server process when finished (#2700) ehhuang 2025-07-09 20:59:37 -07:00
  • 780b4c6eea
    fix: llama stack run starter in conda (#2679) ehhuang 2025-07-09 20:33:45 -07:00
  • 7915551eee
    build: replace "python-jose" with "python-jose[cryptography]" (#2695) Nathan Weinberg 2025-07-09 16:21:57 -04:00
  • 1d8c00635c
    chore: Update CODEOWNERS (#2692) Matthew Farrellee 2025-07-09 11:19:31 -04:00
  • 9b7eecebcf
    ci: test safety with starter (#2628) Sébastien Han 2025-07-09 16:53:50 +02:00
  • de01eefdef
    chore: add mypy post training (#2675) Mustafa Elbehery 2025-07-09 15:44:39 +02:00
  • dafd9ed5c0
    docs: Update links to Android Demo App (#2687) Jorge 2025-07-09 15:41:57 +02:00
  • cd0ad21111
    chore(api): add mypy coverage to apis (#2648) Mustafa Elbehery 2025-07-09 12:55:16 +02:00
  • 297cd8e0db
    fix: runpod transition to python 3.12 (#2682) Sébastien Han 2025-07-09 12:27:42 +02:00
  • 7f3661e7d8
    chore: add mypy loader (#2672) Mustafa Elbehery 2025-07-09 10:26:33 +02:00
  • a5c3362bcd
    chore(api): add mypy coverage to meta_reference_config (#2664) Mustafa Elbehery 2025-07-09 10:24:30 +02:00
  • 28343fea51
    chore(api): add mypy coverage to meta_reference_safety (#2661) Mustafa Elbehery 2025-07-09 10:22:34 +02:00
  • d39660afed
    fix(remote:milvus): add missing files_api parameter and kvstore configuration (#2630) pgustafs 2025-07-09 10:08:14 +02:00
  • 2d3d9664a7
    chore(api): add mypy coverage to prompts (#2657) Mustafa Elbehery 2025-07-09 10:07:00 +02:00
  • 84fa83b788
    fix: update k8s templates (#2645) ehhuang 2025-07-08 15:57:01 -07:00
  • daf660c4ea
    feat(auth,ui): support github sign-in in the UI (#2545) ehhuang 2025-07-08 11:02:57 -07:00
  • c8bac888af
    feat(auth): support github tokens (#2509) ehhuang 2025-07-08 11:02:36 -07:00
  • 83c89265e0
    chore: Adding unit tests for Milvus and OpenAI compatibility (#2640) Francisco Arceo 2025-07-08 03:50:16 -04:00
  • 27b3cd570f
    fix: use --template flag for server (#2643) Charlie Doern 2025-07-08 03:48:50 -04:00
  • e9926564bd
    fix: authorized sql store with postgres (#2641) ehhuang 2025-07-07 19:36:34 -07:00
  • 5bb3817c49
    fix: Restore the nvidia distro (#2639) Ben Browning 2025-07-07 18:50:05 -04:00
  • d0ec5c3d3a
    fix: print proper template path upon build (#2642) Charlie Doern 2025-07-07 18:39:39 -04:00
  • 5561f1c36d
    ci: error when a pipefails (#2635) Sébastien Han 2025-07-07 16:47:30 +02:00
  • 4bca4af3e4
    refactor: set proper name for embedding all-minilm:l6-v2 and update to use "starter" in detailed_tutorial (#2627) Wen Zhou 2025-07-06 05:37:37 +02:00
  • 2faec38724
    chore(deps): bump next from 15.3.2 to 15.3.3 in /llama_stack/ui (#2632) dependabot[bot] 2025-07-05 00:13:33 -04:00
  • c025cab3a3
    docs: update docs to use "starter" than "ollama" (#2629) Wen Zhou 2025-07-05 05:14:57 +02:00
  • dc7df60d42
    docs: Update starter docs to include milvus inline (#2631) Francisco Arceo 2025-07-04 23:13:39 -04:00
  • ea966565f6
    feat: improve telemetry (#2590) Sébastien Han 2025-07-04 17:29:09 +02:00
  • 4eae0cbfa4
    fix(starter): Add missing faiss provider to build.yaml vector_io section (#2625) Derek Higgins 2025-07-04 16:28:57 +01:00
  • df6ce8befa
    fix: only load mcp when enabled in tool_group (#2621) Sébastien Han 2025-07-04 16:57:05 +02:00
  • c4349f532b
    feat: consolidate most distros into "starter" (#2516) Sébastien Han 2025-07-04 15:58:03 +02:00
  • f77d4d91f5
    fix: handle encoding errors when adding files to vector store (#2574) Derek Higgins 2025-07-04 11:10:18 +01:00
  • f1c62e0af0 build: Bump version to 0.2.14 Ashwin Bharambe 2025-07-04 12:12:12 +05:30