Commit graph

  • c79cc92b37 Update PR Template to be much more succinct Ashwin Bharambe 2025-02-06 15:57:22 -08:00
  • e964ec95e9
    docs: Correct typos in Zero to Hero guide (#997) Maxime Lecanu 2025-02-06 23:29:52 +01:00
  • a84e7669f0
    feat: Add a new template for dell (#978) Hardik Shah 2025-02-06 14:14:39 -08:00
  • dd1265bea7
    ci: Add semantic PR title check (#979) Yuan Tang 2025-02-06 15:22:34 -05:00
  • 21f763c4f3 Reduce noise from PR templates further Ashwin Bharambe 2025-02-06 11:02:53 -08:00
  • 0a0ee5ca96
    Fix incorrect handling of chat completion endpoint in remote::vLLM (#951) Yuan Tang 2025-02-06 13:45:19 -05:00
  • 09ed0e9c9f
    Add Kubernetes deployment guide (#899) Yuan Tang 2025-02-06 13:28:02 -05:00
  • a25e3b405c
    docs: Add license badge to README.md (#994) Yuan Tang 2025-02-06 13:22:02 -05:00
  • a764b823ee
    docs: use uv in CONTRIBUTING guide (#970) Sébastien Han 2025-02-06 19:21:27 +01:00
  • 403292fcf6
    test: replace memory with vector_io fixture (#984) Sébastien Han 2025-02-06 19:12:59 +01:00
  • f5e4bf2edf
    chore: remove unused argument (#987) Charlie Doern 2025-02-06 13:05:35 -05:00
  • 42c10da1c3
    github: update PR template to use correct syntax to auto-close issues (#989) Ihar Hrachyshka 2025-02-06 12:59:26 -05:00
  • 610de1ba05
    chore: update PR template to reinforce changelog (#988) Sébastien Han 2025-02-06 18:58:30 +01:00
  • 3922999118
    sys_prompt support in Agent (#938) ehhuang 2025-02-05 21:11:32 -08:00
  • e777d965a1
    docs: add addn server guidance for Linux users in Quick Start (#972) Nathan Weinberg 2025-02-05 23:57:51 -05:00
  • f4343f7dc0
    docs: clarify host.docker.internal works for recent podman (#977) Ihar Hrachyshka 2025-02-05 19:02:05 -05:00
  • 8fa642835b
    Fix README.md notebook links (#976) Aakanksha Duggal 2025-02-05 17:33:46 -05:00
  • 2d9c8b549e
    docs: missing T in import (#974) Ryan Cook 2025-02-05 17:06:39 -05:00
  • d9c0b4e3ba
    [docs] update the zero_to_hero_guide llama stack version to 0.1.0 (#960) Kamesh Akella 2025-02-05 14:49:26 -05:00
  • a79a083e39
    Fix broken pgvector provider and memory leaks (#947) Yuan Tang 2025-02-05 12:32:05 -05:00
  • 5c8e35a9e2
    docs, tests: replace datasets.rst with memory_optimizations.rst (#968) Ihar Hrachyshka 2025-02-05 11:25:56 -05:00
  • 529708215c
    [docs] Make RAG example self-contained (#962) Ihar Hrachyshka 2025-02-04 19:22:50 -05:00
  • 474c4bdd7a
    Make a couple properties optional (#963) Ashwin Bharambe 2025-02-04 16:20:24 -08:00
  • 0cbb3e401c
    docs: miscellaneous small fixes (#961) Ihar Hrachyshka 2025-02-04 18:31:30 -05:00
  • b84ab6c6b8
    github: issue templates automatically apply relevant label (#956) Nathan Weinberg 2025-02-04 17:44:03 -05:00
  • b0dec797a0
    Add Podman instructions to Quick Start (#957) Bill Murdock 2025-02-04 17:37:02 -05:00
  • d67401c644 Several documentation fixes and fix link to API reference Ashwin Bharambe 2025-02-04 14:00:27 -08:00
  • 26aef50bc5
    if client.initialize fails, the example should exit (#954) Charlie Doern 2025-02-04 16:54:21 -05:00
  • 981bb52b59 Quote the token properly Ashwin Bharambe 2025-02-04 11:44:29 -08:00
  • 5005939494 Use a secret again for the workflow Ashwin Bharambe 2025-02-04 11:42:47 -08:00
  • 7392daddee Try a new webhook Ashwin Bharambe 2025-02-04 11:36:54 -08:00
  • 2987fb37c3 fixes? Ashwin Bharambe 2025-02-04 11:23:11 -08:00
  • 766b11f1f8 Debug workflow Ashwin Bharambe 2025-02-04 11:09:16 -08:00
  • 5233666143 Debug workflow Ashwin Bharambe 2025-02-04 11:07:04 -08:00
  • b35930a7e5 rename Ashwin Bharambe 2025-02-04 11:02:45 -08:00
  • ea538e4b32 Add a workflow to trigger readthedocs rebuild Ashwin Bharambe 2025-02-04 11:02:06 -08:00
  • b17277b06a Fix the OpenAPI HTML Ashwin Bharambe 2025-02-04 10:38:49 -08:00
  • c9ab72fa82
    Support sys_prompt behavior in inference (#937) ehhuang 2025-02-03 23:35:16 -08:00
  • 62cd3c391e notebook point to github as source of truth Xi Yan 2025-02-03 15:08:25 -08:00
  • 753a1aa7bc Update colab link to be pointing back to github source Ashwin Bharambe 2025-02-03 15:00:21 -08:00
  • aefd5bb619 Test notebook update Ashwin Bharambe 2025-02-03 14:59:06 -08:00
  • a251566f92
    [docs] typescript sdk readme (#946) Xi Yan 2025-02-03 14:30:42 -08:00
  • 7a72082cdd
    fix: formatting for ollama note in Quick Start doc (#945) v0.1.2rc1 Nathan Weinberg 2025-02-03 17:13:57 -05:00
  • f98efe68c9
    Misc fixes (#944) Ashwin Bharambe 2025-02-03 14:08:47 -08:00
  • 0f14378135
    fix: broken "core concepts" link in docs website (#940) Nathan Weinberg 2025-02-03 16:46:34 -05:00
  • 1e36721686
    fix: broken link in Quick Start doc (#943) Nathan Weinberg 2025-02-03 16:45:35 -05:00
  • fd367e20c8
    github: ignore non-hidden python virtual environments (#939) Nathan Weinberg 2025-02-03 14:53:05 -05:00
  • 7558678b8c
    Fix uv pip install timeout issue for PyTorch (#929) Yuan Tang 2025-02-03 09:39:35 -05:00
  • e370a77752
    Add issue template config with docs and Discord links (#930) Yuan Tang 2025-02-03 09:39:00 -05:00
  • 9e0c8a82cb Litellm support in llama stack: ak/llama-stack-litellm-support Abhishek Kumawat 2025-02-03 06:10:51 -08:00
  • 83a51c7bfb
    Properly close PGVector DB connection during shutdown() (#931) Yuan Tang 2025-02-03 00:23:13 -05:00
  • ccf0cbb903 Update release pointer Ashwin Bharambe 2025-02-02 12:11:57 -08:00
  • 1bb74d95ad Delete CI workflows from here since they have moved to llama-stack-ops Ashwin Bharambe 2025-02-02 10:21:57 -08:00
  • 587753da2f
    LocalInferenceImpl update for LS 0.1 (#911) Jeff Tang 2025-02-02 09:49:40 -08:00
  • 7fdbd5b642 Add NBVAL skips to the getting started notebook Ashwin Bharambe 2025-02-02 07:53:07 -08:00
  • dfd6461498 kill old readme Ashwin Bharambe 2025-02-02 06:49:01 -08:00
  • 34ab7a3b6c
    Fix precommit check after moving to ruff (#927) Yuan Tang 2025-02-02 09:46:45 -05:00
  • 4773092dd1
    Fix UBI9 image build when installing Python packages via uv (#926) Yuan Tang 2025-02-01 22:14:29 -05:00
  • 3b8d6578d0 Bump version to 0.1.1 v0.1.1 github-actions[bot] 2025-02-02 02:16:26 +00:00
  • 75abe48cd0 completions can randomly blurt out something else v0.1.1rc4 Ashwin Bharambe 2025-02-01 16:01:21 -08:00
  • b03e093e80 Add a COPY option for copying source files into docker Ashwin Bharambe 2025-02-01 15:35:38 -08:00
  • 942e8b96ac Fix uv pip uninstall Ashwin Bharambe 2025-02-01 11:42:17 -08:00
  • e21c8b6d80
    add image support to NVIDIA inference provider (#907) v0.1.1rc3 Matthew Farrellee 2025-02-01 12:02:27 -05:00
  • 439d0da84c More pyproject shenanigans Ashwin Bharambe 2025-02-01 08:51:45 -08:00
  • 1ac0d8306b Remove test parameterization for safety tests, too much noise Ashwin Bharambe 2025-02-01 08:38:44 -08:00
  • 8f9ff545a4 Update LICENSE format Ashwin Bharambe 2025-02-01 08:34:25 -08:00
  • 3af9be744d Make package finding automatic Ashwin Bharambe 2025-02-01 08:09:39 -08:00
  • 5836ab2454 Add uv.lock Ashwin Bharambe 2025-01-31 22:40:53 -08:00
  • 6344b2429b Kill requirements.txt Ashwin Bharambe 2025-01-31 22:38:58 -08:00
  • 5b1e69e58e
    Use uv pip install instead of pip install (#921) Ashwin Bharambe 2025-01-31 22:29:41 -08:00
  • c6d9ff2054 Move to use pyproject.toml so it is uv compatible Ashwin Bharambe 2025-01-31 17:24:42 -08:00
  • 95786d5bdc Update client-sdk test config option handling Ashwin Bharambe 2025-01-31 15:29:55 -08:00
  • a67324c975
    Update CODEOWNERS ehhuang 2025-01-31 15:35:58 -08:00
  • f0ba367877 Update client-sdk test config option handling Ashwin Bharambe 2025-01-31 15:29:55 -08:00
  • 589a6911ba
    fix rag tests (#918) Hardik Shah 2025-01-31 15:29:29 -08:00
  • 216cde5ee8 Add --print-deps-only for computing dependencies Ashwin Bharambe 2025-01-31 14:31:13 -08:00
  • da46d98a63
    Run code-gen (#916) Hardik Shah 2025-01-31 13:47:42 -08:00
  • a7b929f17e
    Sec fixes as raised by bandit (#917) Hardik Shah 2025-01-31 13:44:26 -08:00
  • a5a573ad76 init lmstudio inference structure lm-studio-integration Justin Lee 2025-01-31 13:37:59 -08:00
  • 5d88a2fff5 init lm studio Justin Lee 2025-01-31 13:24:06 -08:00
  • 7ea14ae62e
    feat: enable xpu support for meta-reference stack (#558) Dmitry Rogozhkin 2025-01-31 12:11:49 -08:00
  • 15dcc4ea5e
    openapi gen return type fix for streaming/non-streaming (#910) Xi Yan 2025-01-30 18:03:02 -08:00
  • 2f11c7c203
    add test for user message w/ image.data content (#906) Matthew Farrellee 2025-01-30 20:35:27 -05:00
  • 97eb3eecea
    Fix Agents to support code and rag simultaneously (#908) Hardik Shah 2025-01-30 17:09:34 -08:00
  • 94051cfe9e
    fix ImageContentItem to take base64 string as image.data (#909) Xi Yan 2025-01-30 15:58:23 -08:00
  • 7fe2592795
    SambaNova supports Llama 3.3 (#905) snova-edwardm 2025-01-30 09:24:46 -08:00
  • 836f47a82d
    log probs - mark pytests as xfail for unsupported providers + add support for together (#883) Sixian Yi 2025-01-29 23:41:25 -08:00
  • 6f9023d948
    create a github action for triggering client-sdk tests on new pull-request (#850) Sixian Yi 2025-01-29 21:26:04 -08:00
  • 80f2032485
    Fix running stack built with base conda environment (#903) Dmitry Rogozhkin 2025-01-29 21:24:22 -08:00
  • 39c34dd25f
    [#432] Groq Provider tool call tweaks (#811) Aidan Do 2025-01-30 07:02:12 +11:00
  • d5b7de3897
    Fix link to selection guide and change "docker" to "container" (#898) Yuan Tang 2025-01-29 14:59:40 -05:00
  • 0d96070af9
    Update OpenAPI generator to add param and field documentation (#896) Ashwin Bharambe 2025-01-29 10:04:30 -08:00
  • 53721e91ad
    Fix validator of "container" image type (#901) Yuan Tang 2025-01-29 12:36:52 -05:00
  • 11b1cdf31d
    add NVIDIA_BASE_URL and NVIDIA_API_KEY to control hosted vs local endpoints (#897) Matthew Farrellee 2025-01-29 12:31:56 -05:00
  • 1a5c17a92f
    align with CompletionResponseStreamChunk.delta as str (instead of TextDelta) (#900) Matthew Farrellee 2025-01-29 12:25:50 -05:00
  • 9f709387e2 Kill X-LlamaStack-{Client-Version, Provider-Data} from OpenAPI spec Ashwin Bharambe 2025-01-28 13:26:34 -08:00
  • f2feb7d15c
    Fix Chroma adapter (#893) Ashwin Bharambe 2025-01-28 13:19:47 -08:00
  • ec3ebb5bcf
    Use ruamel.yaml to format the OpenAPI spec (#892) Ashwin Bharambe 2025-01-28 11:27:40 -08:00
  • 41749944a5 Fix ResponseFormat import Ashwin Bharambe 2025-01-28 09:34:05 -08:00
  • aee6237685 Small refactor for run_with_pty Ashwin Bharambe 2025-01-28 09:32:33 -08:00