Commit graph

  • af7748a4d5 feat: Adding sqlite-vec as vectordb Francisco Javier Arceo 2025-02-10 16:16:55 -05:00
  • b2a86532a2
    Handle response Yuan Tang 2025-02-10 15:23:09 -05:00
  • cc3bb0938a
    fix: Handle tool calling in remote vLLM provider Yuan Tang 2025-02-10 14:55:59 -05:00
  • 65ffcddd84 deprecation Xi Yan 2025-02-10 11:35:21 -08:00
  • 79e7253625 deprecation in OpenAPI spec Xi Yan 2025-02-10 11:21:51 -08:00
  • e013b9066c fix path Xi Yan 2025-02-10 10:47:28 -08:00
  • b11c38ea55 openapi Xi Yan 2025-02-10 09:41:21 -08:00
  • 5fe3ddb27d update eval_task_id -> task_id Xi Yan 2025-02-10 09:41:01 -08:00
  • f1844a88c4 update eval-tasks -> eval/task Xi Yan 2025-02-10 09:37:21 -08:00
  • a12e8b3641
    build: update uv lock to sync package versions Sébastien Han 2025-02-10 09:38:52 +01:00
  • 787e78d7d4
    chore: update return type to Optional[str] Sébastien Han 2025-02-06 13:45:38 +01:00
  • 3df95a07a0
    fix: replace blocked image URLs with GitHub-hosted Sébastien Han 2025-02-10 09:29:04 +01:00
  • 24d012cb33
    docs: Render check marks correctly on PyPI Yuan Tang 2025-02-09 22:18:05 -05:00
  • eeae5f6cbc fix: Update Qdrant support post-refactor Bill Murdock 2025-02-09 17:02:00 -05:00
  • 162cfb280e added note of the image understanding working with LS 0.1.0 and 0.1.2 Jeff Tang 2025-02-09 09:27:15 -08:00
  • 44f1a4fd5c fix of the agent image understanding example error for LS 0.1.2 Jeff Tang 2025-02-09 09:24:15 -08:00
  • adb83e0465
    test: Use JSON tool prompt format for remote::vllm provider Yuan Tang 2025-02-08 23:18:39 -05:00
  • aaa624ed64 chore: added pypdf and chardet to requirements.txt sarthakdeshpande 2025-02-08 15:30:53 +05:30
  • 5e393f851d Updated requirements.txt sarthakdeshpande 2025-02-08 15:18:04 +05:30
  • ba33494aee
    edits Yuan Tang 2025-02-07 23:18:24 -05:00
  • 6dea61609d
    test: Make text-based chat completion tests run faster Yuan Tang 2025-02-07 22:35:22 -05:00
  • 533e39bd08
    Update index.md for 0.1.2 raghotham 2025-02-07 15:30:48 -08:00
  • 54c2513c1b update rag.md example code Michael Clifford 2025-02-07 11:46:05 -05:00
  • 04174bafa0 fix: Clarify llama model prompt-format help text Alina Ryan 2025-02-07 13:10:00 -05:00
  • 2493eb794f
    Avoid error catching Ashwin Bharambe 2025-02-07 09:46:02 -08:00
  • b3bfff78c5 SSL -> TLS thanks @leseb Ashwin Bharambe 2025-02-07 09:28:26 -08:00
  • 7ee04827a2 tests: remove flaky agent test Eric Huang 2025-02-07 09:20:43 -08:00
  • 64d6e67644
    test: Split inference tests to text and vision Yuan Tang 2025-02-07 12:19:22 -05:00
  • 997b097e26 Address feedback Ashwin Bharambe 2025-02-07 09:11:15 -08:00
  • e23213ee8a fix Ashwin Bharambe 2025-02-06 16:54:31 -08:00
  • 4f3c19114c Add HTTPS serving option Ashwin Bharambe 2025-02-06 16:04:25 -08:00
  • 9fdc253011 [Docs] Updating wording and nits in the README.md Kelly Brown 2025-02-06 11:08:03 -05:00
  • d9c460cb4b
    refactor(ollama): model availability check Sébastien Han 2025-02-06 14:57:19 +01:00
  • 6d7f1d04ae
    test: encode image data as base64 Sébastien Han 2025-02-07 09:34:49 +01:00
  • 1906c120c1
    test: rm unused exception alias in pytest.raises Sébastien Han 2025-02-06 16:42:51 +01:00
  • 447a6933e9 test: fix flaky agent test Eric Huang 2025-02-06 20:17:37 -08:00
  • 20bd7601e8
    Address feedback Yuan Tang 2025-02-06 21:37:52 -05:00
  • 3e7f682906 update rag examples to use fresh faiss index every time Hardik Shah 2025-02-06 16:07:38 -08:00
  • 9267a3bc79 no homedirs Hardik Shah 2025-02-06 13:45:54 -08:00
  • a4415f5657 Correct typos in Zero to Hero guide Maxime Lecanu 2025-02-06 13:07:10 -08:00
  • f724562629 Add comment that files are autogen Hardik Shah 2025-02-06 12:54:34 -08:00
  • 38fb2ceea6 revert to TGI for now Hardik Shah 2025-02-06 12:33:19 -08:00
  • a5b245e1ac
    Update semantic-pr.yml Yuan Tang 2025-02-06 15:02:35 -05:00
  • 0c7fa1a20c doc: getting started notebook Eric Huang 2025-02-06 11:52:44 -08:00
  • b281ae343a point to DEH for infernece Hardik Shah 2025-02-06 11:45:54 -08:00
  • 14ea403ba6 ci: add "Pull Request Labeler" GitHub Action Nathan Weinberg 2025-02-03 14:17:30 -05:00
  • ec472b6663
    Update semantic-pr.yml Yuan Tang 2025-02-06 13:29:55 -05:00
  • 532696ea89
    docs: Add license badge to README.md Yuan Tang 2025-02-06 12:38:45 -05:00
  • 66afbe8e7f github: update PR template so issues are auto-linked Nathan Weinberg 2025-02-06 10:42:16 -05:00
  • bad49a93a9 github: update PR template to use correct syntax to auto-close issues Ihar Hrachyshka 2025-02-06 10:40:28 -05:00
  • 11e2478a15
    chore: update PR template to reinforce changelog Sébastien Han 2025-02-06 15:57:59 +01:00
  • e508a87361 chore: remove unused argument Charlie Doern 2025-02-06 09:51:40 -05:00
  • e18513f3f2
    chore: add missing ToolConfig import in groq.py Sébastien Han 2025-02-06 13:48:41 +01:00
  • 02564461ed
    test: replace memory with vector_io fixture Sébastien Han 2025-02-06 13:50:38 +01:00
  • 106bc25b98
    docs: use uv in CONTRIBUTING guide Sébastien Han 2025-02-05 16:37:28 +01:00
  • c7f28e06e1 sys_prompt support in Agent Eric Huang 2025-02-05 21:10:34 -08:00
  • b7a44481fa
    ci: Add semantic PR title check Yuan Tang 2025-02-05 21:45:25 -05:00
  • aa6138e0ca update doc.md Hardik Shah 2025-02-05 15:36:29 -08:00
  • a56b25c8f7 docs: clarify host.docker.internal works for recent podman Ihar Hrachyshka 2025-02-05 18:30:36 -05:00
  • 0d006bb341 codegen Hardik Shah 2025-02-05 15:01:45 -08:00
  • 76b14a6c01 Fix README.md notebook links Aakanksha Duggal 2025-02-05 17:24:27 -05:00
  • 56373cc686 docs: add addn server guidance for Linux users in Quick Start Nathan Weinberg 2025-02-05 13:16:11 -05:00
  • 4c1db13cf4
    missing T in import Ryan Cook 2025-02-05 15:47:28 -05:00
  • 7c1c5e7dff
    Clean up Yuan Tang 2025-02-05 14:41:41 -05:00
  • 111f31b60d
    fix Yuan Tang 2025-02-05 14:41:14 -05:00
  • 79b79889bc
    Reuse builtin_automatically_routed_apis Yuan Tang 2025-02-05 14:40:10 -05:00
  • ff3cb032a6 fix stack trace when stack is not built. Charlie Doern 2025-02-04 12:52:48 -05:00
  • 35bc05d71b
    List providers command prints out non-existing APIs from registry. Fixes #966 Yuan Tang 2025-02-05 10:26:37 -05:00
  • 8f9b8a57cb docs, tests: replace datasets.rst with memory_optimizations.rst Ihar Hrachyshka 2025-02-05 10:21:44 -05:00
  • 33b433a7a7 fix uv uninstall Hardik Shah 2025-02-04 18:38:07 -08:00
  • 65e8f5bfaf dell template + codegen for others Hardik Shah 2025-02-04 17:33:29 -08:00
  • 42f0e91909 remove response parser Xi Yan 2025-02-04 17:33:08 -08:00
  • e982565cac Make a couple properties optional Ashwin Bharambe 2025-02-04 16:16:42 -08:00
  • 4b85b8ae51 [docs] Make RAG example self-contained Ihar Hrachyshka 2025-02-04 18:32:38 -05:00
  • a107960fd8 [docs] Show that llama-stack-client configure will ask for api key Ihar Hrachyshka 2025-02-04 18:27:21 -05:00
  • 0bec24c3db [docs]: Export variables (e.g. INFERENCE_MODEL) in getting_started Ihar Hrachyshka 2025-02-04 18:25:45 -05:00
  • 3672e120ff [docs] Fix misc typos and formatting issues in intro docs Ihar Hrachyshka 2025-02-04 18:25:01 -05:00
  • 45ae533009
    update the zero_to_hero_guide llama stack version to 0.1.0 Kamesh Akella 2025-02-04 17:30:38 -05:00
  • ede4ab652e
    Refine Podman instructions for Quick Start Bill Murdock 2025-02-04 17:19:10 -05:00
  • 9698e59f91
    Add podman instructions to Quick Start Bill Murdock 2025-02-04 16:38:17 -05:00
  • 0c77470945 if init fails, the example should exit Charlie Doern 2025-02-04 13:48:12 -05:00
  • 5dde1f51be github: issue templates automatically apply relevant label Nathan Weinberg 2025-02-04 15:13:01 -05:00
  • 662f171e88 api change Xi Yan 2025-02-04 11:56:50 -08:00
  • 4d07460398 tmp Xi Yan 2025-02-04 10:54:53 -08:00
  • 6fb289a2c6
    Fix incorrect handling of chat completion endpoint in remote::vLLM Yuan Tang 2025-02-04 13:39:13 -05:00
  • b1492ecb4e revert print Xi Yan 2025-02-04 10:30:19 -08:00
  • 5595f5b9b8 tmp Xi Yan 2025-02-04 10:27:05 -08:00
  • 695106cb7c
    Fix issues Yuan Tang 2025-02-03 23:08:08 -05:00
  • 57b4129c51 Support sys_prompt behavior in inference Eric Huang 2025-02-03 16:20:10 -08:00
  • 511e082b0e
    Fix Yuan Tang 2025-02-03 18:43:51 -05:00
  • 710088239c
    Fix memory leaks due to open cursors in PGVector provider Yuan Tang 2025-02-03 18:41:52 -05:00
  • 818396db29 Merge branch 'main' into typescript-doc Xi Yan 2025-02-03 14:28:31 -08:00
  • d9bcbba6e3 typescript Xi Yan 2025-02-03 14:27:03 -08:00
  • afb109245c typescript Xi Yan 2025-02-03 14:23:35 -08:00
  • 46e040dc66 fix: formatting for ollama note in Quick Start doc Nathan Weinberg 2025-02-03 17:03:25 -05:00
  • e1c57d5b94 Update getting started for uv Ashwin Bharambe 2025-02-03 14:06:45 -08:00
  • 109f210369 Add a pre-commit for requirements.txt Ashwin Bharambe 2025-02-03 13:55:36 -08:00
  • bc862f1d25 Make sure torch + torchvision go together as deps Ashwin Bharambe 2025-02-03 13:52:39 -08:00
  • c786a7986b fix: broken link in Quick Start doc Nathan Weinberg 2025-02-03 16:35:30 -05:00
  • dac3f0595c fix: Update link to redirect to index page Francisco Javier Arceo 2025-02-03 15:52:47 -05:00