Commit graph

  • ff247e35be
    feat: scaffolding for Llama Stack UI (#2149) ehhuang 2025-05-14 17:22:46 -07:00
  • 48763f21fd shadcn Eric Huang 2025-05-14 14:23:47 -07:00
  • 3faaeb0bba
    Merge branch 'main' into rag-metadata-support Francisco Arceo 2025-05-14 17:15:57 -06:00
  • b42eb1ccbc
    fix: Responses API: handle type=None in streaming tool calls (#2166) Ben Browning 2025-05-14 17:16:33 -04:00
  • ef88a53f9c
    chore: more API validators Sébastien Han 2025-05-14 21:39:18 +02:00
  • a713221280 fix: Responses API: handle type=None in streaming tool calls Ben Browning 2025-05-14 16:31:23 -04:00
  • b51427716d
    Merge branch 'main' into rag-metadata-support Francisco Arceo 2025-05-14 14:19:50 -06:00
  • aa5bef8e05
    feat: expand set of known openai models, allow using openai canonical model names (#2164) Matthew Farrellee 2025-05-14 16:18:15 -04:00
  • 5052c3cbf3
    fix: Fixed an "out of token budget" error when attempting a tool call via remote vLLM provider (#2114) Ilya Kolchinsky 2025-05-14 22:11:02 +02:00
  • 268725868e
    chore: enforce no git tags or branches in external github actions (#2159) Ihar Hrachyshka 2025-05-14 14:40:06 -04:00
  • 76679e2f0b updating doc strings Francisco Javier Arceo 2025-05-14 14:10:45 -04:00
  • 10a77b0715 chore: enforce no git tags or branches in external github actions Ihar Hrachyshka 2025-05-14 08:50:01 -04:00
  • e42f374a11 feat: expand set of known openai models, allow using openai canonical model names Matthew Farrellee 2025-05-14 11:36:20 -04:00
  • 75f29fbde0 fix behavior of --image-type in llama stack build Michele Dolfi 2025-05-14 17:26:32 +02:00
  • 1e59ef1f76
    Merge branch 'main' into rag-metadata-support Francisco Arceo 2025-05-14 08:19:08 -06:00
  • 97266dbca2
    Merge 1afd33c21e into a1fbfb51e2 Sébastien Han 2025-05-14 15:16:10 +02:00
  • a1fbfb51e2
    ci(chore): use hashes for all version pinning (#2157) Nathan Weinberg 2025-05-14 08:59:58 -04:00
  • 2792f067cd ci(chore): use hashes for all version pinning Nathan Weinberg 2025-05-13 16:05:45 -04:00
  • 85ef55391d
    Merge branch 'main' into out-of-token-budget-fix Ilya Kolchinsky 2025-05-14 12:46:24 +02:00
  • 63cce5673a Resolving merge conflicts. ilya-kolchinsky 2025-05-14 12:39:32 +02:00
  • 43d4447ff0
    fix: remote vLLM tool execution now works when the last chunk contains the call arguments (#2112) Ilya Kolchinsky 2025-05-14 11:38:00 +02:00
  • 1afd33c21e
    wip Sébastien Han 2025-05-13 20:47:03 +02:00
  • e6c9aebe47 refactor: Add ProviderContext for a flexible storage directory Roland Huß 2025-05-12 11:44:21 +02:00
  • 1de0dfaab5
    docs: Clarify kfp provider is both inline and remote (#2144) Ihar Hrachyshka 2025-05-14 03:37:07 -04:00
  • dd07c7a5b5
    fix: Make search tool talk about models (#2151) Derek Higgins 2025-05-14 06:41:51 +01:00
  • 26dffff92a
    chore: remove pytest reports (#2156) Sébastien Han 2025-05-14 07:40:15 +02:00
  • 227ff4c9b3
    Merge branch 'main' into rag-metadata-support Francisco Arceo 2025-05-13 21:14:02 -06:00
  • a962d2550d removing commented out Results item Francisco Javier Arceo 2025-05-13 22:56:10 -04:00
  • 66f7b42795 swapping to configuring the entire chunk template Francisco Javier Arceo 2025-05-13 22:47:35 -04:00
  • c17bccf730 docs: Clarify kfp provider is both local and remote Ihar Hrachyshka 2025-05-12 13:13:33 -04:00
  • c2670b44d3 Initial commit dualipa589 2025-05-14 00:15:35 +00:00
  • fb4463a9aa
    chore: remove pytest reports Sébastien Han 2025-05-13 21:16:47 +02:00
  • 8e316c9b1e
    feat: function tools in OpenAI Responses (#2094) Ben Browning 2025-05-13 14:29:15 -04:00
  • e0d10dd0b1
    docs: revamp testing documentation (#2155) Nathan Weinberg 2025-05-13 14:28:29 -04:00
  • 62476a5373
    fix: pytest reports (#2152) Sébastien Han 2025-05-13 20:27:29 +02:00
  • 749cbcca31
    feat: add s3 provider to files API Sébastien Han 2025-04-01 11:46:42 +02:00
  • 75f08d9bb5 docs: revamp testing documentation Nathan Weinberg 2025-05-13 11:31:39 -04:00
  • 8064e3d412 chore: Clean up variable names, duplication in openai_responses.py Ben Browning 2025-05-13 09:55:30 -04:00
  • dd57eff47b feat: Propagate W3C trace context headers from clients Ben Browning 2025-05-13 08:36:58 -04:00
  • 97cdcd1e22
    fix: pytest reports Sébastien Han 2025-05-13 11:46:50 +02:00
  • c1f53ddc16
    chore: more code-interpreter removal Sébastien Han 2025-05-12 20:36:44 +02:00
  • a5dcb89079 fix: Make search tool talk about models Derek Higgins 2025-05-13 09:52:52 +01:00
  • d8712c4242 feat: add llama stack rm and llama stack list commands Abhishek koserwal 2025-05-09 15:23:03 +05:30
  • e3ad17ec5e
    feat: enable mutual tls (#2140) grs 2025-05-12 17:08:36 -04:00
  • fb3c9be1fd refactor(api): rename "files" API to "artifacts" Sébastien Han 2025-05-12 11:13:23 +02:00
  • a5d14749a5
    chore: rehydrate requirements.txt (#2146) Sébastien Han 2025-05-12 21:45:35 +02:00
  • 89ed374fe3 CR fixes. ilya-kolchinsky 2025-05-12 20:55:24 +02:00
  • ef522efbb7
    chore: rehydrate requirements.txt Sébastien Han 2025-05-12 20:42:17 +02:00
  • 23d9f3b1fb build: Bump version to 0.2.6 github-actions[bot] 2025-05-12 18:02:05 +00:00
  • 2669cb5a33 build: Bump version to 0.2.6 v0.2.6 release-0.2.6 github-actions[bot] 2025-05-12 18:01:15 +00:00
  • c985ea6326
    fix: Adding Embedding model to watsonx inference (#2118) Divya 2025-05-12 23:28:22 +05:30
  • 136e6b3cf7
    fix: ollama openai completion and chat completion params (#2125) Ben Browning 2025-05-12 13:57:53 -04:00
  • 80c349965f
    chore(refact): move paginate_records fn outside of datasetio (#2137) Sébastien Han 2025-05-12 19:56:14 +02:00
  • 53b7f50828
    chore: force ellipsis in API webmethods (#2141) Sébastien Han 2025-05-12 19:55:39 +02:00
  • 43e623eea6
    chore: remove last instances of code-interpreter provider (#2143) Sébastien Han 2025-05-12 19:54:43 +02:00
  • 8bdd0ef2c5 Release candidate 0.2.6rc1 v0.2.6rc1 github-actions[bot] 2025-05-12 17:42:28 +00:00
  • 2e70782e63
    Merge branch 'main' into rag-metadata-support Francisco Arceo 2025-05-12 10:10:28 -06:00
  • 440a15d81e
    chore: force ellipsis in API webmethods Sébastien Han 2025-05-12 14:51:32 +02:00
  • 675f34e79d
    fix: Syntax error with missing stubs at the end of some function calls (#2116) Krzysztof Malczuk 2025-05-12 16:05:40 +01:00
  • f639e79549 Add stubs to functions create_agent_turn, create_openai_response, job_result, evaluate_rows and job_status 2000krysztof 2025-05-08 10:30:42 +01:00
  • b823e8f2a7
    chore: remove last instances of code-interpreter provider Sébastien Han 2025-05-12 16:41:50 +02:00
  • 9a6e91cd93
    fix: chromadb type hint (#2136) Matthew Farrellee 2025-05-12 09:27:01 -04:00
  • 91602bfa5e feat: enable mutual tls Gordon Sim 2025-05-12 11:53:24 +01:00
  • db21eab713
    fix: catch TimeoutError in place of asyncio.TimeoutError (#2131) Ihar Hrachyshka 2025-05-12 05:49:59 -04:00
  • dd7be274b9
    fix: raise an error when no vector DB IDs are provided to the RAG tool (#1911) Ilya Kolchinsky 2025-05-12 11:25:13 +02:00
  • 7d6942e793
    chore(refact): move paginate_records fn outside of datasetio Sébastien Han 2025-05-12 11:16:34 +02:00
  • f2b83800cc
    docs: Add link to Discord to README (#2126) Yuan Tang 2025-05-10 21:32:44 -04:00
  • dc8e25c02b adding exceptional handling for serializing the metadata Francisco Javier Arceo 2025-05-10 21:25:17 -04:00
  • f7d0b7830a fix chromadb type hint Matthew Farrellee 2025-05-10 07:40:35 -04:00
  • 54d28d13e9 fix typo in comment Francisco Javier Arceo 2025-05-09 23:56:03 -04:00
  • e50a546bc0 feat: Adding support for metadata in RAG insertion and querying Francisco Javier Arceo 2025-05-09 23:38:47 -04:00
  • 851d0fdc10 fix: catch TimeoutError in place of asyncio.TimeoutError Ihar Hrachyshka 2025-05-09 16:12:24 -04:00
  • 56cc8f376d adding Sentence Transformer to watsonx Inference Divya 2025-05-08 08:18:36 -07:00
  • 1ceebdc813 fix: cancel scheduler tasks on shutdown Ihar Hrachyshka 2025-05-09 13:34:04 -04:00
  • 3be85c717f Added proper support for calling tools without parameters. ilya-kolchinsky 2025-05-09 12:38:59 +02:00
  • f142af9576
    docs: Add link to Discord to README Yuan Tang 2025-05-08 19:59:08 -04:00
  • 8747210470 fix: ollama openai completion and chat completion params Ben Browning 2025-05-08 18:12:51 -04:00
  • 473a07f624
    fix: revert "feat(provider): adding llama4 support in together inference provider (#2123)" (#2124) Ashwin Bharambe 2025-05-08 15:18:16 -07:00
  • 21235f0045 Revert "feat(provider): adding llama4 support in together inference provider (#2123)" Ashwin Bharambe 2025-05-08 14:57:43 -07:00
  • 0f878ad87a
    feat(provider): adding llama4 support in together inference provider (#2123) Yogish Baliga 2025-05-08 14:27:56 -07:00
  • af6f7bc535 adding llama4 support in together inference provider Yogish Baliga 2025-05-08 14:16:35 -07:00
  • 4df8caab41 Fixes for multi-turn tool calls in Responses API Ben Browning 2025-05-08 16:21:15 -04:00
  • 65c56d0ee8 chore: Address review feedback with minor code cleanups Ben Browning 2025-05-08 06:47:53 -04:00
  • 9166baa716 Load OpenAIChatCompletion directly from YAML Derek Higgins 2025-05-06 11:24:38 +01:00
  • dfb641a3de Handle more input content types in Responses API Ben Browning 2025-05-02 14:38:25 -04:00
  • 11081c2029 foo Ben Browning 2025-05-02 14:38:00 -04:00
  • a1955215c4 Update verification run.yaml based on latest main Ben Browning 2025-05-02 12:58:40 -04:00
  • 924213a689 Responses API: Finish wiring up function tool calls Ben Browning 2025-04-30 17:01:00 -04:00
  • 1990df2c50 feat: add function tools to openai responses Ashwin Bharambe 2025-04-30 13:06:33 -07:00
  • b90bb66f28 fix: Restore previous responses to input list, not messages Ben Browning 2025-05-02 11:08:09 -04:00
  • 5b2e850754 fix: Responses API previous_response input items Ben Browning 2025-04-30 12:25:38 -04:00
  • 150b9a0834 feat(openai-responses): Support multiple message roles in API inputs Derek Higgins 2025-05-02 11:10:07 +01:00
  • 1369b5858e chore: Refactor OpenAIChatCompletion's to be loaded from yaml Derek Higgins 2025-05-02 11:07:58 +01:00
  • 7a8e398f09 Removed an accidentally committed debug print. ilya-kolchinsky 2025-05-08 11:08:41 +02:00
  • 57e28b5b9b Reverted the change in handling the case of no chunks found. ilya-kolchinsky 2025-05-08 10:52:00 +02:00
  • 7784307a5f Fixed an "out of token budget" tool execution bug in the remote vLLM provider. ilya-kolchinsky 2025-05-08 10:42:26 +02:00
  • 55da406471 Fixed an error where a tool call fails when the arguments are passed in the chunk containing finish_reason. ilya-kolchinsky 2025-05-08 09:46:35 +02:00
  • fe5f5e530c
    feat: add metrics query API (#1394) Dinesh Yeduguru 2025-05-07 10:11:26 -07:00
  • 5d70a6baba fix Ashwin Bharambe 2025-05-07 10:00:22 -07:00
  • 6371bb1b33
    chore(refact)!: simplify config management (#1105) Sébastien Han 2025-05-07 18:18:12 +02:00