Commit graph

  • adc373600e test: added integeration test that queries for identical vectors and verifies no divide by zero exception occurs Ibrahim Haroon 2025-06-09 09:09:51 -04:00
  • f5d2108191 fix: handle case where distance is 0 by setting score to infinity Ibrahim Haroon 2025-06-06 15:33:05 -04:00
  • 91a5b1d921
    Merge branch 'main' into feat/add-url-to-paginated-response Rohan Awhad 2025-06-09 09:04:53 -04:00
  • dbe4f745e5 Release candidate 0.0.0.dev20250609002706 rc-0.0.0.dev20250609002706 github-actions[bot] 2025-06-09 00:27:49 +00:00
  • cd7a246050 Release candidate 0.0.0.dev20250608002809 rc-0.0.0.dev20250608002809 github-actions[bot] 2025-06-08 00:28:54 +00:00
  • 06be99f1a2 fix: loosen tool call checks in inference store Ben Browning 2025-06-07 19:47:51 -04:00
  • 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
  • a34cef925b
    fix(faiss): handle case where distance is 0 by setting d to minimum positive… (#2387) Ibrahim Haroon 2025-06-07 16:09:46 -04:00
  • e4d7651ffa Don't downgrade llama-stack version in uv.lock Ben Browning 2025-06-07 15:58:55 -04:00
  • e28a57ad76 feat: Add url field to PaginatedResponse and populate it using route path Rohan Awhad 2025-06-06 22:24:30 -04:00
  • 75d9d0ad74 Release candidate 0.0.0.dev20250607002501 rc-0.0.0.dev20250607002501 github-actions[bot] 2025-06-07 00:26:30 +00:00
  • 6f8312ddd0 fix: handle case where distance is 0 by setting score to infinity Ibrahim Haroon 2025-06-06 15:31:25 -04:00
  • 33ecefd284
    feat: To add health status check for remote VLLM (#2303) Sumit Jaiswal 2025-06-07 01:03:12 +05:30
  • 379b6530ee build: Bump version to 0.2.10.1 v0.2.10.1 release-0.2.10.1 github-actions[bot] 2025-06-06 18:54:51 +00:00
  • 32c651e3a7
    chore: update CODEOWNERS (#2414) Alexey Rybak 2025-06-06 11:35:15 -07:00
  • 10d4c5a80f Release candidate 0.2.10.1rc1 v0.2.10.1rc1 rc-0.2.10.1rc1 github-actions[bot] 2025-06-06 18:32:20 +00:00
  • 9239e09181 chore: update CODEOWNERS Alexey Rybak 2025-06-06 11:30:34 -07:00
  • 1f48577a02
    fix: ChromaDB provider (#2413) Hardik Shah 2025-06-06 11:25:58 -07:00
  • ea110857df update chroma interface to match new spec Hardik Shah 2025-06-06 11:11:36 -07:00
  • b05a3db358
    Merge branch 'main' into fix/divide-by-zero-exception-faiss-query-vector Ibrahim Haroon 2025-06-06 11:29:14 -04:00
  • 57494665e1 buid: test_faiss.py requires faiss-cpu Ibrahim Haroon 2025-06-06 10:33:23 -04:00
  • 1a492ad0cc Merge branch 'main' into nvidia-e2e-notebook Jash Gulabrai 2025-06-06 11:11:53 -04:00
  • 6b6d8d70a5 Remove print statement Jash Gulabrai 2025-06-06 10:43:24 -04:00
  • 6346024fa3 fix: Don't reuse session in NVIDIA post_training request handler Jash Gulabrai 2025-06-06 10:42:10 -04:00
  • 4b32cfa846 chore: fixed formatting issues Ibrahim Haroon 2025-06-06 10:32:39 -04:00
  • 0d0b8d2be1
    ci: use ollama container image with loaded models (#2410) Sébastien Han 2025-06-06 12:08:20 +02:00
  • c8b5774ff3
    ci: use ollama container image with loaded models Sébastien Han 2025-06-06 09:54:39 +02:00
  • 6ed971c67d
    chore: resync requirements.txt Sébastien Han 2025-06-06 11:49:44 +02:00
  • 7572768bd8 Release candidate 0.0.0.dev20250606002455 rc-0.0.0.dev20250606002455 github-actions[bot] 2025-06-06 00:25:41 +00:00
  • 692709cd45 build: Bump version to 0.2.10 github-actions[bot] 2025-06-05 22:56:39 +00:00
  • 8bc53d047c build: Bump version to 0.2.10 v0.2.10 release-0.2.10 github-actions[bot] 2025-06-05 22:55:45 +00:00
  • 1979132115 Release candidate 0.2.10rc3 v0.2.10rc3 rc-0.2.10rc3 github-actions[bot] 2025-06-05 22:35:04 +00:00
  • 102516f33c
    fix: Pin fastapi to avoid picking up spurious versions in test pypi (#2409) Hardik Shah 2025-06-05 15:33:30 -07:00
  • 18333d1ac8 fix version Hardik Shah 2025-06-05 15:29:56 -07:00
  • 446893f791
    feat: add deps dynamically based on metastore config (#2405) ehhuang 2025-06-05 14:07:25 -07:00
  • acabeec42f Release candidate 0.2.10rc2 v0.2.10rc2 rc-0.2.10rc2 github-actions[bot] 2025-06-05 20:59:41 +00:00
  • d211f5188b internal_providers Eric Huang 2025-06-05 13:44:09 -07:00
  • 92b59a3377
    test: skip files integrations tests for library client (#2407) ehhuang 2025-06-05 13:42:10 -07:00
  • 7b7a958106 test: skip files integrations tests for library client Eric Huang 2025-06-05 13:41:47 -07:00
  • 460c67be62 kvstore Eric Huang 2025-06-05 11:59:11 -07:00
  • f0170c5d3a chore: remove explicit sqlite dependency Raghotham Murthy 2025-06-05 02:03:21 -07:00
  • ee6feaa2d5
    chore: remove dead code (#2403) ehhuang 2025-06-05 12:17:54 -07:00
  • fe50ec2190 chore: remove dead code Eric Huang 2025-06-05 11:58:15 -07:00
  • 04592b9590
    fix: update pyproject to include recursive LS deps (#2404) Hardik Shah 2025-06-05 11:46:48 -07:00
  • 51c05ae762 Add fastapi dependency Hardik Shah 2025-06-05 11:42:28 -07:00
  • 4fb228a1d8
    ci: run integration test on more python version (#2400) Sébastien Han 2025-06-05 20:40:21 +02:00
  • 7e643b9b12 update to import all dependencies inside llama-stack Hardik Shah 2025-06-05 11:27:00 -07:00
  • e6cbe94ace update doc Gordon Sim 2025-06-05 18:06:13 +01:00
  • 3251b44d8a
    refactor: unify stream and non-stream impls for responses (#2388) Ashwin Bharambe 2025-06-05 17:48:09 +02:00
  • 1135af30cf remove cluster role binding as it is not needed Gordon Sim 2025-06-05 16:33:32 +01:00
  • a996ce2af2 change value of test token for clarity Gordon Sim 2025-06-05 16:20:46 +01:00
  • d01d3d998b reuse existing token Gordon Sim 2025-06-05 16:11:39 +01:00
  • f60c3c4acf feat: created unit test to verify query_vector function handles the edge case when the query embedding and an embedding in the vector db are identical doesn't lead to zero divison exception. Ibrahim Haroon 2025-06-05 11:06:31 -04:00
  • fea01c5a25 fix: handle case where distance is 0 by setting score to infinity Ibrahim Haroon 2025-06-03 19:20:31 -04:00
  • bc36e50b61 pre-commit Ashwin Bharambe 2025-06-05 15:43:36 +02:00
  • c18b585d32
    Merge branch 'main' into vllm_health_check Sumit Jaiswal 2025-06-05 18:09:36 +05:30
  • 1b36bd377e
    ci: run integration test on more python version Sébastien Han 2025-06-05 12:17:00 +02:00
  • d9c5931363 chore: remove explicit sqlite dependency Raghotham Murthy 2025-06-05 02:03:21 -07:00
  • ef885d2147
    fix(server): Add missing OpenTelemetry dependencies to resolve telemetry import errors (#2391) Jose Angel Morena Simon 2025-06-05 09:34:46 +02:00
  • cc1197cfb8
    Merge branch 'main' into add_opentelemetry_pip_packages raghotham 2025-06-04 23:28:29 -07:00
  • 179d72615b
    docs: update contributing guidance around uv python versions (#2398) Nathan Weinberg 2025-06-05 02:12:03 -04:00
  • 73f68783c1 docs: update contributin guidance around uv python versions Nathan Weinberg 2025-06-04 22:14:01 -04:00
  • a58c0639d5
    chore: update postgres_demo distro config (#2396) ehhuang 2025-06-04 17:41:27 -07:00
  • eb5f4c4cf2 chore: update postgres_demo distro config Eric Huang 2025-06-04 16:51:52 -07:00
  • 74d891db72 feat(auth): allow token to be provided for use against jwks endpoint Gordon Sim 2025-06-04 19:12:15 +01:00
  • 34b3b6e049 fix(server): add missing OpenTelemetry dependencies to avoid runtime import errors Jose Angel Morena 2025-06-04 11:15:40 +02:00
  • c8c742ba45
    fix: vllm starter name (#2392) Sébastien Han 2025-06-04 16:21:36 +02:00
  • af0d6014c1
    fix: vllm starter name Sébastien Han 2025-06-04 11:55:26 +02:00
  • 0de9536717
    fix: remove debug print accidentally merged (#2393) grs 2025-06-04 09:14:14 -04:00
  • b30ddb1d2b fix: remove debug print accidentally merged Gordon Sim 2025-06-04 13:47:44 +01:00
  • e9d9f01b8b
    docs: Add OpenAI API compatibility page (#2316) Ben Browning 2025-06-04 06:51:52 -04:00
  • db2fb7e3c4 feat: Add experimental integration tests with cached providers Derek Higgins 2025-05-14 14:41:25 +01:00
  • c4f644a1ea Remove remote::openai from openai_completion support Derek Higgins 2025-06-04 09:08:30 +01:00
  • 8afad3f63a refactor: unify stream and non-stream impls for responses Ashwin Bharambe 2025-06-03 16:51:06 -07:00
  • c4c67ac775 chore: cleanups from review feedback on openai api docs Ben Browning 2025-06-03 20:42:56 -04:00
  • ed69c1b3cc
    feat(responses): add more streaming response types (#2375) Ashwin Bharambe 2025-06-03 15:48:41 -07:00
  • 252249cf91 feat(responses): add more streaming response types Ashwin Bharambe 2025-06-03 15:41:07 -07:00
  • d96f6ec763
    chore(ui): use proxy server for backend API calls; simplified k8s deployment (#2350) ehhuang 2025-06-03 14:57:10 -07:00
  • 7c1998db25
    feat: fine grained access control policy (#2264) grs 2025-06-03 17:51:12 -04:00
  • 8bee2954be
    feat: Structured output for Responses API (#2324) Ben Browning 2025-06-03 17:43:00 -04:00
  • c70ca8344f
    fix: resolve template name to config path in llama stack run (#2361) Ignas Baranauskas 2025-06-03 22:39:12 +01:00
  • 7cd2a1c031 k8s Eric Huang 2025-06-03 12:09:01 -07:00
  • cba55808ab
    feat(distro): add more providers to starter distro, prefix conflicting models (#2362) Ashwin Bharambe 2025-06-03 12:10:46 -07:00
  • e45e4f947a bugfix Ashwin Bharambe 2025-06-03 12:00:51 -07:00
  • 471d40e80c kill verif template Ashwin Bharambe 2025-06-03 11:56:07 -07:00
  • 96cd51a0c8 Changes to access rule conditions: Gordon Sim 2025-05-29 20:21:20 +01:00
  • 528a391c5f feat(distro): add more providers to starter distro, prefix conflicting models Ashwin Bharambe 2025-06-03 11:43:19 -07:00
  • a8ba160852
    fix: resolve template name to config path in llama stack run Ignas Baranauskas 2025-06-03 19:18:38 +01:00
  • b380cb463f
    feat: add postgres deps to starter distro (#2360) Ashwin Bharambe 2025-06-03 11:04:23 -07:00
  • 032f92b3e1 feat: add postgres deps to starter distro Ashwin Bharambe 2025-06-03 10:57:08 -07:00
  • e743257d1d
    docs: Add missing dependencies in quickstart demo command (#2347) Jorge 2025-06-03 18:01:36 +02:00
  • 7e30b5a466
    fix: remove sentence-transformers from remote vllm Sébastien Han 2025-06-03 18:00:27 +02:00
  • 643c0bb747 fix: Add fictional liquids to get_boiling_point Derek Higgins 2025-05-14 12:14:37 +01:00
  • 73ca0fb37a
    chore: remove torch dep from sentence-transformers Sébastien Han 2025-06-03 15:13:11 +02:00
  • 59830e5a22
    chore: return NotImplementedError instead of ValueError Sébastien Han 2025-06-03 15:11:54 +02:00
  • 9e757c433a Add missing dependencies in quickstart command Jorge Garcia Oncins 2025-06-03 14:28:08 +02:00
  • 3c9a10d2fe
    feat: reference implementation for files API (#2330) ehhuang 2025-06-02 21:54:24 -07:00
  • ba25c5e7e1
    docs(k8s): add UI template (#2343) Ashwin Bharambe 2025-06-02 17:55:18 -07:00
  • 0ea429c163 fix Ashwin Bharambe 2025-06-02 17:53:57 -07:00
  • e92f571f47
    fix: ollama chat completion needs unique ids (#2344) Ben Browning 2025-06-02 20:43:20 -04:00