Commit graph

  • 1dcffac3fd
    chore: help setuptools finding the project path Sébastien Han 2025-06-02 15:26:45 +02:00
  • f586bdd912 fix: remote-vllm event loop blocking unit test on Mac Ben Browning 2025-06-02 08:33:23 -04:00
  • 88edf74b6f
    fix: use unicode escape sequence for zero-width Sébastien Han 2025-06-02 10:12:49 +02:00
  • 365b896b38
    revert: "chore: Remove zero-width space characters from OTEL service name env var defaults" Sébastien Han 2025-06-02 10:05:42 +02:00
  • b413c7562b
    fix review cosmetic comment Sumit Jaiswal 2025-06-02 12:45:17 +05:30
  • afa9db5a6b
    fix pre-commit issues Sumit Jaiswal 2025-06-01 16:00:18 +05:30
  • ae85dd6182
    fix unit tc failure due to updated logic Sumit Jaiswal 2025-05-31 08:05:04 +05:30
  • 9c42598aee
    fix review around /models api call Sumit Jaiswal 2025-05-30 16:14:31 +05:30
  • 6a96b6c264
    update the API Sumit Jaiswal 2025-05-30 00:23:56 +05:30
  • 6d1cf140ba
    to add health status check for remote vllm Sumit Jaiswal 2025-05-29 02:10:13 +05:30
  • 6cbb3366f2 more fixes, gah Ashwin Bharambe 2025-06-01 17:07:18 -07:00
  • 6f4f51f8d9 apply anti affinity and separate PVCs for the models so the two vllms can be mapped to two nodes and avoid causing unnecessary memory pressure Ashwin Bharambe 2025-06-01 16:54:36 -07:00
  • 4121166784 split off safety so it can be applied one at a time Ashwin Bharambe 2025-06-01 15:59:00 -07:00
  • d93f6c9e5b play around with util Ashwin Bharambe 2025-06-01 15:34:43 -07:00
  • a36b0c5fe3 docs(kubernetes): add a more fleshed out example of a Demo Kubernetes cluster Ashwin Bharambe 2025-06-01 14:25:54 -07:00
  • 319300fe24
    updates to fix pre-commit checks Sumit Jaiswal 2025-06-01 17:51:02 +05:30
  • 6ec2ed4196
    feat: New OpenAI compat embeddings API (#2314) Hardik Shah 2025-05-31 22:11:47 -07:00
  • 455939e63c
    fix: Responses streaming tools don't concatenate None and str (#2326) Ben Browning 2025-05-31 21:24:04 -04:00
  • 2818e444f2
    feat: Enable ingestion of precomputed embeddings (#2317) Francisco Arceo 2025-05-31 04:03:37 -06:00
  • dfdf854865
    fix: Fix requirements from broken github-actions[bot] (#2323) Francisco Arceo 2025-05-30 20:05:47 -06:00
  • 769d8f5428
    build: Bump version to 0.2.9 github-actions[bot] 2025-05-30 19:43:09 +00:00
  • fbc8fc6eb5
    feat: support postgresql inference store (#2310) ehhuang 2025-05-29 14:33:09 -07:00
  • a6d8e6831b fix: Responses streaming tools don't concatenate None and str Ben Browning 2025-05-31 15:40:01 -04:00
  • be4d924ffe skip ollama openai_embeddings test Hardik Shah 2025-05-30 21:30:03 -07:00
  • a3d83ea653
    Merge branch 'main' into precomputed-embeddings Francisco Arceo 2025-05-30 20:05:59 -06:00
  • 1dd4c06d42 fix: Fix requirements from broken github-actions[bot] Francisco Javier Arceo 2025-05-30 21:53:29 -04:00
  • a9daf358c4
    Merge branch 'main' into precomputed-embeddings Francisco Arceo 2025-05-30 19:36:55 -06:00
  • 09bdaf07a1 update dqdrant test Francisco Javier Arceo 2025-05-30 21:35:13 -04:00
  • 1e2d1643fe build: Bump version to 0.2.9 github-actions[bot] 2025-05-30 19:43:09 +00:00
  • 681e697fff updated tests and refactored the validation for readability Francisco Javier Arceo 2025-05-30 17:07:20 -04:00
  • 8e79ef9a7d build: Bump version to 0.2.9 v0.2.9 release-0.2.9 github-actions[bot] 2025-05-30 19:42:28 +00:00
  • 535e55d7dd Merge branch 'embeddings' of https://github.com/hardikjshah/llama-stack into embeddings Hardik Shah 2025-05-30 12:25:07 -07:00
  • ca32658ed7 added tests Hardik Shah 2025-05-30 12:23:23 -07:00
  • b53dda91ab Release candidate 0.2.9rc1 v0.2.9rc1 github-actions[bot] 2025-05-30 19:06:01 +00:00
  • 71caa271ad feat: associated models API with post_training Charlie Doern 2025-05-30 12:05:33 -04:00
  • cc03093705 Add unit and integration tests for synthetic data kit provider Alina Ryan 2025-05-29 16:24:24 -04:00
  • f86f107f15 (feat) Add synthetic_data_kit provider integration for synthetic_data_generation API Alina Ryan 2025-05-29 14:56:12 -04:00
  • e867501073 feat: add synthetic_data_generation API scaffolding (no provider) Alina Ryan 2025-05-28 13:48:43 -04:00
  • 7c51bf87f9 docs: update building distro to use container commands over llama stack run Bobbins228 2025-05-19 13:06:35 +01:00
  • 390ace8748
    Apply suggestions from code review Ben Browning 2025-05-30 07:14:12 -04:00
  • 73456878e5 feat: Enable ingestion of custom embeddings Francisco Javier Arceo 2025-05-29 20:58:41 -04:00
  • 09ab94b8ab blacken-docs formatting for OpenAI API docs Ben Browning 2025-05-29 20:12:20 -04:00
  • d8f8dba2e0 docs: Add OpenAI API compatibility page Ben Browning 2025-05-29 20:06:03 -04:00
  • f2c2a05f58 OpenAI compat embeddings API Hardik Shah 2025-05-29 15:27:59 -07:00
  • 2d681a9120 OpenAI compat embeddings API Hardik Shah 2025-05-29 15:27:59 -07:00
  • 6151f336b9 postgres Eric Huang 2025-05-29 12:57:01 -07:00
  • 6af13bbbf0
    Merge branch 'main' into watsonx_health_check Sumit Jaiswal 2025-05-30 00:26:52 +05:30
  • 4c83cfa7cc refactor: remove container from list of run image types Bobbins228 2025-05-15 14:49:48 +01:00
  • afdb11b561 update strict to false in json schema mode jhpiedrahitao 2025-05-29 10:00:06 -05:00
  • bde502ef59 chore: fix flaky distro_codegen script Bobbins228 2025-05-29 11:40:58 +01:00
  • f967e64490
    update the fn comment Sumit Jaiswal 2025-05-29 12:28:10 +05:30
  • 2087c18105 remove eval deps Raghotham Murthy 2025-05-28 22:35:38 -07:00
  • 73776e48b8 add back rag deps Raghotham Murthy 2025-05-28 22:26:09 -07:00
  • e145a410b7 add back eval deps Raghotham Murthy 2025-05-28 22:25:40 -07:00
  • c99b62b76a remove rag Raghotham Murthy 2025-05-28 22:24:27 -07:00
  • 02ba6973c7 remove basic scoring Raghotham Murthy 2025-05-28 22:24:03 -07:00
  • fa9dd0586a cleanup Raghotham Murthy 2025-05-28 22:17:21 -07:00
  • 2d5d05a2b4 feat: small ollama package Raghotham Murthy 2025-05-28 21:13:48 -07:00
  • 414642b092 fix Raghotham Murthy 2025-05-28 17:31:32 -07:00
  • fb47cc0931 uv ness Raghotham Murthy 2025-05-28 17:09:10 -07:00
  • 6a004e99ed Merge branch 'main' into nvidia-e2e-notebook Jash Gulabrai 2025-05-28 17:50:38 -04:00
  • f5cb965f0f Merge branch 'main' into nvidia-e2e-notebook Jash Gulabrai 2025-05-28 17:48:15 -04:00
  • bc58bbf94c
    remove unused asyncio lib Sumit Jaiswal 2025-05-29 02:16:29 +05:30
  • 2e81a8f020
    watsonx health check implementation Sumit Jaiswal 2025-05-29 01:41:22 +05:30
  • b883ce9a06 add unit test Ashwin Bharambe 2025-05-28 12:09:41 -07:00
  • cda44a77e6 fix(responses): use input, not original_input when storing the Response Ashwin Bharambe 2025-05-28 11:56:42 -07:00
  • 5c26b10c53
    chore: use groups when running commands Sébastien Han 2025-05-28 09:42:27 +02:00
  • de53390c1c responses table, responses details Eric Huang 2025-05-27 21:23:10 -07:00
  • 7a701d5020
    Merge branch 'main' into providers Francisco Arceo 2025-05-27 19:41:11 -06:00
  • 0c494d0b9a
    Update .readthedocs.yaml raghotham 2025-05-27 16:06:12 -07:00
  • c053b0e32c
    fix: build docs without requirements.txt raghotham 2025-05-27 15:56:44 -07:00
  • d4b0b46275 fix: chat completion with more than one choice Eric Huang 2025-05-27 13:56:43 -07:00
  • 089a1578e9 uncomment Eric Huang 2025-05-27 14:48:56 -07:00
  • 9472c1090e
    chore: use starlette built-in Route class Sébastien Han 2025-05-26 15:19:30 +02:00
  • 49f5d33ec7
    chore: use dependency-groups for dev Sébastien Han 2025-05-27 22:00:59 +02:00
  • 01ad876012 feat: fine grained access control policy Gordon Sim 2025-05-06 18:54:58 +01:00
  • 7dc010727c
    chore: bump uv version Sébastien Han 2025-05-27 22:34:51 +02:00
  • 1d7b19312a build: Bump version to 0.2.8 v0.2.8 release-0.2.8 github-actions[bot] 2025-05-27 20:27:39 +00:00
  • 8d15a49864 docs: add post training to providers list Charlie Doern 2025-05-27 09:36:18 -04:00
  • bf8d76f19b fixes Ashwin Bharambe 2025-05-27 12:58:44 -07:00
  • cad646478f fixes, update test to be more robust Ashwin Bharambe 2025-05-27 12:46:03 -07:00
  • f31e9062c3 chore: add ui/package.json to manifest Eric Huang 2025-05-27 12:28:00 -07:00
  • a22ba377c5
    fix(docs): Remove unused import. jsell-rh 2025-05-27 15:20:03 -04:00
  • b45cc42202
    chore: remove usage of load_tiktoken_bpe Sébastien Han 2025-05-27 10:49:03 +02:00
  • 8638bc2767
    fix: convert boolean string to boolean Sébastien Han 2025-05-27 20:43:38 +02:00
  • 70d3e4bd67 fix Ashwin Bharambe 2025-05-25 22:00:33 -07:00
  • 12dfcd11d9 fix Ashwin Bharambe 2025-05-25 19:08:36 -07:00
  • cad1c9b4c9 feat(responses): add output_text delta events to responses Ashwin Bharambe 2025-05-25 17:28:13 -07:00
  • 6aedcacc83 Release candidate 0.2.8rc4 v0.2.8rc4 github-actions[bot] 2025-05-27 17:37:19 +00:00
  • 2e269194aa Release candidate 0.2.8rc3 v0.2.8rc3 github-actions[bot] 2025-05-27 17:12:31 +00:00
  • 71c3e1a839
    chore: remove depencendies.json Sébastien Han 2025-05-27 17:37:16 +02:00
  • ffeca80558 Release candidate 0.2.8rc2 v0.2.8rc2 github-actions[bot] 2025-05-27 13:36:10 +00:00
  • 51c5016cb2 chore: fix visible comments in pr template Bobbins228 2025-05-27 11:07:52 +01:00
  • 8450400960 docs: fix evals notebook preview Bobbins228 2025-05-27 10:58:20 +01:00
  • 6a561bf239 Release candidate 0.2.8rc1 v0.2.8rc1 github-actions[bot] 2025-05-27 05:51:42 +00:00
  • a21ff2e7d5 test: disable test_inference_store test urrrggg Ashwin Bharambe 2025-05-26 22:46:31 -07:00
  • 374ec349e2 fix: index non-MCP toolgroups at registration time Ashwin Bharambe 2025-05-26 19:57:24 -07:00
  • 311b0e469b
    fix: handle None external_providers_dir in build with run arg Ignas Baranauskas 2025-05-26 15:50:33 +01:00
  • 809e7650a7
    chore: mark blobpath as optional Sébastien Han 2025-05-26 21:57:15 +02:00
  • 7b9a6eda63 squash: address comments Michael Dawson 2025-05-26 13:40:35 -04:00