Commit graph

  • 18fba7ca74 fix: Update requirements.txt via uv-export to resolve pre-commit failure skamenan7 2025-07-15 14:00:00 -04:00
  • d21cfce925 Reorganize documentation on the webpage Kelly Brown 2025-07-08 09:03:02 -04:00
  • 2298d2473c Add .worktrees/ to .gitignore for personal workflow skamenan7 2025-07-15 13:25:55 -04:00
  • e5377d078d fix: address reviewer feedback - improve conditional imports and remove provider alias logic\n\n- Improve conditional import approach with better documentation\n- Remove provider-specific alias logic from sku_list.py\n- Conditional imports are necessary because llama4 requires torch\n- Addresses @ashwinb and @raghotham feedback while maintaining compatibility skamenan7 2025-07-10 12:06:14 -04:00
  • 61dc2a9c58 refactor(llama4): remove duplicate implementation, update imports to llama-models, add comprehensive test for tool calling fix (issue #2584)\n\n- Removes all old llama4 code from llama-stack\n- Updates all relevant imports to use llama-models\n- Adds robust pytest to demonstrate arguments_json fix\n- Updates config/scripts as needed for new structure\n- Resolves merge conflicts with updated main branch\n- Fixes mypy and ruff issues skamenan7 2025-07-10 09:39:33 -04:00
  • 8deb9cd1cf
    Update .github/workflows/integration-tests.yml ehhuang 2025-07-15 09:38:35 -07:00
  • 126d6698a7 test(models): convert decode_assistant_message test from unittest to pytest skamenan7 2025-07-09 08:57:48 -04:00
  • 857496ea3e fix: Resolve Llama4 tool calling 500 errors (Issue #2584) skamenan7 2025-07-08 16:20:19 -04:00
  • c0022be33d
    Merge branch 'main' into pgvector-openai-compat Francisco Arceo 2025-07-15 11:36:57 -04:00
  • f097da7a31 updating to use execute_values Francisco Javier Arceo 2025-07-15 11:34:31 -04:00
  • 9a5d47e085 fix: stop image_name from being cast to an integer Nathan Weinberg 2025-07-14 23:38:16 -04:00
  • 82165a111e
    Merge branch 'main' into vectordb_name Francisco Arceo 2025-07-15 10:32:06 -04:00
  • 1a47975837 explicit names in function Francisco Javier Arceo 2025-07-15 10:29:42 -04:00
  • 532c1c3c16
    docs: update outdated llama stack client documentation Bobbins228 2025-07-15 14:40:05 +01:00
  • 5679d4dfd6
    Merge branch 'main' into fix/issue-2584-llama4-tool-calling Sumanth Kamenani 2025-07-15 09:12:15 -04:00
  • 822e87907c
    chore: use uv build backend Sébastien Han 2025-07-10 11:59:06 +02:00
  • daeed865df fix: rebase error Wen Zhou 2025-07-15 13:47:49 +02:00
  • 201824946e update: code review Wen Zhou 2025-07-15 13:29:25 +02:00
  • 2ce9402593 update: code review Wen Zhou 2025-07-03 17:11:52 +02:00
  • 0b051c037b update: add validation on non-string type Wen Zhou 2025-06-30 10:12:48 +02:00
  • 8563c76f88 feat: add optional metrics under API /providers Wen Zhou 2025-06-30 09:10:43 +02:00
  • dd6e6f9ac2 chore: Adding OpenAI Vector Stores Files API compatibility for PGVector Francisco Javier Arceo 2025-07-15 00:02:23 -04:00
  • bd8c1cc071
    Merge branch 'main' into vectordb_name Francisco Arceo 2025-07-14 23:42:45 -04:00
  • b01c72a7de removing provider_vector_db from VectorIORouter.openai_create_vector_store, VectorIO.openai_create_vector_store, and PGVector Francisco Javier Arceo 2025-07-14 23:31:34 -04:00
  • dd00bff776
    Merge branch 'main' into add-llamacpp-provider Young Han 2025-07-14 17:58:21 -07:00
  • 2153957ab6 docs Young Han 2025-07-14 17:52:27 -07:00
  • 723a870171 docs: add detailed explanation Young Han 2025-07-14 17:51:28 -07:00
  • ccef7e325d fix: add kwargs in sample_run_config Young Han 2025-07-14 17:35:43 -07:00
  • d3d50121cf fix: LLAMACPP_URL and LLAMACPP_API_KEY format Young Han 2025-07-14 17:25:18 -07:00
  • f69ae45127 query_available_models() -> list[str] -> check_model_availability(model) -> bool Matthew Farrellee 2025-07-14 19:20:15 -04:00
  • c2ab8988e6 Merge branch 'main' into allow-dynamic-models-nvidia Matthew Farrellee 2025-07-14 19:01:28 -04:00
  • 6a1cb00deb chore: remove tests.yaml Eric Huang 2025-07-14 15:35:50 -07:00
  • 143bc7eb74 Fix adding index for BM25 func Varsha Prasad Narsing 2025-07-12 17:09:50 -07:00
  • ac039e6bac Fix formatting and finalize Milvus BM25 integration Varsha Prasad Narsing 2025-07-07 12:48:40 -07:00
  • 86cca275c1 Feat: Implement keyword search in milvus Varsha Prasad Narsing 2025-05-22 15:21:40 -07:00
  • 89b1052806 query_available_models() -> list[str] -> check_model_availability(model) -> bool Matthew Farrellee 2025-07-14 17:42:37 -04:00
  • b884bc490b feat: pre-commit result Young Han 2025-07-14 14:32:58 -07:00
  • b6a334604c Merge branch 'main' into allow-dynamic-models-ollama Matthew Farrellee 2025-07-14 17:29:18 -04:00
  • a8e52264ff chore: add issue template for technical debt Nathan Weinberg 2025-07-14 17:11:20 -04:00
  • 4c53db9f50 fix agent test_rag Hardik Shah 2025-07-14 13:35:57 -07:00
  • f65a260cdd feat: pre-commit results Young Han 2025-07-14 13:21:33 -07:00
  • c1cc3d1ac3
    Merge branch 'main' into kvstore-refactor Francisco Arceo 2025-07-14 15:25:33 -04:00
  • 5850de7dc1 test: add tests against published client Eric Huang 2025-07-14 12:09:35 -07:00
  • a2cffb7d0e
    Merge branch 'main' into kvstore-refactor Francisco Arceo 2025-07-14 15:00:49 -04:00
  • 3d86619361 patch vectordb methods Francisco Javier Arceo 2025-07-14 14:56:06 -04:00
  • e083e09401 fix: address reviewer feedback - improve conditional imports and remove provider alias logic\n\n- Improve conditional import approach with better documentation\n- Remove provider-specific alias logic from sku_list.py\n- Conditional imports are necessary because llama4 requires torch\n- Addresses @ashwinb and @raghotham feedback while maintaining compatibility skamenan7 2025-07-10 12:06:14 -04:00
  • cb17594611 refactor(llama4): remove duplicate implementation, update imports to llama-models, add comprehensive test for tool calling fix (issue #2584)\n\n- Removes all old llama4 code from llama-stack\n- Updates all relevant imports to use llama-models\n- Adds robust pytest to demonstrate arguments_json fix\n- Updates config/scripts as needed for new structure\n- Resolves merge conflicts with updated main branch\n- Fixes mypy and ruff issues skamenan7 2025-07-10 09:39:33 -04:00
  • bdf251b870 test(models): convert decode_assistant_message test from unittest to pytest skamenan7 2025-07-09 08:57:48 -04:00
  • c37d831911 fix: Resolve Llama4 tool calling 500 errors (Issue #2584) skamenan7 2025-07-08 16:20:19 -04:00
  • 68cca8dae2
    Merge branch 'main' into pr2750 raghotham 2025-07-14 11:39:07 -07:00
  • 257cde3041 strip @pytest.mark.asyncio Matthew Farrellee 2025-07-14 14:27:11 -04:00
  • ea35358853 Merge branch 'main' into infra-for-dynamic-model-detection Matthew Farrellee 2025-07-14 14:25:40 -04:00
  • 770c20e36b query_available_models() -> list[str] -> check_model_availability(model) -> bool Matthew Farrellee 2025-07-14 14:08:44 -04:00
  • 2c3513510d docs: fix building distro link Eric Huang 2025-07-14 11:21:01 -07:00
  • c30e343fbb
    Merge branch 'main' into rm-faiss-file raghotham 2025-07-14 10:57:14 -07:00
  • 061911b993 updating weaviate and pgvector classes Francisco Javier Arceo 2025-07-14 13:40:04 -04:00
  • 938786733c chore: Migrating kvstore into openai_vector_store_mixin.py Francisco Javier Arceo 2025-07-14 13:05:19 -04:00
  • 9613c63ca6 docs: clarify run.yaml files are starting points for customization skamenan7 2025-07-14 11:22:15 -04:00
  • 4087dcdd16 chore: update OpenAPI spec files after brave search integration skamenan7 2025-07-08 09:50:03 -04:00
  • 533c1323b8 feat: add proper BuiltinTool support for both websearch providers skamenan7 2025-07-07 15:41:41 -04:00
  • a0a8b86fc8 fix(brave-search): change tool name and standardize response format skamenan7 2025-07-07 15:13:56 -04:00
  • ec2ce3ef9d feat(starter): add Brave search to tool groups skamenan7 2025-07-05 09:36:05 -04:00
  • 3066f5992d chore: block asyncio marks in tests Matthew Farrellee 2025-07-14 07:40:34 -04:00
  • 253b74a1e4
    test: add unit tests for vector db search mode validation Bobbins228 2025-05-28 14:34:09 +01:00
  • 82730fd325
    feat: add input validation for search mode of rag query Bobbins228 2025-05-27 10:14:41 +01:00
  • fd8da5fa67
    Merge branch 'main' into rm-faiss-file raghotham 2025-07-13 23:01:42 -07:00
  • a562d81825 docs: model name Young Han 2025-07-13 09:49:43 -07:00
  • 5517950edc updated client Francisco Javier Arceo 2025-07-13 00:03:25 -04:00
  • a520430ebb updated font to make dark mode more readable Francisco Javier Arceo 2025-07-12 01:08:23 -04:00
  • dc822226cb fix: telemetry config Young Han 2025-07-12 18:00:46 -07:00
  • 9b3d7e85ff feat: add llamacpp in registry Young Han 2025-07-12 16:28:22 -07:00
  • ec73d0d55b init: first remote llamacpp implementation Young Han 2025-07-12 16:28:08 -07:00
  • 6e2663b8d9
    chore(github-deps): bump medyagh/setup-minikube from 0.0.19 to 0.0.20 dependabot[bot] 2025-07-12 20:16:04 +00:00
  • f8311c827d adding vector store detailed view Francisco Javier Arceo 2025-07-12 00:28:52 -04:00
  • 466e234591 feat: Adding UI support for Vector Stores Francisco Javier Arceo 2025-07-12 00:19:26 -04:00
  • 9b5f90eefa tavily changes anigasan 2025-07-11 20:03:27 -07:00
  • ac643bfb0e
    Merge branch 'main' into vectordb_name Francisco Arceo 2025-07-11 22:41:52 -04:00
  • 78bf4558ba Merge branch 'main' of https://github.com/anigasan/llama-stack anigasan 2025-07-11 19:28:49 -07:00
  • 46148bfe83 made changes to tavily_search, simplified config logic anigasan 2025-07-07 12:39:33 -07:00
  • 1c4de89b30 chore: Exposing vector stores bug Francisco Javier Arceo 2025-07-11 22:08:09 -04:00
  • 0f74943154 adding test to verify new expected behavior Francisco Javier Arceo 2025-07-11 21:58:35 -04:00
  • a01a679914 chore: block network access from unit tests Matthew Farrellee 2025-07-11 21:24:17 -04:00
  • 3d83322003 fix safety in starter Hardik Shah 2025-07-11 16:42:24 -07:00
  • 95b6dc69bf updated docs Francisco Javier Arceo 2025-07-11 16:29:30 -04:00
  • cfde4af3ab simplyfing Francisco Javier Arceo 2025-07-11 16:25:23 -04:00
  • d361154102 reverting to original call order for a simpler change Francisco Javier Arceo 2025-07-11 16:10:10 -04:00
  • bc65d5c9ef update api_key_from_config initialization jhpiedrahitao 2025-07-11 15:07:22 -05:00
  • 56811a1483 reverting back to original order of parameters Francisco Javier Arceo 2025-07-11 15:47:24 -04:00
  • 22f2484edc moving order of parameters Francisco Javier Arceo 2025-07-11 15:20:36 -04:00
  • 7ae99f33e7 adjusting vector_db_id Francisco Javier Arceo 2025-07-11 15:07:07 -04:00
  • 67f1131040
    Merge branch 'main' into vectordb_name Francisco Arceo 2025-07-11 13:46:16 -04:00
  • 9b82ac7376 Add together dep to unit tests as well Ben Browning 2025-07-11 13:10:55 -04:00
  • f4af72d98e update nvidia/test_supervised_fine_tuning.py to simulate an available non-llama model Matthew Farrellee 2025-07-11 13:03:31 -04:00
  • e3a3f86cf7 chore: default to pytest asyncio-mode=auto Matthew Farrellee 2025-07-11 11:48:58 -04:00
  • 03e07f1236 Unit tests need litellm now... Ben Browning 2025-07-11 10:29:00 -04:00
  • fa9e2dd543 fix: Don't cache clients for passthrough auth providers Ben Browning 2025-07-11 10:11:31 -04:00
  • 51787a93f6 feat: allow dynamic model registration for ollama inference provider Matthew Farrellee 2025-07-11 10:08:49 -04:00
  • d3b637e6ab chore(api): add mypy coverage to chat_format Mustafa Elbehery 2025-07-08 19:49:03 +02:00
  • 74103e4eee chore(api): add mypy coverage to meta_reference_inference Mustafa Elbehery 2025-07-08 23:11:26 +02:00
  • e3de28d872 chore: add mypy coverage to meta_llama3_multimodal Mustafa Elbehery 2025-07-10 11:50:54 +02:00