Commit graph

  • 86a3c6da88 update Models to models reidliu 2025-02-26 20:27:18 +08:00
  • 52efe45e9f chore: update model list reidliu 2025-02-26 18:48:54 +08:00
  • baa5193be8 fix: Avoid unexpected keyword argument for sentence_transformers Luis Tomas Bolivar 2025-02-26 09:14:52 +01:00
  • 64767578d6
    fix(CLI): Missing default for --image-type in stack run command Yuan Tang 2025-02-26 05:11:54 -05:00
  • 2f01bcdae2 update reidliu 2025-02-26 17:11:04 +08:00
  • bab75d7acb fix the pre-commit new line issue1 reidliu 2025-02-26 17:03:59 +08:00
  • 0f4f8abf8e fix the pre-commit new line issue reidliu 2025-02-26 17:01:32 +08:00
  • f227045b6b refine Botao Chen 2025-02-25 23:28:05 -08:00
  • 0da8974526 docs: update build doc reidliu 2025-02-26 09:46:26 +08:00
  • 87be396e47 docs: update the downloaded list doc reidliu 2025-02-26 11:52:52 +08:00
  • 3cd387aff6 fix ci-tests distro Ashwin Bharambe 2025-02-25 22:04:51 -08:00
  • bf8283a925 feat: add (openai, anthropic, gemini) providers via litellm Ashwin Bharambe 2025-02-25 12:13:58 -08:00
  • 88768a93eb small enhancement, immaterial mostly Ashwin Bharambe 2025-02-25 14:47:51 -08:00
  • fea9ef59b7 Move OpenAI compat utilities from nvidia to openai_compat Ashwin Bharambe 2025-02-25 13:21:45 -08:00
  • cc24967f8c removed executorch submodule Jeff Tang 2025-02-25 19:48:11 -08:00
  • 14822c4028 fix: fix the pre-commit issue reidliu 2025-02-26 10:10:58 +08:00
  • 81aed4c1e7 upload notebook Botao Chen 2025-02-25 17:35:23 -08:00
  • da5357f09c feat: remove special handling of builtin::rag tool Eric Huang 2025-02-25 17:24:36 -08:00
  • 822ffe9f2e
    Fix diff Yuan Tang 2025-02-25 20:06:58 -05:00
  • de777be9ee
    build: Merge redundant files field in .pre-commit-config.yaml Yuan Tang 2025-02-25 16:41:09 -05:00
  • 32e89191c2 fix ollama.py bug Kai Wu 2025-02-25 15:08:48 -08:00
  • 733b9c07b5 pre-commit Kai Wu 2025-02-25 13:42:02 -08:00
  • deae02f313 Docs: Remove $ from client CLI ref to add valid copy and paste ability Kelly Brown 2025-02-25 16:41:44 -05:00
  • dd9bb9300a
    Update based on feedback Yuan Tang 2025-02-25 16:34:45 -05:00
  • 25c375471b
    Update index.md to include 0.1.4 raghotham 2025-02-25 13:32:49 -08:00
  • fdc620857c Update Ashwin Bharambe 2025-02-25 13:21:45 -08:00
  • de1e70f7d8 Update Ashwin Bharambe 2025-02-25 12:16:35 -08:00
  • 39fbe9c608 Update (base update) Ashwin Bharambe 2025-02-25 12:16:35 -08:00
  • 8a86a96786 Adding Containerfile for playground and GitHub workflow Jamie Land 2025-02-25 11:47:10 -05:00
  • ed2bd60bd9 add ollama embedding config and fix sqlite_vec db Kai Wu 2025-02-25 11:25:23 -08:00
  • 056432fb14 "feat: completing text /chat-completion and /completion provider and e1e tests" Haiping Zhao 2025-02-23 10:15:08 -08:00
  • 902eb9dae7 fix: include timezone in Agent steps' timestamps Eric Huang 2025-02-25 09:47:35 -08:00
  • 5a05553e93 feat: adding a Makefile and a test script for sqlite-vec Francisco Javier Arceo 2025-02-25 12:45:53 -05:00
  • f6a0c3e97d
    fix: Raise exception when tool call result is None Yuan Tang 2025-02-25 12:17:36 -05:00
  • 0942329ec6
    docs: move sections from README to docs Sébastien Han 2025-02-18 21:16:35 +01:00
  • 8eb4f7fcb6
    refactor(server): replace print statements with logger Sébastien Han 2025-02-25 15:00:55 +01:00
  • 8eefbfecdd skip -> xfail for image tests Matthew Farrellee 2025-02-25 11:03:38 -05:00
  • 27714fb3b7
    Update Yuan Tang 2025-02-25 10:59:51 -05:00
  • 3665bccac2
    Add defaults Yuan Tang 2025-02-25 10:59:05 -05:00
  • b41afa5843
    Merge branch 'meta-llama:main' into main Jamie Land 2025-02-25 10:58:53 -05:00
  • 9f68836d7e
    build: Add dotenv file for running tests with uv Yuan Tang 2025-02-25 10:56:27 -05:00
  • d4c3aee490 remove redundant defensive checks, fastapi does appropriate request validation Matthew Farrellee 2025-02-25 07:17:57 -05:00
  • 9b7b0c4c8d Merge branch 'main' into update-nvidia-embedding Matthew Farrellee 2025-02-25 06:52:00 -05:00
  • efb6428b60 update to a public function reidliu 2025-02-25 18:44:06 +08:00
  • cfdb9c9b57 chore: add subcommands description in help reidliu 2025-02-22 22:17:34 +08:00
  • 0fb674d77b address comment Botao Chen 2025-02-24 23:53:31 -08:00
  • 0a62ceecb7 refine Botao Chen 2025-02-24 20:09:17 -08:00
  • 31ad6c780c resolve conflict Botao Chen 2025-02-24 19:52:08 -08:00
  • 11fc59e9e5 Merge remote-tracking branch 'origin/main' into hf_format_checkpointer Botao Chen 2025-02-24 19:41:58 -08:00
  • f23550ce95 refine Botao Chen 2025-02-24 19:37:52 -08:00
  • 6748e2abcd refine Botao Chen 2025-02-24 19:26:10 -08:00
  • 922c326111
    Update Llama_Stack_Benchmark_Evals.ipynb Hardik Shah 2025-02-24 18:04:25 -08:00
  • 266eacea49
    Update getting_started.ipynb Hardik Shah 2025-02-24 18:01:14 -08:00
  • 431ae6aa97 use system python and path for notebook Hardik Shah 2025-02-24 17:41:05 -08:00
  • c30394d0d7 fix pre-commit Charlie Doern 2025-02-24 19:59:57 -05:00
  • f695bceccd LocalInferenceImpl update for LS013 Jeff Tang 2025-02-24 16:54:25 -08:00
  • d82c8ac22b init commit Botao Chen 2025-02-24 16:30:17 -08:00
  • 55ba5b3def init commit Botao Chen 2025-02-24 16:25:58 -08:00
  • 7946285745 Bump version to 0.1.4 v0.1.4 Ashwin Bharambe 2025-02-24 15:53:30 -08:00
  • 9ffbcb87c4 update the header reidliu 2025-02-25 07:35:04 +08:00
  • a9d7f63c1f feat: add prompt-format list reidliu 2025-02-23 17:41:06 +08:00
  • ec52c46ff2 tests: add a ci-tests distro template for running e2e tests Ashwin Bharambe 2025-02-24 14:03:54 -08:00
  • 4400d9028f Release candidate 0.1.4rc3 v0.1.4rc3 github-actions[bot] 2025-02-24 21:20:18 +00:00
  • 8ead5c216a fix: Get builtin tool calling working in remote-vllm Ben Browning 2025-02-24 15:24:17 -05:00
  • 44be0762f1 test: fix test_tool_choice Eric Huang 2025-02-24 11:50:05 -08:00
  • c41072f6b2 fix test asserts Hardik Shah 2025-02-24 11:51:34 -08:00
  • 9aec73ffe3 added dependency Chantal D Gama Rose 2025-02-24 19:15:26 +00:00
  • f47ebb54f8 adding back requests as dep Chantal D Gama Rose 2025-02-24 19:08:14 +00:00
  • d8e864da34 fixed pre-commit checks Chantal D Gama Rose 2025-02-24 19:05:48 +00:00
  • ca6a12e362 Merge remote-tracking branch 'upstream/main' into add_nvidia_safety_provider Chantal D Gama Rose 2025-02-24 18:55:08 +00:00
  • b9564fb435 Fixes for safety provider added to nvidia distro Chantal D Gama Rose 2025-02-24 18:52:56 +00:00
  • 3aa3937560 fix: build_venv expects an extra argument Charlie Doern 2025-02-24 11:06:03 -05:00
  • 9a80776c0e fix: set default tool_prompt_format in inference api Eric Huang 2025-02-24 10:09:57 -08:00
  • fea46fb334 Release candidate 0.1.4.dev3 v0.1.4.dev3 github-actions[bot] 2025-02-24 17:36:59 +00:00
  • 238d69b3cf Update llama_stack/distribution/start_stack.sh Ashwin Bharambe 2025-02-21 08:58:03 -08:00
  • a6b1294d39 refactor: combine start scripts for each env Charlie Doern 2025-02-18 10:09:04 -05:00
  • c8e9b19aca
    docs: remove redundant installation instructions Sébastien Han 2025-02-18 16:56:00 +01:00
  • 0c4591a73d fix: image_name defaults to none Charlie Doern 2025-02-23 19:51:30 -05:00
  • 8dc9be9aa3 Ensure build_container does not fail on missing special_pip_deps Luis Tomas Bolivar 2025-02-24 14:57:39 +01:00
  • bc89d8b5c9
    fix: avoid failure when no special pip deps and better exit Sébastien Han 2025-02-24 12:33:36 +01:00
  • 36794a1c02
    fix: resolve type hint issues and import dependencies Sébastien Han 2025-02-20 17:18:32 +01:00
  • d18bd7187a
    Update index.md Yuan Tang 2025-02-23 22:18:22 -05:00
  • 8eb56f466d
    docs: Add vLLM to the list of inference providers in concepts page Yuan Tang 2025-02-23 22:09:45 -05:00
  • a3fa992af4 feat: add --run to llama stack build Charlie Doern 2025-02-19 14:37:55 -05:00
  • 0fb4dafa24 update ruff pre-commit Ashwin Bharambe 2025-02-23 16:49:22 -08:00
  • 0b37299af6 fix: update virtualenv building so llamastack- prefix is not added, make notebook experience easier Ashwin Bharambe 2025-02-23 16:45:54 -08:00
  • 4d8a96a961 fix the 404 reidliu 2025-02-24 07:26:02 +08:00
  • 8b3110295a docs: update the hyperlink name reidliu 2025-02-24 07:18:44 +08:00
  • 6608c7fed9 refactor: support downloading any model from HF Charlie Doern 2025-02-06 19:48:50 -05:00
  • 5a9cb0fd4f fix: fix the describe table display issue reidliu 2025-02-23 14:20:17 +08:00
  • 9867a4dfef chore: update the zero_to_hero_guide doc link reidliu 2025-02-23 07:58:00 +08:00
  • 4f8f0beae2
    Unregister for ollama remote provider Yuan Tang 2025-02-21 22:38:44 -05:00
  • 6abfe0c43b
    fix: Unregister a model from registry if not being served Yuan Tang 2025-02-20 13:04:15 -05:00
  • 00b2a65084 add nemo retriever text embedding models to nvidia inference provider Matthew Farrellee 2025-02-21 20:49:46 -06:00
  • 301a0689f5 fix typo: doument -> document Matthew Farrellee 2025-02-21 20:42:55 -06:00
  • 81b3e65897 chore: update download error message reidliu 2025-02-22 08:56:31 +08:00
  • 8f221e4a33 test: do not overwrite agent_config Eric Huang 2025-02-21 16:37:20 -08:00
  • 01aef1382c test: fix test_rag_agent test Eric Huang 2025-02-21 15:19:26 -08:00
  • ad5ea63140 feat: add substring search option for model list reidliu 2025-02-20 14:33:41 +08:00
  • b54d896ce7 handle error and update tests for new client Matthew Farrellee 2025-02-21 16:38:39 -06:00