Commit graph

  • 1a044ef894
    fix: Raise exception when tool call result is None (#1253) Yuan Tang 2025-02-25 13:10:50 -05:00
  • 73a0c7a0e7
    LocalInferenceImpl update for LS013 (#1242) Jeff Tang 2025-02-25 09:58:34 -08:00
  • dc3c881ffe
    fix: include timezone in Agent steps' timestamps (#1247) ehhuang 2025-02-25 09:49:25 -08:00
  • 1bd080c23d
    build: hint on Python version for uv venv (#1172) Sébastien Han 2025-02-25 16:37:45 +01:00
  • 30f79fafcb
    fix: Update Llama_Stack_Benchmark_Evals.ipynb (#1246) Hardik Shah 2025-02-24 18:22:42 -08:00
  • a1fe3c30dd
    fix: Update getting_started.ipynb (#1245) Hardik Shah 2025-02-24 18:22:32 -08:00
  • de878e15a9
    fix: pre-commit updates (#1243) Charlie Doern 2025-02-24 20:20:29 -05:00
  • 4684fd3f8d
    refactor: combine start scripts for each env (#1139) Charlie Doern 2025-02-24 19:53:31 -05:00
  • 47f8c592b9 Bump version to 0.1.4 github-actions[bot] 2025-02-24 21:20:18 +00:00
  • 7946285745 Bump version to 0.1.4 v0.1.4 Ashwin Bharambe 2025-02-24 15:53:30 -08:00
  • 9b0f783e54
    test: add a ci-tests distro template for running e2e tests (#1237) Ashwin Bharambe 2025-02-24 14:43:21 -08:00
  • 4400d9028f Release candidate 0.1.4rc3 v0.1.4rc3 github-actions[bot] 2025-02-24 21:20:18 +00:00
  • 27a08b7266 test fix for sometimes tools get called more than once Hardik Shah 2025-02-24 13:16:40 -08:00
  • e8f4efba44
    test: fix test_tool_choice (#1234) ehhuang 2025-02-24 12:42:42 -08:00
  • 14c38acf97
    fix: set default tool_prompt_format in inference api (#1214) ehhuang 2025-02-24 12:38:37 -08:00
  • c4987bc349
    fix: avoid failure when no special pip deps and better exit (#1228) Sébastien Han 2025-02-24 19:18:52 +01:00
  • d6356f822a fix: remove UV_SYSTEM_PYTHON from getting started notebook since llama stack build detects notebook environment Ashwin Bharambe 2025-02-24 10:05:02 -08:00
  • e8e8fe7c93 fix: add LLAMA_STACK_CLIENT_DIR mount when installing in docker from source Ashwin Bharambe 2025-02-24 10:00:57 -08:00
  • fea46fb334 Release candidate 0.1.4.dev3 v0.1.4.dev3 github-actions[bot] 2025-02-24 17:36:59 +00:00
  • 641549c631 Add llama stack client overrides also; necessary for correct docker building Ashwin Bharambe 2025-02-24 07:51:02 -08:00
  • 1842eeb96f
    docs: small fixes (#1224) Reid 2025-02-24 20:59:58 +08:00
  • 0973d386e6 fix: update build_container.sh to ensure llama-models is installed first Ashwin Bharambe 2025-02-23 21:47:18 -08:00
  • 17162b9978
    docs: Add vLLM to the list of inference providers in concepts and providers pages (#1227) Yuan Tang 2025-02-23 23:16:30 -05:00
  • 34e3faa4e8
    feat: add --run to llama stack build (#1156) v0.1.4rc2 Charlie Doern 2025-02-23 22:06:09 -05:00
  • 6227e1e3b9
    fix: update virtualenv building so llamastack- prefix is not added, make notebook experience easier (#1225) Ashwin Bharambe 2025-02-23 16:57:11 -08:00
  • 19ae4b35d9
    docs: Adding Provider sections to docs (#1195) Francisco Arceo 2025-02-22 12:59:34 -07:00
  • b890d7a611 Test be not having prints yo Ashwin Bharambe 2025-02-21 16:43:00 -08:00
  • c9e08cc0a8
    test: do not overwrite agent_config (#1216) v0.1.4rc1 ehhuang 2025-02-21 16:38:56 -08:00
  • 187524d4ae
    feat: add substring search for model list (#1099) Reid 2025-02-22 08:38:10 +08:00
  • 5be628f637 Add test jsons to MANIFEST for now Ashwin Bharambe 2025-02-21 16:25:51 -08:00
  • 45ffe87d7c Kill noise from test output Ashwin Bharambe 2025-02-21 15:37:23 -08:00
  • bf38d0aba0
    test: fix test_rag_agent test (#1215) ehhuang 2025-02-21 15:24:28 -08:00
  • e7d261ef4a Fix test infra, sentence embeddings mixin Ashwin Bharambe 2025-02-21 15:10:10 -08:00
  • 182608d4bf better test naming Ashwin Bharambe 2025-02-21 14:24:09 -08:00
  • ab54b8cd58
    feat(providers): support non-llama models for inference providers (#1200) Ashwin Bharambe 2025-02-21 13:21:28 -08:00
  • 9bbe34694d
    ci: add mypy for static type checking (#1101) Sébastien Han 2025-02-21 22:15:40 +01:00
  • 25fddccfd8
    feat: tool outputs metadata (#1155) ehhuang 2025-02-21 13:15:31 -08:00
  • 36162c8c82 fix(ollama): register model with the helper first so it gets normalized Ashwin Bharambe 2025-02-21 12:51:38 -08:00
  • 0fe071764f
    feat(1/n): api: unify agents for handling server & client tools (#1178) Xi Yan 2025-02-21 11:48:27 -08:00
  • 992f865b2e
    chore: move embedding deps to RAG tool where they are needed (#1210) Ashwin Bharambe 2025-02-21 11:33:41 -08:00
  • 11697f85c5
    fix: pull ollama embedding model if necessary (#1209) Ashwin Bharambe 2025-02-21 10:35:56 -08:00
  • 840fae2259
    fix: Updating images so that they are able to run without root access (#1208) Jamie Land 2025-02-21 11:32:56 -05:00
  • 6634864b19
    docs: Add missing uv command and clarify website rebuild (#1199) Yuan Tang 2025-02-21 11:29:32 -05:00
  • 9898589f12
    fix: convert back to model descriptor for model in list --downloaded (#1201) Reid 2025-02-22 00:10:34 +08:00
  • da9f0b7869
    test(client-sdk): Update embedding test types to use latest imports (#1203) Rashmi Pawar 2025-02-21 21:39:17 +05:30
  • 46da187c07
    fix: remove list of list tests, no longer relevant after #1161 (#1205) Matthew Farrellee 2025-02-21 10:07:35 -06:00
  • d2701b0d6a
    chore: remove configure subcommand (#1202) Reid 2025-02-22 00:06:25 +08:00
  • c9c4a3c921
    feat: model remove cmd (#1128) Reid 2025-02-22 00:05:12 +08:00
  • 3099c5243f
    fix: update URL import, URL -> ImageContentItemImageURL (#1204) Matthew Farrellee 2025-02-21 10:02:21 -06:00
  • 34226d6c93 Another test_case related breakage fix Ashwin Bharambe 2025-02-20 23:10:33 -08:00
  • 36b762303c Fix client-sdk inference text -- spurious parameterization of test_case Ashwin Bharambe 2025-02-20 22:46:17 -08:00
  • 81ce39a607
    feat(api): Add options for supporting various embedding models (#1192) Ashwin Bharambe 2025-02-20 22:27:12 -08:00
  • 6f9d622340
    fix(api): update embeddings signature so inputs and outputs list align (#1161) Ashwin Bharambe 2025-02-20 21:43:13 -08:00
  • cfa752fc92
    fix: pass tool_prompt_format to chat_formatter (#1198) ehhuang 2025-02-20 21:38:35 -08:00
  • 33a64eb5ec
    ci: improve GitHub Actions workflow for website builds (#1151) Sébastien Han 2025-02-21 06:37:37 +01:00
  • dd43494847 Fix inference test fixture Ashwin Bharambe 2025-02-20 21:24:49 -08:00
  • 6820718b71
    fix: BuiltinTool JSON serialization in remote vLLM provider (#1183) Ben Browning 2025-02-21 00:18:37 -05:00
  • 16e3d99942
    docs: Simplify installation guide with uv (#1196) Yuan Tang 2025-02-21 00:05:47 -05:00
  • 35de423556
    docs: Add missing uv command for docs generation in contributing guide (#1197) Yuan Tang 2025-02-21 00:05:03 -05:00
  • 35ae0e16a1 Fix sqlite_vec config defaults Ashwin Bharambe 2025-02-20 17:50:24 -08:00
  • 832c535aaf
    feat(providers): add NVIDIA Inference embedding provider and tests (#935) Matthew Farrellee 2025-02-20 18:59:48 -06:00
  • 2608b6074f Update embedding dimension singular Ashwin Bharambe 2025-02-20 16:14:46 -08:00
  • 9436dd570d
    feat: register embedding models for ollama, together, fireworks (#1190) Ashwin Bharambe 2025-02-20 15:39:08 -08:00
  • 736560ceba Remove os.getenv() from ollama config Ashwin Bharambe 2025-02-20 14:30:32 -08:00
  • 2cbe9395b0
    feat: D69478008 [llama-stack] turning tests into data-driven (#1180) LESSuseLESS 2025-02-20 14:13:06 -08:00
  • 1166afdf76
    fix: some telemetry APIs don't currently work (#1188) ehhuang 2025-02-20 14:09:25 -08:00
  • ea1faae50e
    chore!: deprecate eval/tasks (#1186) Xi Yan 2025-02-20 14:06:21 -08:00
  • 07ccf908f7 ModelAlias -> ProviderModelEntry Ashwin Bharambe 2025-02-20 14:02:36 -08:00
  • 561295af76
    docs: Fix Links, Add Podman Instructions, Vector DB Unregister, and Example Script (#1129) Kevin Cogan 2025-02-20 21:52:14 +00:00
  • f7161611c6
    feat: adding endpoints for files and uploads (#1070) Vladimir Ivić 2025-02-20 13:09:00 -08:00
  • eddef0b2ae
    chore: slight renaming of model alias stuff (#1181) Ashwin Bharambe 2025-02-20 11:48:46 -08:00
  • 2eda050aef Fix ollama fixture Ashwin Bharambe 2025-02-20 11:46:02 -08:00
  • 3d891fc9ba ModelAlias cleanup Ashwin Bharambe 2025-02-20 11:21:13 -08:00
  • fbec826883
    docs: Add note about distro_codegen.py and provider dependencies (#1175) Ben Browning 2025-02-20 12:23:46 -05:00
  • 984a8039ad Kill unnecessary check on --safety-shield test param Ashwin Bharambe 2025-02-20 09:15:23 -08:00
  • 996f27a308
    fix: add logging import (#1174) Rashmi Pawar 2025-02-20 21:56:47 +05:30
  • fb6a3efb1d
    feat: Enable CPU training for torchtune (#1140) Ihar Hrachyshka 2025-02-20 01:42:58 -05:00
  • a324ceb9a9 precommit again Xi Yan 2025-02-19 22:40:26 -08:00
  • 4694780d23
    test: skip model registration for unsupported providers (#1030) Sébastien Han 2025-02-20 07:39:13 +01:00
  • 531940aea9
    script for running client sdk tests (#895) Sixian Yi 2025-02-19 22:38:06 -08:00
  • a3d8c49459 precommit Xi Yan 2025-02-19 22:37:41 -08:00
  • ce040ad111 precommit Xi Yan 2025-02-19 22:35:24 -08:00
  • ca687d3e86 style: env var in build_venv Xi Yan 2025-02-19 22:32:59 -08:00
  • b74f25035c
    Added support for mongoDB KV store (#543) Shrinit Goyal 2025-02-20 12:00:50 +05:30
  • 5966079770
    fix: More robust handling of the arguments in tool call response in remote::vllm (#1169) Yuan Tang 2025-02-20 01:27:02 -05:00
  • 69eebaf5bf
    build: add missing dev dependencies for unit tests (#1004) Sébastien Han 2025-02-20 07:26:11 +01:00
  • 61f43b8677
    fix: llama stack build use UV_SYSTEM_PYTHON to install dependencies to system environment (#1163) Xi Yan 2025-02-19 22:21:16 -08:00
  • 2b752df79a
    fix: Fixing some small issues with the build scripts (#1132) Francisco Arceo 2025-02-19 23:20:49 -07:00
  • af377e844d
    feat: add a option to list the downloaded models (#1127) Reid 2025-02-20 14:17:39 +08:00
  • 7504cb16c6
    docs: improve API contribution guidelines (#1137) Sébastien Han 2025-02-20 07:14:04 +01:00
  • 25cdab5b28
    docs: Remove unused python-openapi and json-strong-typing in openapi_generator (#1167) Yuan Tang 2025-02-20 01:06:29 -05:00
  • 2b995c22eb
    feat: inference passthrough provider (#1166) Botao Chen 2025-02-19 21:47:00 -08:00
  • d39f8de619 Pin sphinx Ashwin Bharambe 2025-02-19 20:20:46 -08:00
  • 89fdb2c9e9 Try a different css file API for sphinx Ashwin Bharambe 2025-02-19 20:14:40 -08:00
  • b751f7003d
    feat: add aggregation_functions to llm_as_judge_405b_simpleqa (#1164) Botao Chen 2025-02-19 19:42:04 -08:00
  • c1f7d7f005
    fix: miscellaneous job management improvements in torchtune (#1136) Ihar Hrachyshka 2025-02-19 22:09:37 -05:00
  • 7972daa72e
    feat: Chunk sqlite-vec writes (#1094) Francisco Arceo 2025-02-19 20:07:46 -07:00
  • 26503ca1a4
    docs: fix Python llama_stack_client SDK links (#1150) Sébastien Han 2025-02-20 04:05:14 +01:00
  • cdcbeb005b
    chore: remove llama_models.llama3.api imports from providers (#1107) Ashwin Bharambe 2025-02-19 19:01:29 -08:00
  • e9b8259cf9
    fix: Get distro_codegen.py working with default deps and enabled in pre-commit hooks (#1123) Ben Browning 2025-02-19 21:39:20 -05:00