Commit graph

  • 7275bf7fda chore: Increase unit test coverage of routing_tables.py Derek Higgins 2025-04-29 12:14:19 +01:00
  • 07688f5960 fix: Fix precommit-hook Derek Higgins 2025-04-30 10:52:43 +01:00
  • 2ada832e69 ci: validate UBI9 base reluctantfuturist 2025-04-29 13:54:58 -07:00
  • 10ae03eb83 fix(ci): correctly override UBI9 image and switch to full UBI9 reluctantfuturist 2025-04-29 10:45:46 -07:00
  • 5c0680cd3f build: Bump version to 0.2.4 v0.2.4 release-0.2.4 github-actions[bot] 2025-04-29 17:23:26 +00:00
  • 302b3050c2 Release candidate 0.2.4rc1 v0.2.4rc1 github-actions[bot] 2025-04-29 17:18:17 +00:00
  • 96afc98b88 Add reference to notebook in docs Jash Gulabrai 2025-04-29 13:06:43 -04:00
  • 96d4e7241c
    Update config.py Ashwin Bharambe 2025-04-29 10:05:08 -07:00
  • ef2b686ff4
    Update safety_models.py Ashwin Bharambe 2025-04-29 10:03:37 -07:00
  • 2f60f3c347 fix: Consistently prefix customized models with the namespace Jash Gulabrai 2025-04-29 12:57:49 -04:00
  • 38b580db02 feat: add api.llama provider, llama-guard-4 model Ashwin Bharambe 2025-04-29 09:56:46 -07:00
  • 36373e44f2
    refactor: Remove SQLITE_DB_PATH Roland Huß 2025-04-29 12:31:52 +02:00
  • 9f869df356
    chore(ci): misc Ollama improvements Sébastien Han 2025-04-29 10:13:22 +02:00
  • d96a4bc9b2
    Update integration-tests.yml Yuan Tang 2025-04-28 20:43:57 -04:00
  • ef3009ca26
    chore(github-deps): bump astral-sh/setup-uv from 5 to 6 dependabot[bot] 2025-04-28 21:11:29 +00:00
  • d58c2d157e
    ci: simplify external provider integration test Sébastien Han 2025-04-28 23:00:59 +02:00
  • 7323d8e86f fix tool calling by not relying on finish reason but tool_calls Ashwin Bharambe 2025-04-28 13:39:50 -07:00
  • a1524390b9 update the run.yaml Ashwin Bharambe 2025-04-28 12:51:07 -07:00
  • ae012bb857 rename response to responses in verifications, update provider Ashwin Bharambe 2025-04-28 10:46:09 -07:00
  • 78da66016f raise when you find a Literal type we dont support in openapi generator Ashwin Bharambe 2025-04-28 10:37:14 -07:00
  • abd6280cb8 fold openai responses into the Agents API Ashwin Bharambe 2025-04-28 10:27:28 -07:00
  • 207224a811 OpenAPI Responses - move tests under tests/verifications Ben Browning 2025-04-18 15:26:34 -04:00
  • 591e6a3972 OpenAI Responses - streaming handling for text chat responses Ben Browning 2025-04-18 09:45:41 -04:00
  • d523c8692a OpenAI Responses - image support and multi-turn tool calling Ben Browning 2025-04-18 09:13:48 -04:00
  • 35b2e2646f OpenAI Responses API: Stub in basic web_search tool Ben Browning 2025-04-17 20:25:36 -04:00
  • 52a69f0bf9 Extract some helper methods out in openai_responses impl Ben Browning 2025-04-17 15:10:22 -04:00
  • 70c088af3a Stub in an initial OpenAI Responses API Ben Browning 2025-04-17 14:47:24 -04:00
  • 29f57d528d Remove unused env vars; change the other tmp folder name; fix examples Jash Gulabrai 2025-04-28 13:08:36 -04:00
  • c3d8940c95 Merge branch 'main' into nvidia-e2e-notebook Jash Gulabrai 2025-04-28 12:52:46 -04:00
  • c7ab6eeedb Minor unit test updates Jash Gulabrai 2025-04-28 12:49:50 -04:00
  • e64961697a Rename tmp dir to sample_data; remove print statements Jash Gulabrai 2025-04-28 12:04:36 -04:00
  • 73275f07b7 Merge branch 'main' into nvidia-e2e-notebook Jash Gulabrai 2025-04-28 12:00:11 -04:00
  • a083465ba4 Add openai completion/chat completion Matt Clayton 2025-04-28 09:21:23 -04:00
  • ee1f06417d
    feat: Add Kubernetes authentication Sébastien Han 2025-03-25 18:27:33 +01:00
  • 53f474845b fix: ollama still using tools with tool_choice="none" Ben Browning 2025-04-28 07:55:55 -04:00
  • aa8b2aa31f fix template validation Rashmi Pawar 2025-04-28 16:04:57 +05:30
  • 00e57d693f update provider to provider_id Rashmi Pawar 2025-04-16 14:55:21 +05:30
  • 4491a51149 skip nvidia integration in github actions raspawar 2025-04-09 13:06:06 +00:00
  • 1381d3f3e8 linting fix raspawar 2025-04-09 12:34:36 +00:00
  • 60bf0eb532 datastore documentation raspawar 2025-04-09 12:31:46 +00:00
  • a3c07ac10a update tests raspawar 2025-04-09 12:25:13 +00:00
  • 234f4e4583 add integration test raspawar 2025-04-09 11:10:01 +00:00
  • c139f787c8 add unit tests raspawar 2025-04-02 15:18:15 +00:00
  • cf3f3ff130 linting fix raspawar 2025-04-02 14:26:48 +00:00
  • 2baf252f71 add code for register, unregister raspawar 2025-04-02 14:20:10 +00:00
  • 1e77873a02 add datasetio to distribution raspawar 2025-03-26 15:21:38 +05:30
  • ae973c9595 add datasetio code raspawar 2025-03-26 15:04:20 +05:30
  • 3b4024bdcc docs: update prompt in quickstart guide to reflect output Bobbins228 2025-04-28 10:25:22 +01:00
  • df2320d302
    chore(github-deps): bump astral-sh/setup-uv from 5 to 6 dependabot[bot] 2025-04-28 00:52:53 +00:00
  • 59e1c5f4a0 Pass 1 for pre-commit fixes Matt Clayton 2025-04-27 15:24:37 -04:00
  • fdb1109491 fix: tools page on playground resets agent after every interaction Michael Clifford 2025-04-27 13:54:44 -04:00
  • 40160719c8 address disagreement between ruff versions (again) Matthew Farrellee 2025-04-27 10:59:11 -04:00
  • 7fd8a61b4d Merge branch 'main' into test-modelregistryhelper Matthew Farrellee 2025-04-27 10:56:30 -04:00
  • c590674ee2 live listing overrides static listing for ollama & vllm model registration Matthew Farrellee 2025-04-27 10:44:45 -04:00
  • a4c8a849b6 Revert "vllm unit test, check for exception on error" Matthew Farrellee 2025-04-27 10:36:54 -04:00
  • e89fbb8213
    Lint fix Yuan Tang 2025-04-26 21:27:21 -04:00
  • a7fd3c8848
    fix: Bump h11 to 0.16.0 to fix cve-2025-43859 Yuan Tang 2025-04-26 21:23:20 -04:00
  • d840037a15
    docs: Add changelog for v0.2.2 and v0.2.3 Yuan Tang 2025-04-26 21:07:48 -04:00
  • fdaa7adbab ci: add UBI 9 container-build gate reluctantfuturist 2025-04-26 14:59:05 -07:00
  • 9132530ec6
    chore(github-deps): bump actions/setup-python from 5.5.0 to 5.6.0 dependabot[bot] 2025-04-26 20:53:48 +00:00
  • 0ec5151ab5 feat: add post_training RuntimeConfig Charlie Doern 2025-04-26 10:40:58 -04:00
  • 4884c62190 Merge branch 'main' into watsonx-infer-fix Sajikumar JS 2025-04-26 18:31:59 +05:30
  • a9e4d1f00e pre-commit updates Sajikumar JS 2025-04-26 18:29:47 +05:30
  • 7f1e4bf075 Updated parameters Sajikumar JS 2025-04-26 18:29:06 +05:30
  • 3588c5bcd7 Updated SamplingParams Sajikumar JS 2025-04-26 18:25:58 +05:30
  • 045836ebfc doc: update prompt_format.md for llama4 Eric Huang 2025-04-25 15:48:06 -07:00
  • 1e8fce126f build: Bump version to 0.2.3 v0.2.3 release-0.2.3 Ashwin Bharambe 2025-04-25 15:38:49 -07:00
  • 3ca284a52b Release candidate 0.2.3rc5 v0.2.3rc5 github-actions[bot] 2025-04-25 22:07:01 +00:00
  • dd349b2176 Remove check to parse either dict or pydantic model Jash Gulabrai 2025-04-25 16:13:39 -04:00
  • ff6081a353 fix: tool call encoded twice Eric Huang 2025-04-25 13:05:06 -07:00
  • 6659ed995a Merge branch 'main' into fix/nvidia-launch-customization Jash Gulabrai 2025-04-25 16:01:22 -04:00
  • bb142435db Use correct shapes in unit tests; remove use of unsupported params Jash Gulabrai 2025-04-25 15:52:12 -04:00
  • 03a25a7753 updated the additional params to pass any type of values Sajikumar JS 2025-04-26 01:19:37 +05:30
  • 1d6ef73dd7 added additional params and new functions required to watsonx Sajikumar JS 2025-04-26 01:09:46 +05:30
  • a233bdc76e add unit tests for content from doc Kevin 2025-04-25 15:09:33 -04:00
  • 7b34153fff fix: check that llama stack client plain can be used as a subst for OpenAI client Ashwin Bharambe 2025-04-25 12:13:20 -07:00
  • cfc6bdae68 llama-4-scout-17b-16e-instruct passing tests Matt Clayton 2025-04-25 13:38:40 -04:00
  • 6135bdec22 add tests/verification/conf/lmstudio.yaml Neil Mehta 2025-04-22 13:09:36 -04:00
  • 6377b1912b Revert "Use int for year in test case" Neil Mehta 2025-03-24 18:54:52 -04:00
  • 357d7ea9ea Use int for year in test case Neil Mehta 2025-03-24 17:57:48 -04:00
  • 00affd1f02 Fix async streaming Neil Mehta 2025-03-24 14:10:49 -04:00
  • 05777dfb52 implement error handling, improve completion, tool calling and streaming Justin Lee 2025-03-21 16:52:32 -07:00
  • fe575a0fdf Update report.md to reflect current version support Rugved Somwanshi 2025-03-19 18:35:32 -04:00
  • a0ff1f0464 Update README.md Rugved Somwanshi 2025-03-18 17:31:20 -04:00
  • 302d72cc47 Fix python3.10 async Neil Mehta 2025-03-18 15:53:41 -04:00
  • aa9562e104 Addressed comments Rugved Somwanshi 2025-03-14 16:33:53 -04:00
  • 1a5cfd1b6f Fix stream generate Neil Mehta 2025-03-14 15:51:12 -04:00
  • 9c83ca415d Fix lmstudio name Neil Mehta 2025-03-14 15:40:50 -04:00
  • 461eec425d LM Studio inference integration Neil Mehta 2025-03-14 15:21:15 -04:00
  • 17edf138e8 new prompt Eric Huang 2025-04-25 11:15:04 -07:00
  • 8e9217774a new prompt Eric Huang 2025-04-24 13:16:42 -07:00
  • 8409109ca7 docs(readme): add one-line installer snippet reluctantfuturist 2025-04-25 10:01:55 -07:00
  • bed5a9f55a chore(installer): remove ollama-models bind-mount for a stateless install reluctantfuturist 2025-04-25 09:39:19 -07:00
  • a5a842fa76 feat(installer): dump container logs on health-check failure reluctantfuturist 2025-04-24 10:26:59 -07:00
  • 0ae46f9417 chore(installer): fully silence container output by redirecting stderr Alexey Rybak 2025-04-24 10:21:07 -07:00
  • 876fd6e80b chore(ci): refine shellcheck reluctantfuturist 2025-04-23 11:50:16 -07:00
  • 6a135e80c7 chore(ci): refine shellcheck reluctantfuturist 2025-04-23 11:39:01 -07:00
  • b67940e5cc ci(installer): pin actions to SHAs, add ShellCheck, drop redundant steps reluctantfuturist 2025-04-23 11:27:56 -07:00
  • 19ad7ba513 chore(ci): remove redundant steps and simplify network setup reluctantfuturist 2025-04-18 15:00:25 -07:00
  • d4e5d4c1fa chore(installer): make install.sh executable in repo reluctantfuturist 2025-04-18 13:51:13 -07:00