Commit graph

  • df68db644b Refactoring distribution/distribution.py Ashwin Bharambe 2024-10-02 13:20:17 -07:00
  • 5d3403202e update output msg Xi Yan 2024-10-02 12:56:16 -07:00
  • 7fadfa7435 cleanup tmp config Xi Yan 2024-10-02 12:50:46 -07:00
  • 92a255c187 avoid configure twice Xi Yan 2024-10-02 12:40:46 -07:00
  • 546f05bd3f No automatic pager Ashwin Bharambe 2024-10-02 12:25:54 -07:00
  • 204eb6d810
    docker: Check for selinux before using --security-opt (#167) Russell Bryant 2024-10-02 13:37:41 -04:00
  • 9b93ee2c2b Bump version to 0.0.37 Ashwin Bharambe 2024-10-02 10:15:08 -07:00
  • 227b69e6e6 Fix sample memory impl Ashwin Bharambe 2024-10-02 10:13:09 -07:00
  • 335dea849a fix sample impls Ashwin Bharambe 2024-10-02 10:09:36 -07:00
  • bf0d111c53 Fix build script Ashwin Bharambe 2024-10-02 10:04:23 -07:00
  • 4a75d922a9 Make Llama Guard 1B the default Ashwin Bharambe 2024-10-02 09:48:26 -07:00
  • cc5029a716 Add special case for prompt guard Ashwin Bharambe 2024-10-02 08:38:23 -07:00
  • a80b707ff8 Ensure we always ask for pydantic>=2 Ashwin Bharambe 2024-10-02 06:29:06 -07:00
  • f9e2e34370 docker: Check for selinux before using --security-opt Russell Bryant 2024-10-01 13:17:09 +00:00
  • de8fdd8db8 Adds markdown-link-check and fixes a broken link Adrian Cole 2024-10-01 13:23:37 +08:00
  • eb2d8a31a5
    Add a RoutableProvider protocol, support for multiple routing keys (#163) Ashwin Bharambe 2024-09-30 17:30:21 -07:00
  • 6d8f59e359 Cleanup Ashwin Bharambe 2024-09-30 17:28:55 -07:00
  • 1702aa5e3f Kill get_routing_keys(), rename register_ to validate_ Ashwin Bharambe 2024-09-30 17:08:56 -07:00
  • aab81cd5ad Refactor distribution/datatypes into a providers/datatypes Ashwin Bharambe 2024-09-30 16:45:08 -07:00
  • 86834ee6c2 Update configure.py to use multiple routing keys for safety Ashwin Bharambe 2024-09-30 16:36:53 -07:00
  • 73decb3781 re-build from name Xi Yan 2024-09-30 16:22:52 -07:00
  • 4897bf2f85 allow --name to re-build from config Xi Yan 2024-09-30 16:18:12 -07:00
  • 0996ffb3b3 bug fixes Ashwin Bharambe 2024-09-30 16:15:51 -07:00
  • 878b2c31c7 add more RoutableProviders Ashwin Bharambe 2024-09-30 15:51:45 -07:00
  • c17c17cb19 Make routing_key accept multiple values Ashwin Bharambe 2024-09-30 13:32:41 -07:00
  • d28c3dfe0f
    [CLI] simplify docker run (#159) Xi Yan 2024-09-30 15:04:04 -07:00
  • cae5369455 remove quotes in configure Xi Yan 2024-09-30 15:01:29 -07:00
  • e9de2dee02 unique special_deps Xi Yan 2024-09-30 14:59:59 -07:00
  • 16ad2de97b configure msg Xi Yan 2024-09-30 14:23:35 -07:00
  • 8c2ba15703 build output msg Xi Yan 2024-09-30 14:17:48 -07:00
  • e026538b4c update msg Xi Yan 2024-09-30 14:14:30 -07:00
  • 0f10de04ba address comments, update output msg Xi Yan 2024-09-30 13:49:26 -07:00
  • 8db49de961
    docker: Install in editable mode for dev purposes (#160) Russell Bryant 2024-09-30 14:56:31 -04:00
  • fd04ad9e1e default entrypoint Xi Yan 2024-09-30 11:53:13 -07:00
  • da33fa0f80 docker: Install in editable mode for dev purposes Russell Bryant 2024-09-30 16:30:04 +00:00
  • 340e134629 clean up debug Xi Yan 2024-09-30 11:02:55 -07:00
  • 827525c77c unique deps Xi Yan 2024-09-30 10:50:42 -07:00
  • 8731cc3304 delete generated Dockerfile Xi Yan 2024-09-30 10:47:44 -07:00
  • 3482adb257 add docker template examples Xi Yan 2024-09-30 09:07:04 -07:00
  • 6cd3e4183f bake run.yaml inside docker, simplify run Xi Yan 2024-09-30 08:49:25 -07:00
  • cb36be320f
    Fix podman+selinux compatibility (#132) Russell Bryant 2024-09-29 23:19:44 -04:00
  • 2bd785354d
    fix broken bedrock inference provider (#151) moritalous 2024-09-30 12:17:58 +09:00
  • 2f096ca509
    accepts not model itself. (#153) Byung Chun Kim 2024-09-30 12:16:50 +09:00
  • 5bf679cab6
    Pull (extract) provider data from the provider instead of pushing from the top (#148) Ashwin Bharambe 2024-09-29 20:00:51 -07:00
  • 78b07ddc92 accepts not model itself. Byung Chun Kim 2024-09-30 02:29:19 +00:00
  • ed84641953 remove prints Zain Hasan 2024-09-29 14:59:10 -04:00
  • c13b2f06af
    Merge branch 'meta-llama:main' into main Zain Hasan 2024-09-29 11:56:29 -07:00
  • 54d7b2f2d7 fix broken bedrock inference provider moritalous 2024-09-29 14:59:30 +00:00
  • cd64371b2e
    Merge branch 'meta-llama:main' into main Pixee OSS Assistant 2024-09-29 07:57:31 -04:00
  • fdadfb6afb Add timeout to requests calls (#1) pixeeai 2024-09-29 07:24:20 -04:00
  • 7274802de9 Pull (extract) provider data from the provider instead of pushing from the top Ashwin Bharambe 2024-09-28 22:04:16 -07:00
  • f6a6598d1a
    [bugfix] fix #146 (#147) Xi Yan 2024-09-28 17:47:00 -07:00
  • 3428c4868d lint Xi Yan 2024-09-28 17:45:38 -07:00
  • 12c0860cae more robust image type Xi Yan 2024-09-28 17:44:45 -07:00
  • b646167d94
    Update README.md Xi Yan 2024-09-28 16:55:22 -07:00
  • 5ce759adc4
    Update README.md Xi Yan 2024-09-28 16:55:08 -07:00
  • 6a8c2ae1df
    [CLI] remove dependency on CONDA_PREFIX in CLI (#144) Xi Yan 2024-09-28 16:46:47 -07:00
  • 390a8fdbe7 more robust Xi Yan 2024-09-28 16:44:28 -07:00
  • 31e235490c Fix TypeError when CONDA_PREFIX is not set Russell Bryant 2024-09-28 23:39:01 +00:00
  • 47b0be1497 typo Xi Yan 2024-09-28 16:37:08 -07:00
  • 0477b29ba9 lint Xi Yan 2024-09-28 16:32:29 -07:00
  • 3ffe51052a remove dependency on CONDA_PREFIX in CLI Xi Yan 2024-09-28 16:21:50 -07:00
  • fe460ba103 Avoid importing a lot of stuff Ashwin Bharambe 2024-09-28 16:05:49 -07:00
  • 4ae8c63a2b pre-commit lint Xi Yan 2024-09-28 16:04:41 -07:00
  • ced5fb6388 Small cleanup for together safety implementation Ashwin Bharambe 2024-09-28 15:47:35 -07:00
  • 940968ee3f
    fixing safety inference and safety adapter for new API spec. Pinned t… (#105) Yogish Baliga 2024-09-28 15:45:38 -07:00
  • 0a3999a9a4
    Use inference APIs for executing Llama Guard (#121) Ashwin Bharambe 2024-09-28 15:40:06 -07:00
  • e61c4954d5 minor Ashwin Bharambe 2024-09-28 15:32:03 -07:00
  • 23028e26ff bugfixes Ashwin Bharambe 2024-09-28 15:21:32 -07:00
  • 37ca22cda6 Use inference APIs for executing Llama Guard Ashwin Bharambe 2024-09-25 19:40:49 -07:00
  • c39ba23508 Fix podman+selinux compatibility Russell Bryant 2024-09-27 14:05:18 +00:00
  • 6236634d84
    [bugfix] fix duplicate api endpoints (#139) Xi Yan 2024-09-27 15:32:50 -07:00
  • d09218a275 remove print Xi Yan 2024-09-27 15:31:20 -07:00
  • 21452a162b fix server api to serve Xi Yan 2024-09-27 15:28:21 -07:00
  • 572c01f454 for agents API, provider data from the header is not parsed as for agents there is no provider_data_validator meta-reference implementation. Added Together data validator as the provider_data_validator for now. Did some code changes accordingly. Yogish Baliga 2024-09-27 14:59:24 -07:00
  • 208b861289
    add env for LLAMA_STACK_CONFIG_DIR (#137) Xi Yan 2024-09-27 14:16:46 -07:00
  • a3fea59eb5 add env for LLAMA_STACK_CONFIG_DIR Xi Yan 2024-09-27 14:11:41 -07:00
  • 43744455d7
    docs: Note how to use podman (#130) Russell Bryant 2024-09-27 17:00:40 -04:00
  • f70c88ab7a
    configure: Fix a error msg typo (#131) Russell Bryant 2024-09-27 17:00:25 -04:00
  • ebb57a0c67 wip Xi Yan 2024-09-27 13:52:23 -07:00
  • f2125667e7 remove library Edward Ma 2024-09-27 13:50:45 -07:00
  • 67ac0e0895 Add SambaNova Adapter Edward Ma 2024-09-27 13:48:24 -07:00
  • 27b63f4de5 adding vision guard to Together safety Yogish Baliga 2024-09-27 13:33:33 -07:00
  • 5828ffd53b
    inference: Fix download command in error msg (#133) Russell Bryant 2024-09-27 16:31:11 -04:00
  • fb9e6371ec
    Validate name in llama stack build (#128) Russell Bryant 2024-09-27 16:30:55 -04:00
  • d7c55f0ad0 fixing model names Yogish Baliga 2024-09-25 21:24:36 -07:00
  • 2b568a462a support Llama 3.2 models in Together inference adapter and cleanup Together safety adapter Yogish Baliga 2024-09-25 17:51:42 -07:00
  • 9bb0c8f4fc fixing safety inference and safety adapter for new API spec. Pinned the llama_models version to 0.0.24 as the latest version 0.0.35 has the model descriptor name changed. I was getting the missing package error during runtime as well, hence added the dependency to requirements.txt Yogish Baliga 2024-09-25 14:14:15 -07:00
  • 53070e34a3
    Update RFC-0001-llama-stack.md (#134) Bhimraj Yadav 2024-09-27 21:59:36 +05:45
  • 787ef09ea3
    Update RFC-0001-llama-stack.md Bhimraj Yadav 2024-09-27 20:58:18 +05:45
  • bec6ab78c2 inference: Fix download command in error msg Russell Bryant 2024-09-27 14:14:07 +00:00
  • 273990659f configure: Fix a error msg typo Russell Bryant 2024-09-27 13:55:55 +00:00
  • e3f98ce97e docs: Note how to use podman Russell Bryant 2024-09-27 13:42:46 +00:00
  • e2a1387b97 Validate name in llama stack build Russell Bryant 2024-09-27 13:21:50 +00:00
  • ecd17ce9e9 reorder output msg Xi Yan 2024-09-26 23:28:42 -07:00
  • 3b807912d2 remove configure outside for docker Xi Yan 2024-09-26 23:11:15 -07:00
  • 0ad0a15810 configure outside container Xi Yan 2024-09-26 21:36:17 -07:00
  • eb526b4d9b
    Update RFC-0001-llama-stack.md Xi Yan 2024-09-26 17:17:08 -07:00
  • 6b0805ebb4
    fix: 404 link to agentic system repository (#118) Moritz Althaus 2024-09-26 23:43:41 +02:00
  • 557ae38289
    Update getting_started.ipynb (#117) Deep Doshi 2024-09-26 14:43:04 -07:00