Commit graph

  • 5bf2fe452d fix build command Xi Yan 2024-09-10 11:06:32 -07:00
  • 0981193d78 config file for build Xi Yan 2024-09-10 11:02:46 -07:00
  • 0964b0a74a Improve TGI adapter initialization condition Celina Hanouti 2024-09-10 18:22:09 +02:00
  • 2b63074676 add /inference/chat_completion to SSE special case Dalton Flanagan 2024-09-10 01:14:11 -04:00
  • bdede6d14e simplify search tool and enable configuration for search engine Hardik Shah 2024-09-09 18:41:11 -07:00
  • 4f021de10f
    API spec update, client demo with Stainless SDK (#58) Xi Yan 2024-09-09 13:09:47 -07:00
  • 6bfcbc678e remove client sdk examples Xi Yan 2024-09-09 12:21:08 -07:00
  • 26209a9d99 add comment todos Xi Yan 2024-09-09 11:50:35 -07:00
  • 8c378fadcc agentic system client sdk Xi Yan 2024-09-09 11:46:08 -07:00
  • b7b8f5c2c3 update script Xi Yan 2024-09-09 11:19:57 -07:00
  • 6ccb0a4c1f Simplified Telemetry API and tying it to logger Ashwin Bharambe 2024-09-07 15:25:35 -07:00
  • 84b8a53a34 update wrapper request Xi Yan 2024-09-09 11:15:22 -07:00
  • 838ab91ebf update generator & yaml spec Xi Yan 2024-09-09 10:39:29 -07:00
  • 2ac8e7b901 Remove unecessary method argument Celina Hanouti 2024-09-09 19:04:21 +02:00
  • fff1b6d6bf Use HfApi to get the namespace when not provide in the hf endpoint name Celina Hanouti 2024-09-09 18:59:10 +02:00
  • 3d660ad938 Rename TGI Adapter class Celina Hanouti 2024-09-09 18:30:34 +02:00
  • eee6c69f46 Update CLI reference and add typing Celina Hanouti 2024-09-09 17:49:07 +02:00
  • b96e705680 Fixes post-review and split TGI adapter into local and Inference Endpoints ones Celina Hanouti 2024-09-09 17:47:49 +02:00
  • ee32de4c3f [wip] client w/ stainless sdk Xi Yan 2024-09-08 18:31:49 -07:00
  • 640c5f8ab9 add tool for bing search Hardik Shah 2024-09-08 17:25:52 -07:00
  • 741310f78e rename observability -> Telemetry; regen Spec Ashwin Bharambe 2024-09-07 15:23:53 -07:00
  • 70e682fbdf Update distribution_id -> distribution_type, provider_id -> provider_type Ashwin Bharambe 2024-09-07 08:42:28 -07:00
  • 3f090d1975
    Add Chroma and PGVector adapters (#56) Ashwin Bharambe 2024-09-06 18:53:17 -07:00
  • c02d8aa3d3 Add Chroma and PGVector adapters Ashwin Bharambe 2024-09-05 23:49:14 -07:00
  • 5de6ed946e
    Query generators for RAG query (#54) Hardik Shah 2024-09-06 13:10:39 -07:00
  • 95a5982524 drop classes for functions Hardik Shah 2024-09-06 12:58:13 -07:00
  • c2b7b462e9 use agent.inference_api instead of passing host/port again Hardik Shah 2024-09-06 12:48:08 -07:00
  • 406c3b24d4
    upgrade llama_models (#55) Yufei (Benny) Chen 2024-09-06 12:03:13 -07:00
  • f1e23075d1 upgrade llama_models benjibc 2024-09-06 18:55:19 +00:00
  • 5ab4fd31f7 Merge branch 'tgi-integration' of github.com:hanouticelina/llama-stack into tgi-integration Celina Hanouti 2024-09-06 17:58:22 +02:00
  • 031dbc0e45 Use InferenceClient.text_generation for TGI inference Celina Hanouti 2024-09-06 17:56:27 +02:00
  • 3858d94edf
    Merge branch 'meta-llama:main' into tgi-integration Celina Hanouti 2024-09-06 15:37:12 +02:00
  • 4a70f3d2ba Query generators for rag query Hardik Shah 2024-09-04 17:58:42 -07:00
  • dd1e1ceb13 Add bubblewrap to the container Ashwin Bharambe 2024-09-05 16:45:58 -07:00
  • f6b5e394ab Remove dependence on os.environ["USER"] Ashwin Bharambe 2024-09-05 15:37:12 -07:00
  • 7aa50934bf Update the default value for TGI URL Celina Hanouti 2024-09-05 19:05:07 +02:00
  • e5bcfdac21 Use huggingface_hub inference client for TGI inference Celina Hanouti 2024-09-05 18:29:04 +02:00
  • 6c69e09c6a Bump version to 0.0.13 Ashwin Bharambe 2024-09-04 23:10:38 -07:00
  • 21bedc1596
    [inference] Add a TGI adapter (#52) Ashwin Bharambe 2024-09-04 22:49:33 -07:00
  • 046afcb945 Use the lower-level generate_stream() method for correct tool calling Ashwin Bharambe 2024-09-04 17:36:45 -07:00
  • f355b9b844 TGI adapter and some refactoring of other inference adapters Ashwin Bharambe 2024-09-04 10:51:27 -07:00
  • 6ad7365676 A little clean up for the Fireworks and Together adapters Ashwin Bharambe 2024-09-04 22:34:15 -07:00
  • 225cd75074
    Update cli_reference.md raghotham 2024-09-04 18:50:10 -07:00
  • bfee50aa83 A few more fixes to the OpenAPI generator Ashwin Bharambe 2024-09-04 10:29:20 -07:00
  • 0167953d2d Update OpenAPI generator for POST requests Ashwin Bharambe 2024-09-04 09:27:00 -07:00
  • 01d971bda6 Bump version to 0.0.12 Ashwin Bharambe 2024-09-03 23:24:02 -07:00
  • 1380d78c19 Fixes to the llama stack configure script + inference adapters Ashwin Bharambe 2024-09-03 23:22:21 -07:00
  • 4869f2b983 Update fireworks and together entries as adapters Ashwin Bharambe 2024-09-03 22:56:52 -07:00
  • f802d481d9 Bump version to 0.0.11 Ashwin Bharambe 2024-09-03 22:41:29 -07:00
  • 7bc7785b0d
    API Updates: fleshing out RAG APIs, introduce "llama stack" CLI command (#51) Ashwin Bharambe 2024-09-03 22:39:39 -07:00
  • 86059af5af Added a "--raw" option for model template printing Ashwin Bharambe 2024-09-03 22:04:43 -07:00
  • 85d56ed3f2 Merge remote-tracking branch 'origin/main' into api_updates_1 Ashwin Bharambe 2024-09-03 21:42:25 -07:00
  • 19770f6330 Remove conflicting annotation Ashwin Bharambe 2024-09-03 21:39:56 -07:00
  • b60c125c55 Add pyopenapi fork to the repository, update RFC assets Ashwin Bharambe 2024-09-03 21:22:30 -07:00
  • 35093c0b6f
    Add patch for SSE event endpoint responses (#50) Dalton Flanagan 2024-09-03 23:40:31 -04:00
  • 0d619b9f8e Change name of build for less confusion Ashwin Bharambe 2024-09-03 18:48:29 -07:00
  • 6c82f110f8 Add patch for SSE event endpoint responses Dalton Flanagan 2024-09-03 15:00:49 -04:00
  • fb3c4566ce llama stack start -> llama stack run Ashwin Bharambe 2024-09-03 11:23:26 -07:00
  • 0af81776c7 fix for incomplete SSE type generation Dalton Flanagan 2024-09-03 13:11:40 -04:00
  • b5d958631e Add timeout and retries for HTTP requests in AgenticSystemClient Mandlin Sarah 2024-09-03 03:20:07 -07:00
  • fab6bd1728 Update documentation again and add error messages to llama stack start Ashwin Bharambe 2024-09-02 21:36:32 -07:00
  • 279565499b Fixes to llama stack commands and update docs Ashwin Bharambe 2024-09-02 18:58:54 -07:00
  • 5927f3c3c0 Remote llama api [] subcommands Ashwin Bharambe 2024-09-02 18:48:19 -07:00
  • 9be0edc76c Allow building an "adhoc" distribution Ashwin Bharambe 2024-09-02 18:37:31 -07:00
  • d99c06fce8 Fix stack start Ashwin Bharambe 2024-08-30 15:03:23 -07:00
  • 5172d9a79d Update llama stack configure to be very simple also Ashwin Bharambe 2024-08-30 14:55:20 -07:00
  • f8517e4688 Simplify and generalize llama api build yay Ashwin Bharambe 2024-08-30 14:51:40 -07:00
  • 297d51b183 Support downloading of URLs for attachments for code interpreter Ashwin Bharambe 2024-08-30 12:10:15 -07:00
  • afb18880b5 Delete utils.py; move to agentic system Ashwin Bharambe 2024-08-30 11:52:40 -07:00
  • 9ec06918a5 missing import lol Ashwin Bharambe 2024-08-30 10:45:23 -07:00
  • a2470aae11 Fix api dependencies not getting added to configuration Ashwin Bharambe 2024-08-30 10:40:17 -07:00
  • 886a01ee2e chmod +x scripts Dalton Flanagan 2024-08-30 00:07:12 -04:00
  • e53e115a5b Add a log just for consistency Ashwin Bharambe 2024-08-29 16:19:43 -07:00
  • 6fa074168e update paths Ashwin Bharambe 2024-08-29 16:14:45 -07:00
  • d12aa64bbf Add termcolor Ashwin Bharambe 2024-08-29 16:04:00 -07:00
  • 70d557f793
    Update LICENSE (#47) raghotham 2024-08-29 07:39:50 -07:00
  • c93709ec2d
    Update LICENSE raghotham 2024-08-29 07:01:32 -07:00
  • 48595b23bd
    Update LICENSE raghotham 2024-08-29 06:47:05 -07:00
  • 3cb67f1f58 llama_toolchain/distribution -> llama_toolchain/core Ashwin Bharambe 2024-08-28 17:39:41 -07:00
  • 81540e6ce8
    Update cli_reference.md Ashwin Bharambe 2024-08-28 17:36:32 -07:00
  • 896f057b76 Updated README phew Ashwin Bharambe 2024-08-28 17:34:23 -07:00
  • 3063329dad Some quick fixes to the CLI behavior to make it consistent Ashwin Bharambe 2024-08-28 17:17:46 -07:00
  • f1244f6d9e Make Fireworks and Together into the Adapter format Ashwin Bharambe 2024-08-28 16:21:07 -07:00
  • a23a6ab95b Merge remote-tracking branch 'origin/main' into api_updates_1 Ashwin Bharambe 2024-08-28 16:08:06 -07:00
  • f2e18826b6
    Together AI basic integration (#43) Hassan El Mghari 2024-08-28 16:07:13 -07:00
  • d3965dd435 Merge remote-tracking branch 'origin/main' into api_updates_1 Ashwin Bharambe 2024-08-28 16:02:34 -07:00
  • 197f768636 All the new CLI for api + stack work Ashwin Bharambe 2024-08-28 15:52:49 -07:00
  • fd3b65b718 llama distribution -> llama stack + containers (WIP) Ashwin Bharambe 2024-08-28 10:07:08 -07:00
  • 45987996c4 Several smaller fixes to make adapters work Ashwin Bharambe 2024-08-28 09:42:08 -07:00
  • 2a1552a5eb ollama remote adapter works Ashwin Bharambe 2024-08-28 06:51:07 -07:00
  • 2076d2b6db api build works for conda now Ashwin Bharambe 2024-08-27 21:40:43 -07:00
  • c4fe72c3a3 bunch more work to make adapters work Ashwin Bharambe 2024-08-27 19:15:42 -07:00
  • 68f3db62e9 <WIP> adapters Ashwin Bharambe 2024-08-27 11:54:33 -07:00
  • a4af9675ac build + run image seems to work Ashwin Bharambe 2024-08-27 06:12:19 -07:00
  • 6f83187809 fix Ashwin Bharambe 2024-08-27 05:38:54 -07:00
  • 3a337c5f1c Add api build subcommand -- WIP Ashwin Bharambe 2024-08-26 19:19:37 -07:00
  • f5620c09ad Rag Updates Hardik Shah 2024-08-27 20:09:33 -07:00
  • a8b9541f19 Bump version to 0.0.10 Ashwin Bharambe 2024-08-27 04:19:27 -07:00
  • 117b95b38c
    Update RFC-0001-llama-stack.md raghotham 2024-08-26 20:56:09 -07:00
  • c72ce9e726 accounting for eos Hassan El Mghari 2024-08-26 21:24:00 -04:00