Commit graph

  • 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
  • 279017e37a working! Hassan El Mghari 2024-08-26 21:01:36 -04:00
  • ea6d9ec937 templates take optional --format={json,function_tag} Hardik Shah 2024-08-26 17:42:09 -07:00
  • 69d9655ecd Add ToolPromptFormat to ChatFormat.encode_message so that tools are encoded properly Hardik Shah 2024-08-26 17:03:34 -07:00
  • 870cd7bb8b Add blobfile for tiktoken Ashwin Bharambe 2024-08-26 14:50:20 -07:00
  • decbbc127b Add blobfile for tiktoken Ashwin Bharambe 2024-08-26 14:50:20 -07:00
  • fd1c7f0197 Fix api.datatypes imports Ashwin Bharambe 2024-08-26 14:43:30 -07:00
  • fb78bdc5a9 use interleaved_text_media_as_str() utilityt Ashwin Bharambe 2024-08-26 14:40:03 -07:00
  • e61b3d91ef use a single impl for ChatFormat.decode_assistant_mesage Hardik Shah 2024-08-26 14:27:20 -07:00
  • c3708859aa minor import fixes Hardik Shah 2024-08-26 14:21:35 -07:00
  • dc433f6c90 split batch_inference from inference Ashwin Bharambe 2024-08-26 13:17:59 -07:00
  • 986a865e62 Attachment / add TTL api Ashwin Bharambe 2024-08-26 13:10:27 -07:00
  • 3230af4910 combine datatypes.py and endpoints.py into api.py Ashwin Bharambe 2024-08-26 12:55:28 -07:00
  • c1078a60e7 remove api.endpoints imports Ashwin Bharambe 2024-08-26 11:18:42 -07:00
  • df489261ac add special unicode character ↵ to showcase newlines in model prompt templates Hardik Shah 2024-08-26 07:35:44 -07:00
  • 091eca0ba4 No need for api_key for Remote providers Ashwin Bharambe 2024-08-25 21:14:16 -07:00
  • 0760849a1f Bug fix, show memory retrieval steps in EventLogger Ashwin Bharambe 2024-08-25 15:03:49 -07:00
  • ceef117abc Refactor custom tool execution utilities Ashwin Bharambe 2024-08-25 14:34:20 -07:00
  • 40ca8e21bd
    Fireworks basic integration (#39) Yufei (Benny) Chen 2024-08-25 08:05:52 -07:00
  • 440d125ea0 small bug fixes for inline attachments Ashwin Bharambe 2024-08-24 23:51:27 -07:00
  • 58e2feceb0 basic RAG seems to work Ashwin Bharambe 2024-08-24 23:36:58 -07:00
  • 830252257b fix agentic_system utils Ashwin Bharambe 2024-08-24 22:56:43 -07:00
  • 8efe614719 re-work tool definitions, fix FastAPI issues, fix tool regressions Ashwin Bharambe 2024-08-24 22:07:06 -07:00
  • 8d14d4228b memory client works Ashwin Bharambe 2024-08-24 18:43:49 -07:00
  • a08958c000 faiss provider implementation Ashwin Bharambe 2024-08-23 20:58:27 -07:00
  • f812648aca Bump version to 0.0.9 Ashwin Bharambe 2024-08-24 09:45:01 -07:00
  • 2a768f0485 Fireworks basic integration benjibc 2024-08-23 05:15:54 +00:00
  • 14637bea66 agentic loop has a RAG implementation Ashwin Bharambe 2024-08-23 15:20:40 -07:00
  • 77d6055d9f flesh out memory banks API Ashwin Bharambe 2024-08-23 06:38:15 -07:00
  • 31289e3f47 InterleavedTextAttachment -> InterleavedTextMedia, introduce memory tool Ashwin Bharambe 2024-08-22 17:44:56 -07:00
  • 48c6a32edd <WIP> memory changes Ashwin Bharambe 2024-08-14 13:46:44 -07:00
  • 5655266d58 Moved ToolPromptFormat and jinja templates to llama_models.llama3.api Hardik Shah 2024-08-23 14:58:52 -07:00
  • ab8193c88c use templates for generating system prompts Hardik Shah 2024-08-23 14:21:12 -07:00
  • c1a82ea8cd Add a script for install a pip wheel from a presigned url Ashwin Bharambe 2024-08-23 12:06:50 -07:00
  • 68855ed218 add tools to chat completion request Hardik Shah 2024-08-21 17:48:48 -07:00
  • 9777639a1c
    Updated URLs and addressed feedback (#37) varunfb 2024-08-22 13:34:46 -07:00
  • 8307211d18 Updated URLs and addressed feedback vontimitta 2024-08-22 20:32:15 +00:00
  • 4930616ec7
    Updated cli instructions with additonal details for each subcommands (#36) varunfb 2024-08-22 12:20:47 -07:00
  • 6daee405fa Updated cli instructions with additonal details for each subcommands vontimitta 2024-08-22 18:59:25 +00:00
  • 49f2bbbaeb
    fixed bug in download not enough disk space condition (#35) sisminnmaw 2024-08-23 00:10:47 +09:00
  • 1612d7e68f fixed bug in download not enough disk space condition sisminnmaw 2024-08-22 21:18:33 +09:00
  • b4af8c0e00
    update cli ref doc: llama model template names related; separation of copy-and-pastable commands with their outputs (#34) Jeff Tang 2024-08-21 20:41:30 -07:00
  • 2789f6174e update cli ref doc: llama model template names related; separation of copy-and-pastable commands with their outputs Jeff Tang 2024-08-21 17:49:20 -07:00
  • f3f7af7b8a add tools to chat completion request Hardik Shah 2024-08-21 17:48:48 -07:00
  • 863bb915e1 Remove quantization_config from the APIs for now Ashwin Bharambe 2024-08-21 14:17:05 -07:00
  • ab0a24f333
    Add API keys to AgenticSystemConfig instead of relying on dotenv (#33) Ashwin Bharambe 2024-08-21 12:35:59 -07:00
  • face3ceff1 suppress warning in CLI Ashwin Bharambe 2024-08-21 12:25:13 -07:00
  • 948610b6af Merge remote-tracking branch 'origin/main' into apikeys Ashwin Bharambe 2024-08-21 12:24:41 -07:00
  • 529c564366 Add API keys to AgenticSystemConfig instead of relying on dotenv Ashwin Bharambe 2024-08-21 05:28:28 -07:00
  • 270b5502d7 broaden URL match in download for older model families Dalton Flanagan 2024-08-21 12:11:11 -04:00
  • 2232bfa8b5
    RFC-0001-The-Llama-Stack (#8) raghotham 2024-08-20 19:01:18 -07:00
  • c736e5b576 llama3_1 -> llama3 Ashwin Bharambe 2024-08-20 19:00:47 -07:00