Commit graph

  • 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
  • 75bbe787b6 Merge remote-tracking branch 'origin/main' into RFC-0001-The-Llama-Stack Ashwin Bharambe 2024-08-20 18:58:47 -07:00
  • 57881c08c1 Bump version to 0.0.8 Ashwin Bharambe 2024-08-19 20:12:01 -07:00
  • e08e963f86 Add --manifest-file option to argparser Ashwin Bharambe 2024-08-19 18:26:30 -07:00
  • b3da6b8afb Bump version to 0.0.7 Ashwin Bharambe 2024-08-19 16:27:36 -07:00
  • 23de941424 Bump version to 0.0.6 Ashwin Bharambe 2024-08-19 14:12:18 -07:00
  • 38244c3161 llama_models.llama3_1 -> llama_models.llama3 Ashwin Bharambe 2024-08-19 10:55:37 -07:00
  • f502716cf7 Fix ShieldType Union equality bug dltn 2024-08-18 19:13:15 -07:00
  • 63ae942f2f
    Update cli_reference.md with conda init and activate Anisha Nainani 2024-08-17 16:18:14 -05:00
  • 5e072d0780 Add a --manifest-file option to llama download Ashwin Bharambe 2024-08-17 10:08:00 -07:00
  • 124b2c1854 First cut at an observability API Ashwin Bharambe 2024-08-15 16:53:53 -07:00
  • 1f5eb9ff96 Add OpenAPI generation utility, update SPEC to reflect latest types Ashwin Bharambe 2024-08-15 13:45:45 -07:00
  • b8fc4d4dee
    Updates to prompt for tool calls (#29) Hardik Shah 2024-08-15 13:23:51 -07:00
  • f8623459fe added docstrings for ToolPromptFormat Hardik Shah 2024-08-15 13:03:39 -07:00
  • 00053b5bb0 function_tag system prompt is also added as a user message Hardik Shah 2024-08-15 12:11:35 -07:00
  • 417ba2aea0 RFC-0001-The-Llama-Stack Raghotham Murthy 2024-07-23 08:45:38 -07:00
  • 0d933ac4c5 No need for unnecessary $(conda run ...) to get python interpreter Ashwin Bharambe 2024-08-14 20:48:35 -07:00
  • 00f0e6d92b
    Avoid using nearly double the memory needed (#30) Ashwin Bharambe 2024-08-14 17:44:36 -07:00
  • 82667f460e Avoid using nearly double the memory needed Ashwin Bharambe 2024-08-14 17:08:54 -07:00
  • 8e526b9536 JSON in caps Hardik Shah 2024-08-14 15:26:23 -07:00
  • 86df597a83 support json format Hardik Shah 2024-08-14 12:43:43 -07:00
  • 48b78430eb Add tool prompt formats Hardik Shah 2024-08-13 16:00:47 -07:00
  • 0c3e754453 update system prompts to drop new line Hardik Shah 2024-08-13 13:01:05 -07:00
  • b311dcd143 formatting Dalton Flanagan 2024-08-14 17:03:43 -04:00
  • 069d877210 Typo bugfix (rename variable x -> prompt) Ashwin Bharambe 2024-08-14 13:47:27 -07:00
  • b6ccaf1778 formatting Dalton Flanagan 2024-08-14 14:22:25 -04:00
  • 94dfa293a6 Bump version to 0.0.5 Hardik Shah 2024-08-13 15:23:57 -07:00
  • 432957d6b6 fix typo dltn 2024-08-13 11:39:57 -07:00
  • 7f13853e5e
    Update README.md Hardik Shah 2024-08-12 17:10:02 -07:00
  • e459670a9c
    Update README.md Hamid Shojanazeri 2024-08-12 16:10:08 -07:00
  • 37da47ef8e upgrade pydantic to latest Hardik Shah 2024-08-12 15:14:21 -07:00
  • 2cd8b2ff5b Add simple validation for RemoteProviderConfig Ashwin Bharambe 2024-08-09 15:15:20 -07:00
  • 898cd5b352 Bump version to 0.0.4 dltn 2024-08-08 15:24:45 -07:00
  • 416097a9ea
    Rename inline -> local (#24) Dalton Flanagan 2024-08-08 17:39:03 -04:00
  • 6c6c75e716 further rename dltn 2024-08-08 14:29:13 -07:00
  • 640741c639 Rename the "inline" distribution to "local" Ashwin Bharambe 2024-08-08 14:05:49 -07:00
  • dd15671f7f Bump version to 0.0.3 Ashwin Bharambe 2024-08-08 13:40:03 -07:00
  • e830814399
    Introduce Llama stack distributions (#22) Ashwin Bharambe 2024-08-08 13:38:41 -07:00
  • 50775b7120 fix PIP_ARGS Ashwin Bharambe 2024-08-08 13:34:59 -07:00
  • 8ff9523747 Must install llama-models at that same version first Ashwin Bharambe 2024-08-08 13:11:14 -07:00
  • 6441b78aac Fix #2 to help with testing packages Ashwin Bharambe 2024-08-08 13:05:47 -07:00
  • 83adaae09b allow installing from test.pypi.org Ashwin Bharambe 2024-08-08 12:55:03 -07:00
  • 7b37ed5dae Add scripts to MANIFEST Ashwin Bharambe 2024-08-08 12:28:37 -07:00
  • ad9eaf13bb for inline make 8b model the default Hardik Shah 2024-08-08 10:45:32 -07:00
  • 8d7ecf0c47 Remove additional_pip_packages; move deps to providers Ashwin Bharambe 2024-08-08 10:19:46 -07:00
  • 6de36b6a15 make optional subclasses default to yes for configuration Hardik Shah 2024-08-08 10:23:54 -07:00
  • 55cf1f0642 resort imports Hardik Shah 2024-08-08 10:13:26 -07:00
  • 9e3182216d add validation for configuration input Ashwin Bharambe 2024-08-08 10:04:39 -07:00
  • ab856c174c update dependencies and rely on LLAMA_TOOLCHAIN_DIR for dev purposes Hardik Shah 2024-08-08 08:22:13 -07:00
  • 72b20b6f5a Avoid using conda run since it buffers everything Ashwin Bharambe 2024-08-07 22:21:38 -07:00