phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-30 07:39:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
92 commits 78 branches 89 tags 90 MiB
Commit graph

92 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ashwin Bharambe
2076d2b6db api build works for conda now 2024-08-28 15:55:21 -07:00
Ashwin Bharambe
c4fe72c3a3 bunch more work to make adapters work 2024-08-28 15:55:18 -07:00
Ashwin Bharambe
68f3db62e9 <WIP> adapters 2024-08-28 15:54:31 -07:00
Ashwin Bharambe
a4af9675ac build + run image seems to work 2024-08-28 15:54:31 -07:00
Ashwin Bharambe
6f83187809 fix 2024-08-28 15:54:31 -07:00
Ashwin Bharambe
3a337c5f1c Add api build subcommand -- WIP 2024-08-28 15:54:31 -07:00
Hardik Shah
f5620c09ad Rag Updates 2024-08-27 20:09:33 -07:00
Hardik Shah
ea6d9ec937 templates take optional --format={json,function_tag} 2024-08-26 17:42:24 -07:00
Hardik Shah
69d9655ecd Add ToolPromptFormat to ChatFormat.encode_message so that tools are encoded properly 2024-08-26 17:42:24 -07:00
Ashwin Bharambe
decbbc127b Add blobfile for tiktoken 2024-08-26 14:50:20 -07:00
Ashwin Bharambe
fd1c7f0197 Fix api.datatypes imports 2024-08-26 14:43:30 -07:00
Ashwin Bharambe
fb78bdc5a9 use interleaved_text_media_as_str() utilityt 2024-08-26 14:40:28 -07:00
Hardik Shah
e61b3d91ef use a single impl for ChatFormat.decode_assistant_mesage 2024-08-26 14:27:32 -07:00
Hardik Shah
c3708859aa minor import fixes 2024-08-26 14:27:32 -07:00
Ashwin Bharambe
dc433f6c90 split batch_inference from inference 2024-08-26 13:21:37 -07:00
Ashwin Bharambe
986a865e62 Attachment / add TTL api 2024-08-26 13:11:37 -07:00
Ashwin Bharambe
3230af4910 combine datatypes.py and endpoints.py into api.py 2024-08-26 12:58:04 -07:00
Ashwin Bharambe
c1078a60e7 remove api.endpoints imports 2024-08-26 12:58:04 -07:00
Hardik Shah
df489261ac add special unicode character ↵ to showcase newlines in model prompt templates 2024-08-26 07:35:49 -07:00
Ashwin Bharambe
091eca0ba4 No need for api_key for Remote providers 2024-08-25 21:14:16 -07:00
Ashwin Bharambe
0760849a1f Bug fix, show memory retrieval steps in EventLogger 2024-08-25 15:03:49 -07:00
Ashwin Bharambe
ceef117abc Refactor custom tool execution utilities 2024-08-25 14:34:20 -07:00
Ashwin Bharambe
440d125ea0 small bug fixes for inline attachments 2024-08-24 23:51:27 -07:00
Ashwin Bharambe
58e2feceb0 basic RAG seems to work 2024-08-24 23:36:58 -07:00
Ashwin Bharambe
830252257b fix agentic_system utils 2024-08-24 22:56:43 -07:00
Ashwin Bharambe
8efe614719 re-work tool definitions, fix FastAPI issues, fix tool regressions 2024-08-24 22:35:56 -07:00
Ashwin Bharambe
8d14d4228b memory client works 2024-08-24 18:43:49 -07:00
Ashwin Bharambe
a08958c000 faiss provider implementation 2024-08-24 14:50:08 -07:00
Ashwin Bharambe
14637bea66 agentic loop has a RAG implementation 2024-08-23 21:01:11 -07:00
Ashwin Bharambe
77d6055d9f flesh out memory banks API 2024-08-23 21:01:08 -07:00
Ashwin Bharambe
31289e3f47 InterleavedTextAttachment -> InterleavedTextMedia, introduce memory tool 2024-08-23 21:00:19 -07:00
Ashwin Bharambe
48c6a32edd <WIP> memory changes 
- inlined AgenticSystemInstanceConfig so API feels more ergonomic
- renamed it to AgentConfig, AgentInstance -> Agent
- added a MemoryConfig and `memory` parameter
- added `attachments` to input and `output_attachments` to the response

- some naming changes
 2024-08-23 21:00:17 -07:00
Hardik Shah
5655266d58 Moved ToolPromptFormat and jinja templates to llama_models.llama3.api 2024-08-23 14:58:52 -07:00
Hardik Shah
ab8193c88c use templates for generating system prompts 2024-08-23 14:21:12 -07:00
Hardik Shah
68855ed218 add tools to chat completion request 2024-08-22 15:57:59 -07:00
varunfb
9777639a1c
Updated URLs and addressed feedback (#37) 2024-08-22 13:34:46 -07:00
varunfb
4930616ec7
Updated cli instructions with additonal details for each subcommands (#36) 2024-08-22 12:20:47 -07:00
sisminnmaw
49f2bbbaeb
fixed bug in download not enough disk space condition (#35) 
bug:
used undeclared variable in download.py.
when the disk space not enough NameError occured.
 2024-08-22 08:10:47 -07:00
Jeff Tang
b4af8c0e00
update cli ref doc: llama model template names related; separation of copy-and-pastable commands with their outputs (#34) 2024-08-21 20:41:30 -07:00
Ashwin Bharambe
863bb915e1 Remove quantization_config from the APIs for now 2024-08-21 14:17:50 -07:00
Ashwin Bharambe
ab0a24f333
Add API keys to AgenticSystemConfig instead of relying on dotenv (#33) 2024-08-21 12:35:59 -07:00
Ashwin Bharambe
face3ceff1 suppress warning in CLI 2024-08-21 12:25:39 -07:00
Dalton Flanagan
270b5502d7 broaden URL match in download for older model families 2024-08-21 12:11:11 -04:00
raghotham
2232bfa8b5
RFC-0001-The-Llama-Stack (#8) 
* RFC-0001-The-Llama-Stack

* Add OpenAPI generation utility, update SPEC to reflect latest types

* First cut at an observability API

* llama3_1 -> llama3

---------

Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
 2024-08-20 19:01:18 -07:00
Ashwin Bharambe
57881c08c1 Bump version to 0.0.8 2024-08-19 20:12:01 -07:00
Ashwin Bharambe
e08e963f86 Add --manifest-file option to argparser 2024-08-19 18:26:56 -07:00
Ashwin Bharambe
b3da6b8afb Bump version to 0.0.7 2024-08-19 16:27:36 -07:00
Ashwin Bharambe
23de941424 Bump version to 0.0.6 2024-08-19 14:12:18 -07:00
Ashwin Bharambe
38244c3161 llama_models.llama3_1 -> llama_models.llama3 2024-08-19 10:55:37 -07:00
dltn
f502716cf7 Fix ShieldType Union equality bug 2024-08-18 19:13:15 -07:00