Commit graph

48 commits

Author SHA1 Message Date
Xi Yan
af8ecac5f5 Revert "add new resolve_impls_with_routing"
This reverts commit 34f0c11001.
2024-09-21 12:42:10 -07:00
Xi Yan
cf8bd10989 Revert "migrate router for memory wip"
This reverts commit 08379f5214.
2024-09-21 12:42:09 -07:00
Xi Yan
3939611676 Revert "delete router from providers"
This reverts commit d8fab77a4f.
2024-09-21 12:42:09 -07:00
Xi Yan
515bec300c Revert "clean up"
This reverts commit bc4ac2ceb4.
2024-09-21 12:42:08 -07:00
Xi Yan
50d95a668b Revert "simple run config"
This reverts commit 756e98cbd8.
2024-09-21 12:42:08 -07:00
Xi Yan
74765cc78f Revert "backward compatibility"
This reverts commit 6a95edc806.
2024-09-21 12:42:08 -07:00
Xi Yan
3ea55d9b0f Revert "stage tmp changes"
This reverts commit 164d0e25c7.
2024-09-21 12:42:07 -07:00
Xi Yan
164d0e25c7 stage tmp changes 2024-09-21 12:32:26 -07:00
Xi Yan
6a95edc806 backward compatibility 2024-09-21 12:31:59 -07:00
Xi Yan
756e98cbd8 simple run config 2024-09-21 12:31:59 -07:00
Xi Yan
bc4ac2ceb4 clean up 2024-09-21 12:31:59 -07:00
Xi Yan
d8fab77a4f delete router from providers 2024-09-21 12:31:59 -07:00
Xi Yan
08379f5214 migrate router for memory wip 2024-09-21 12:31:59 -07:00
Xi Yan
34f0c11001 add new resolve_impls_with_routing 2024-09-21 12:31:59 -07:00
Xi Yan
73399fe905 example config 2024-09-21 12:31:59 -07:00
Ashwin Bharambe
e5a7001874 Further bug fixes 2024-09-20 15:15:57 -07:00
Ashwin Bharambe
9e16b0948b test safety against safety client 2024-09-20 14:55:00 -07:00
Ashwin Bharambe
6e0f283f52 Update safety implementation inside agents 2024-09-20 14:27:54 -07:00
Ashwin Bharambe
51245a417b Update the meta reference safety implementation to match new API 2024-09-20 14:17:44 -07:00
Ashwin Bharambe
93e4ef3829 safety API cleanup part 1
Sample adapter implementation for Bedrock implementation of Guardrails
2024-09-20 13:34:49 -07:00
Ashwin Bharambe
90a59fd89b Add a special header per-client call to parser provider data 2024-09-20 13:34:34 -07:00
Ashwin Bharambe
942cb87a3c remove apis/stack.py 2024-09-20 09:37:08 -07:00
Hardik Shah
7e9e6117e3 do not assume CONDA_PREFIX exists during configuration 2024-09-19 23:39:34 -07:00
Hardik Shah
8fa49593e0
Allow TGI adaptor to have non-standard llama model names (#84)
Co-authored-by: Hardik Shah <hjshah@fb.com>
2024-09-19 21:42:15 -07:00
Hardik Shah
42d29f3a5a Allow TGI adaptor to have non-standard llama model names 2024-09-19 21:37:02 -07:00
Xi Yan
59af1c8fec
fix memory url parsing (#81) 2024-09-19 13:35:03 -07:00
Ashwin Bharambe
132f9429b1 Add a test for CLI, but not fully done so disabled 2024-09-19 13:27:07 -07:00
Ashwin Bharambe
8b3ffa33de Add another test case 2024-09-19 13:02:57 -07:00
Ashwin Bharambe
abb43936ab Add a test runner and 2 very simple tests for agents 2024-09-19 12:22:48 -07:00
Xi Yan
543222ac39 update inference prompt msg 2024-09-19 12:03:24 -07:00
Xi Yan
a30b919ae1 update inference prompt msg 2024-09-19 12:03:24 -07:00
Ashwin Bharambe
9eb01dd664 Add DOCKER_BINARY / DOCKER_OPTS to all scripts 2024-09-19 10:26:41 -07:00
Xi Yan
ca4b87aa05 fix memory client 2024-09-19 09:29:40 -07:00
Xi Yan
6302a1ee90
fix prompt with name args (#80) 2024-09-18 23:48:31 -07:00
Ashwin Bharambe
c63d6cbd08 list(...keys()) so dict_keys does not show up 2024-09-18 23:24:07 -07:00
Ashwin Bharambe
f5eda1decf Add default for max_seq_len 2024-09-18 21:59:10 -07:00
Ashwin Bharambe
9ab27e852b Bug fixes for memory 2024-09-18 21:54:02 -07:00
Ashwin Bharambe
8cdc2f0cfb No RunShieldRequest 2024-09-18 20:38:21 -07:00
Ashwin Bharambe
dff9eab48f Remove "APIs to serve" prompt 2024-09-18 18:26:26 -07:00
Xi Yan
f5d5e32d62 fix docker configure 2024-09-18 17:23:37 -07:00
Xi Yan
1128f69674
CLI: add build templates support, move imports (#77)
* list templates implementation

* relative path

* finalize templates

* remove imports

* remove templates from name, name templates

* fix docker

* fix docker
2024-09-18 14:25:53 -07:00
Xi Yan
6b21523c28
CLI - add back build wizard, configure with name instead of build.yaml (#74)
* add back wizard for build

* conda build path move

* polish message

* run with name only

* prompt for build

* improve comments

* update msgs

* add new lines

* move build.yaml

* address comments

* validator for providers

* move imports

* Please enter -> enter

* comments, get started guide

* nits

* fix cprint import

* fix imports
2024-09-18 11:41:56 -07:00
Xi Yan
e6fdb9df29
fix context retriever (#75) 2024-09-18 08:24:36 -07:00
Ashwin Bharambe
055770a791 Stop asking for "apis to serve" as part of configure 2024-09-17 22:41:10 -07:00
Ashwin Bharambe
9fd431e710 make shield imports more lazy 2024-09-17 21:27:37 -07:00
Ashwin Bharambe
3e27131a69 Don't import pkg_resources until you need it 2024-09-17 20:01:22 -07:00
Ashwin Bharambe
25adc83de8 Fix for safety 2024-09-17 19:56:58 -07:00
Ashwin Bharambe
9487ad8294
API Updates (#73)
* API Keys passed from Client instead of distro configuration

* delete distribution registry

* Rename the "package" word away

* Introduce a "Router" layer for providers

Some providers need to be factorized and considered as thin routing
layers on top of other providers. Consider two examples:

- The inference API should be a routing layer over inference providers,
  routed using the "model" key
- The memory banks API is another instance where various memory bank
  types will be provided by independent providers (e.g., a vector store
  is served by Chroma while a keyvalue memory can be served by Redis or
  PGVector)

This commit introduces a generalized routing layer for this purpose.

* update `apis_to_serve`

* llama_toolchain -> llama_stack

* Codemod from llama_toolchain -> llama_stack

- added providers/registry
- cleaned up api/ subdirectories and moved impls away
- restructured api/api.py
- from llama_stack.apis.<api> import foo should work now
- update imports to do llama_stack.apis.<api>
- update many other imports
- added __init__, fixed some registry imports
- updated registry imports
- create_agentic_system -> create_agent
- AgenticSystem -> Agent

* Moved some stuff out of common/; re-generated OpenAPI spec

* llama-toolchain -> llama-stack (hyphens)

* add control plane API

* add redis adapter + sqlite provider

* move core -> distribution

* Some more toolchain -> stack changes

* small naming shenanigans

* Removing custom tool and agent utilities and moving them client side

* Move control plane to distribution server for now

* Remove control plane from API list

* no codeshield dependency randomly plzzzzz

* Add "fire" as a dependency

* add back event loggers

* stack configure fixes

* use brave instead of bing in the example client

* add init file so it gets packaged

* add init files so it gets packaged

* Update MANIFEST

* bug fix

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Xi Yan <xiyan@meta.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
2024-09-17 19:51:35 -07:00