Commit graph

133 commits

Author SHA1 Message Date
Xi Yan
4be6b2732d cleanup distribution_dependencies 2024-09-14 23:19:59 -07:00
Xi Yan
b9f454f613 add build yaml to Dockerfile 2024-09-14 23:18:50 -07:00
Xi Yan
f639e7f80e getting started 2024-09-14 15:56:34 -07:00
Xi Yan
fc912a3e66 getting started guide 2024-09-14 15:51:20 -07:00
Xi Yan
cf897d188b generate distribution specs 2024-09-14 15:03:15 -07:00
Xi Yan
0068d059db move distribution to yaml files 2024-09-14 15:02:22 -07:00
Xi Yan
3802d5acdc add name args to override name 2024-09-14 14:42:02 -07:00
Xi Yan
1fec9930aa more clean up on build 2024-09-14 14:35:10 -07:00
Xi Yan
1855fd2835 update example build files 2024-09-14 14:33:19 -07:00
Xi Yan
e665b652c6 example build files 2024-09-14 14:28:16 -07:00
Xi Yan
318142a17d remove available_distribution_specs 2024-09-14 14:24:29 -07:00
Xi Yan
9e7db7e244 remove resolve_distribution_spec 2024-09-14 14:22:30 -07:00
Xi Yan
f3492040d6 add example build files for conda & docker 2024-09-14 14:21:23 -07:00
Xi Yan
24e21a12e5 fix configure 2024-09-14 14:17:28 -07:00
Xi Yan
3dca86684c clean up build 2024-09-14 14:13:51 -07:00
Xi Yan
085f9fcce3
Merge branch 'main' into cli 2024-09-14 14:10:34 -07:00
Xi Yan
e69e1b8309 [tmp fix] hardware requirement tmp fix 2024-09-14 14:06:36 -07:00
Xi Yan
bafef7ab96 clean up configure 2024-09-14 14:00:10 -07:00
Xi Yan
20157487d4 configure update 2024-09-14 13:59:09 -07:00
Xi Yan
4ed1f38134 update docker build script 2024-09-14 13:46:17 -07:00
Xi Yan
d1f0d17644 update build cli 2024-09-14 13:35:09 -07:00
Ashwin Bharambe
53ab18d6bb Bump version to 0.0.16 2024-09-14 08:09:45 -07:00
Ashwin Bharambe
49ce36426f Make llama model download error message a bit better 2024-09-14 08:06:55 -07:00
Ashwin Bharambe
7a283ea076 Bump version to 0.0.15 2024-09-13 17:23:12 -07:00
Ashwin Bharambe
498cf03617 add pypdf 2024-09-13 17:04:43 -07:00
Ashwin Bharambe
19a14cd273 Nuke hardware_requirements from SKUs 2024-09-13 16:39:02 -07:00
Xi Yan
768ed09dec rename getting started 2024-09-13 14:48:27 -07:00
Xi Yan
27107fbbbd update doc 2024-09-13 14:31:07 -07:00
Xi Yan
245cc88081 add reedme 2024-09-13 14:24:42 -07:00
Xi Yan
dfeb84be5c udpate build script 2024-09-13 14:09:47 -07:00
Xi Yan
9315eae645 remove comments 2024-09-13 14:08:55 -07:00
Xi Yan
62865ce0d2 update memory providers 2024-09-13 13:58:16 -07:00
Xi Yan
73a6589446 configure to regenerate file 2024-09-13 13:39:39 -07:00
Xi Yan
84047928ce remove config from build 2024-09-13 13:18:42 -07:00
Xi Yan
33772da8e0 remove configure from build 2024-09-13 13:17:17 -07:00
raghotham
d8b3fdbd54
Update README.md 2024-09-13 08:56:47 -07:00
Xi Yan
6a863f9b78 Bump version to 0.0.14 2024-09-12 21:24:07 -07:00
Xi Yan
16635508bd Bump version to 0.0.14 2024-09-12 15:11:15 -07:00
Xi Yan
5712566061
Remove request wrapper migration (#64)
* [1/n] migrate inference/chat_completion

* migrate inference/completion

* inference/completion

* inference regenerate openapi spec

* safety api

* migrate agentic system

* migrate apis without implementations

* re-generate openapi spec

* remove hack from openapi generator

* fix inference

* fix inference

* openapi generator rerun

* Simplified Telemetry API and tying it to logger (#57)

* Simplified Telemetry API and tying it to logger

* small update which adds a METRIC type

* move span events one level down into structured log events

---------

Co-authored-by: Ashwin Bharambe <ashwin@meta.com>

* fix api to work with openapi generator

* fix agentic calling inference

* together adapter inference

* update inference adapters

---------

Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
2024-09-12 15:03:49 -07:00
Hardik Shah
1d0e91d802
Support data: in URL for memory. Add ootb support for pdfs (#67)
* support data: in URL for memory. Add ootb support for pdfs

* moved utility to common and updated data_url parsing logic

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
2024-09-12 13:00:21 -07:00
Celina Hanouti
736092f6bc
[Inference] Use huggingface_hub inference client for TGI adapter (#53)
* Use huggingface_hub inference client for TGI inference

* Update the default value for TGI URL

* Use InferenceClient.text_generation for TGI inference

* Fixes post-review and split TGI adapter into local and Inference Endpoints ones

* Update CLI reference and add typing

* Rename TGI Adapter class

* Use HfApi to get the namespace when not provide in the hf endpoint name

* Remove unecessary method argument

* Improve TGI adapter initialization condition

* Move helper into impl file + fix merging conflicts
2024-09-12 09:11:35 -07:00
Ashwin Bharambe
191cd28831
Simplified Telemetry API and tying it to logger (#57)
* Simplified Telemetry API and tying it to logger

* small update which adds a METRIC type

* move span events one level down into structured log events

---------

Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
2024-09-11 14:25:37 -07:00
Xi Yan
1433aaf9f7 add CODEOWNERS file 2024-09-11 11:40:37 -07:00
Xi Yan
89300df5dc
Add config file based CLI (#60)
* config file for build

* fix build command

* configure script with config

* fix configure script to work with config file

* update build.sh

* update readme

* distribution_type -> distribution

* fix run-config/config-file to config

* move import to inline

* only consume config as argument

* update configure to only consume config

* update readme

* update readme
2024-09-11 11:39:46 -07:00
Xi Yan
58def874a9
add safety to openapi spec (#62) 2024-09-10 17:47:13 -07:00
Hardik Shah
a11d92601b
Enable Bing search (#59)
* add tool for bing search

* simplify search tool and enable configuration for search engine

* dropped commented code

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
2024-09-10 12:34:29 -07:00
Dalton Flanagan
2b63074676 add /inference/chat_completion to SSE special case 2024-09-10 01:14:11 -04:00
Xi Yan
4f021de10f
API spec update, client demo with Stainless SDK (#58)
* [wip] client w/ stainless sdk

* update generator & yaml spec

* update wrapper request

* update script

* agentic system client sdk

* add comment todos

* remove client sdk examples
2024-09-09 13:09:47 -07:00
Ashwin Bharambe
741310f78e rename observability -> Telemetry; regen Spec 2024-09-07 15:23:53 -07:00
Ashwin Bharambe
70e682fbdf Update distribution_id -> distribution_type, provider_id -> provider_type 2024-09-07 08:42:28 -07:00