plano/arch
Shuguang Chen 88a02dc478
Some fixes on model server (#362)
* Some fixes on model server

* Remove prompt_prefilling message

* Fix logging

* Fix poetry issues

* Improve logging and update the support for text truncation

* Fix tests

* Fix tests

* Fix tests

* Fix modelserver tests

* Update modelserver tests
2025-01-10 16:45:36 -08:00
..
tools Some fixes on model server (#362) 2025-01-10 16:45:36 -08:00
arch_config_schema.yaml Use intent model from archfc to pick prompt gateway (#328) 2024-12-20 13:25:01 -08:00
docker-compose.dev.yaml Use intent model from archfc to pick prompt gateway (#328) 2024-12-20 13:25:01 -08:00
Dockerfile use envoy to publish traces (#270) 2024-11-18 17:55:39 -08:00
env.list Use large github action machine to run e2e tests (#230) 2024-10-30 17:54:51 -07:00
envoy.template.yaml Use intent model from archfc to pick prompt gateway (#328) 2024-12-20 13:25:01 -08:00
README.md update rust toolchain to 1.82 (#255) 2024-11-12 10:35:14 -08:00
requirements.txt simplify developer getting started experience (#102) 2024-10-01 10:02:23 -07:00

Envoy filter code for gateway

Add toolchain

$ rustup target add wasm32-wasip1

Building

$ cargo build --target wasm32-wasip1 --release

Testing

$ cargo test

Local development

  • Build docker image for arch gateway. Note this needs to be built once.

    $ sh build_filter_image.sh
    
  • Build filter binary,

    $ cargo build --target wasm32-wasip1 --release
    
  • Start envoy with arch_config.yaml and test,

    $ docker compose -f docker-compose.dev.yaml up archgw
    
  • dev version of docker-compose file uses following files that are mounted inside the container. That means no docker rebuild is needed if any of these files change. Just restart the container and chagne will be picked up,

    • envoy.template.yaml
    • intelligent_prompt_gateway.wasm