Arch is an intelligent prompt gateway. Engineered with (fast) LLMs for the secure handling, robust observability, and seamless integration of prompts with APIs - all outside business logic. Built by the core contributors of Envoy proxy, on Envoy.
1/ removes download_models as a separate CLI command and merge the functionality in "up"
2/ archgw logs now defaults to access logs, you can use --debug to get archgw and model_server logs via --service name
3/ adds a simple test case to test the main method, paving way for more tests in the future.
4/ Fixed issues in README.md
The following PR does a couple of things
1/ removes download_models as a separate CLI command and merge the functionality in "up" 2/ archgw logs now defaults to access logs, you can use --debug to get archgw and model_server logs via --service name 3/ adds a simple test case to test the main method, paving way for more tests in the future. 4/ Fixed issues in README.md