apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-04-28 02:23:56 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions
plano/tests/e2e
History
Salman Paracha 88c2bd1851
removing model_server python module to brightstaff (function calling) (#615) 
* adding function_calling functionality via rust

* fixed rendered YAML file

* removed model_server from envoy.template and forwarding traffic to bright_staff

* fixed bugs in function_calling.rs that were breaking tests. All good now

* updating e2e test to clean up disk usage

* removing Arch* models to be used as a default model if one is not specified

* if the user sets arch-function base_url we should honor it

* fixing demos as we needed to pin to a particular version of huggingface_hub else the chatbot ui wouldn't build

* adding a constant for Arch-Function model name

* fixing some edge cases with calls made to Arch-Function

* fixed JSON parsing issues in function_calling.rs

* fixed bug where the raw response from Arch-Function was re-encoded

* removed debug from supervisord.conf

* commenting out disk cleanup

* adding back disk space

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-288.local>
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-342.local>
2025-11-22 12:55:00 -08:00
..
.vscode better model names (#517) 2025-07-11 16:42:16 -07:00
common.py Use intent model from archfc to pick prompt gateway (#328) 2024-12-20 13:25:01 -08:00
common_scripts.sh Use intent model from archfc to pick prompt gateway (#328) 2024-12-20 13:25:01 -08:00
docker-compose.yaml add support for v1/messages and transformations (#558) 2025-09-10 07:40:30 -07:00
poetry.lock add support for v1/messages and transformations (#558) 2025-09-10 07:40:30 -07:00
pyproject.toml add support for v1/messages and transformations (#558) 2025-09-10 07:40:30 -07:00
README.md Use intent model from archfc to pick prompt gateway (#328) 2024-12-20 13:25:01 -08:00
response.hex Add support for Amazon Bedrock Converse and ConverseStream (#588) 2025-10-22 11:31:21 -07:00
response_with_tools.hex Add support for Amazon Bedrock Converse and ConverseStream (#588) 2025-10-22 11:31:21 -07:00
run_e2e_tests.sh adding support for model aliases in archgw (#566) 2025-09-16 11:12:08 -07:00
test_model_alias_routing.py fixed test and docs for deployment (#595) 2025-10-22 14:13:16 -07:00
test_prompt_gateway.py removing model_server python module to brightstaff (function calling) (#615) 2025-11-22 12:55:00 -08:00

README.md

e2e tests

e2e tests for arch llm gateway and prompt gateway

To be able to run e2e tests successfully run_e2e_script prepares environment in following way,

  1. build and start weather_forecast demo (using docker compose)
  2. build, install and start model server async (using poetry)
  3. build and start arch gateway (using docker compose)
  4. wait for model server to be ready
  5. wait for arch gateway to be ready
  6. start e2e tests (using poetry)
    1. runs llm gateway tests for llm routing
    2. runs prompt gateway tests to test function calling, parameter gathering and summarization
  7. cleanup
    1. stops arch gateway
    2. stops model server
    3. stops weather_forecast demo

How to run

To run locally make sure that following requirements are met.

Requirements

  • Python 3.10
  • Poetry
  • Docker

Running tests locally

sh run_e2e_test.sh