Files
WrenAI/.gitignore
T
Pao ShengandChihYu Yeh e4dfbb6044 feat(wren-ai-service): Implement the process for the evaluation framework (#525)
* feat: implement prediction process

* feat: implement evaluation process

* feat: add args to specify the eval dataset path

* feat: add args to specify the path of prediction file

* feat: CLI to trigger prediction and evaluation

* chore: ignore deepeval cache

* feat: flushing langfuse before process done

* feat: support average score as a trace

* chore: add readme for the evaluation framework

* fix: append sys path to eval processes to avoid the import error

* chore: upgrade the deepeval version

* chore: rename the command option

* chore: add terms into README

* enhance: using with open instead open file directly

* feat: specify the config to init providers

* feat: current commit hash and branch into metadata

* feat: async to run prediction task

* feat: unify retrieval context and expected context format in the prediction result file

* feat: current commit hash and branch into metadata for average trace

* reorder import

* update method parameter types

* reorder imports

* chore: add date into the prediction file name

---------

Co-authored-by: ChihYu Yeh <chihyu.jimmy.yeh@gmail.com>
2024-07-19 11:03:46 +08:00

89 lines
1.5 KiB
Plaintext

# wren-ai-service
wren-ai-service/.env.*
!wren-ai-service/.env.*.example
!wren-ai-service/src/eval/wren-engine/.env
wren-ai-service/src/eval/wren-engine/**/config.properties
wren-ai-service/src/eval/wren-engine/etc/mdl/*
wren-ai-service/src/eval/wren-engine/etc/duckdb
wren-ai-service/src/eval/wren-engine/etc/archived
wren-ai-service/src/eval/data
wren-ai-service/**/outputs/
wren-ai-service/**/spider/
!wren-ai-service/tests/data
!wren-ai-service/src/eval/data/book_2*.json
!wren-ai-service/src/eval/data/baseball_1*.json
!wren-ai-service/src/eval/data/college_3*.json
!wren-ai-service/src/eval/data/college_3_optimal_ddl.json
wren-ai-service/assertion.log
wren-ai-service/redis.*
wren-ai-service/demo/spider
wren-ai-service/demo/poetry.lock
wren-ai-service/demo/custom_dataset
wren-ai-service/demo/.env
wren-ai-service/tools/dev/etc/**
wren-ai-service/.deepeval-cache.json
# python
.python-version
# cache
__pycache__
local_cache
.ruff_cache
.pytest_cache
# ide
.idea
.vscode/
# os
.DS_Store
__MACOSX/
*.pem
# sqlite
*.sqlite
*.sqlite3
# ui
## dependencies
node_modules
.pnp
.pnp.js
## testing
wren-ui/coverage
wren-ui/test-results
wren-ui/playwright-report
wren-ui/e2e/e2e.config.json
## next.js
wren-ui/.next
wren-ui/out
## production
wren-ui/build
## debug
npm-debug.log*
yarn-debug.log*
yarn-error.log*
## local env files
.env*.local
.env.ai
## vercel
.vercel
## typescript
*.tsbuildinfo
next-env.d.ts
# wren-launcher
wren-launcher/dist
wren-launcher/main
## temporary files
.tmp