BROccoLi-921 GitHub avatar

AI-testing-evaluation

BROccoLi-921

A self-hosted AI customer service quality evaluation and knowledge improvement workbench for single-administrator, single-server deployment.

Stars

4

7-day growth

No data

Forks

0

Open issues

0

License

No data

Last updated

2026-07-29

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It provides an end-to-end pipeline for uploading knowledge, importing conversations, creating evaluation batches, and iteratively improving AI agent responses based on automated quality assessments.

Who it is for

  • Customer service operations managers
  • AI chatbot quality assurance teams
  • Developers building or maintaining AI customer service systems

Use cases

  • Evaluate the quality of existing AI customer service conversations
  • Identify knowledge gaps and improve the knowledge base through batch scoring
  • Simulate and test AI responses with imported dialogues before production deployment

Strengths

  • Self-contained Docker Compose setup for easy local deployment
  • Includes automated testing (pytest), linting (ruff), and type checking (mypy) for code quality
  • Clear business and technical requirements defined in AGENTS.md and docs/requirements.md
  • Designed for iterative improvement with a clear workflow from data import to evaluation

Considerations

  • Single-administrator, single-server architecture – not suitable for multi‑user or high‑scale production environments
  • Requires manual configuration of API keys and initial data import (knowledge, conversations)
  • No built‑in support for A/B testing or advanced analytics beyond batch evaluation

README quick start

AI 测评自迭代工作台

单管理员、单服务器部署的 AI 客服质量评测与知识改进工作台。

本地启动

需要 Python 3.12、Docker、Docker Compose。

cp .env.example .env
docker compose up --build
docker compose exec web python manage.py createsuperuser

访问 http://127.0.0.1:8000,登录后依次配置密钥、上传知识、导入对话并创建评测批次。

本地测试

python3.12 -m venv .venv
.venv/bin/pip install -e '.[dev]'
.venv/bin/pytest
.venv/bin/ruff check .
.venv/bin/mypy apps config

业务与技术约束以 AGENTS.mddocs/requirements.md 为准。

Related repositories

Similar projects matched by category, topics, and programming language.

vercel-labs
Featured
vercel-labs GitHub avatar

scriptc

scriptc compiles ordinary TypeScript into small, fast native executables without needing Node.js, V8, or any JavaScript runtime in the binary.

Developer ToolsCode Quality & Build
1,985
jamesob
Featured
jamesob GitHub avatar

local-llm

A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.

AI & Machine LearningLarge Language Models
1,660
mereyabdenbekuly-ctrl
Featured
mereyabdenbekuly-ctrl GitHub avatar

clodex-ide

Clodex is an open-source, local-first agentic IDE that combines persistent AI tasks, code, terminal, browser, Git, models, memory, and governed execution in one Electron workspace, currently in technical preview.

AI & Machine LearningAI Agents
859