Certifiedunder the Production-Grade Agentic System module in the Agentic AI In Production program.Certifiedunder the Production-Grade Agentic System module in the Agentic AI In Production program.A production-ready multi-agent system that analyzes software repositories, generates comprehensive documentation, and provides intelligent question-answering capabilities. Built with LangGraph, integrated with Cohere LLM, Jina embeddings, and Qdrant vector database.
This project demonstrates how multi-agent AI systems solve critical challenges in modern software development:
| Feature | Multi-Agent Assistant | GitHub Copilot Docs |
|---|---|---|
| Article Generation | ✅ Full structured articles | ❌ Code snippets only |
| Repository Analysis | ✅ Deep structural analysis | ❌ File-level only |
| Q&A Capability | ✅ Context-aware answers | ❌ Pattern-based |
| Offline Use | ✅ Supported | ❌ Requires internet |
| Cost | 💰 Pay-per-API | 💰 Monthly subscription |
| Aspect | Multi-Agent Assistant | Traditional Tools |
|---|---|---|
| Automation Level | ✅ Fully automated | ❌ Manual templating |
| Intelligence | ✅ AI-driven insights | ❌ Static templates |
| Learning Curve | ✅ Minimal | ⚠️ Moderate |
| Customization | ✅ AI instructions | ⚠️ Configuration files |
WCAG 2.1 Compliance (Level AA):
Keyboard Navigation:
Screen Reader Support:
Responsive Design:
cd multiagent-repo-assistant python -m venv venv venv\Scripts\activate # Windows # source venv/bin/activate # macOS/Linux
pip install -r requirements.txt
.env file):# Qdrant Cloud QDRANT_URL=https://your-instance.qdrant.io QDRANT_API_KEY=your_api_key QDRANT_COLLECTION=repo_chunks EMBEDDING_DIM=1024 # Cohere COHERE_API_KEY=your_api_key # Jina JINA_API_KEY=your_api_key JINA_EMBEDDING_MODEL=jina-embeddings-v3
# Using LangGraph orchestrator (default) python main.py analyze --repo path/to/repo # Save results to JSON python main.py analyze --repo path/to/repo --output results.json # Use simple orchestrator python main.py analyze --repo path/to/repo --orchestrator simple
# Interactive QA python main.py ask --repo path/to/repo --query "how to install?" # Specify number of context results python main.py ask --repo path/to/repo --query "what is this project?" --top-k 10
# Run complete analysis pipeline python main.py pipeline --repo path/to/repo --output analysis.json
# Start interactive Q&A session python main.py interactive --repo path/to/repo
from orchestrator.langgraph_flow import run_langgraph_pipeline from agents.qa_agent import QAAgent # Run complete pipeline result = run_langgraph_pipeline("path/to/repo") # Use QA agent qa = QAAgent() answer = qa.answer("How to use this project?", top_k=5) print(answer)
┌─────────────────┐
│ Repository │
│ Input │
└────────┬────────┘
│
▼
┌─────────────────┐ ┌──────────────────┐
│ Repo Analyzer │─────→│ File Processing │
└────────┬────────┘ └──────────────────┘
│
▼
┌─────────────────┐ ┌──────────────────┐
│ Text Splitter │─────→│ Chunk Content │
└────────┬────────┘ └──────────────────┘
│
▼
┌─────────────────┐ ┌──────────────────┐
│ Embedding Agent │─────→│ Jina Embeddings │
└────────┬────────┘ └──────────────────┘
│
▼
┌─────────────────┐ ┌──────────────────┐
│ Vector Store │─────→│ Qdrant Cloud │
└────────┬────────┘ └──────────────────┘
│
┌────┴────┬─────────┬──────────┐
▼ ▼ ▼ ▼
┌─────────┐┌──────┐┌──────┐┌─────────┐
│Metadata │Content│Review │QA Agent │
│Recomm. │Improver │ │
└─────────┘└──────┘└──────┘└─────────┘
│ │ │ │
└────┬────┴────┬────┴────┬───┘
▼ ▼ ▼
┌─────────────────────────────┐
│ Analysis Results JSON │
└─────────────────────────────┘
Analyze Repo
↓
Embed Repository Content
↓
Suggest Metadata
↓
Improve Content
↓
Review Results
↓
Complete
multiagent-repo-assistant/
├── agents/ # 7 specialized agents
│ ├── repo_analyzer.py # Repository structure analysis
│ ├── embedding_agent.py # Semantic embeddings
│ ├── metadata_recommender.py # Metadata suggestions
│ ├── content_improver.py # README enhancement
│ ├── reviewer.py # Content validation
│ ├── qa_agent.py # Question answering
│ └── __init__.py
├── tools/ # 5 utility tools
│ ├── file_loader.py # File extraction
│ ├── text_splitter.py # Text chunking
│ ├── code_analyzer.py # Code analysis
│ ├── web_search.py # Web search integration
│ ├── test_llm_embeddings.py # LLM testing
│ └── test_qdrant.py # Database testing
├── orchestrator/ # Workflow orchestration
│ ├── langgraph_flow.py # LangGraph pipeline
│ └── simple_pipeline.py # Alternative pipeline
├── config/ # Configuration
│ └── config.py # Service initialization
├── data/ # Sample data
│ └── sample_repo/ # Test repository
├── main.py # CLI entry point
├── requirements.txt # Python dependencies
├── .env # Environment variables
└── README.md # This file
qdrant-client - Vector DB clientcohere - LLM SDKrequests - HTTP clientpython-dotenv - Environment managementExtracts and analyzes repository structure, files, languages, and metadata.
Manages text embeddings using Jina API, stores vectors in Qdrant for semantic search.
Suggests project metadata, titles, and tags based on README content.
Enhances README using Cohere LLM with structured suggestions.
Validates improved content and identifies gaps (installation, usage, etc.).
Retrieves context from vector database and generates answers using LLM.
Coordinates communication between agents and external services.
Target Coverage: ≥70% overall
# Run all unit tests pytest tests/unit/ -v # Run with coverage report pytest tests/unit/ --cov=backend --cov=agents --cov-report=html # Run specific test file pytest tests/unit/test_agents.py -v
# Run integration tests pytest tests/integration/ -v # Run with external service mocking pytest tests/integration/ -v --mock-external
# Run E2E tests (requires services running) pytest tests/e2e/ -v # Run specific workflow test pytest tests/e2e/test_full_workflow.py::TestAuthenticationFlow -v
# Run entire test suite with coverage pytest tests/ -v --cov=backend --cov-report=html # Generate detailed coverage report coverage report -m
Tests are configured in pytest.ini with:
See Testing Strategy for detailed test architecture and best practices.
{ "title_alternatives": ["Repo Assistant", "Multi-Agent Analyzer"], "one_line_summary": "Intelligent repository analysis system", "tags": ["python", "multi-agent", "langchain", "ai"] }
{ "issues": [ "README lacks Installation section", "No usage examples provided" ], "evidence": [...] }
.env, never commit to repositorypython-dotenv for configurationQDRANT_URL # Qdrant Cloud instance URL QDRANT_API_KEY # Qdrant authentication QDRANT_COLLECTION # Collection name (default: repo_chunks) EMBEDDING_DIM # Vector dimension (default: 1024) COHERE_API_KEY # Cohere API key JINA_API_KEY # Jina API key JINA_EMBEDDING_MODEL # Model name (default: jina-embeddings-v3)
docker build -t multiagent-repo-assistant . docker run -e COHERE_API_KEY=xxx -e QDRANT_URL=xxx multiagent-repo-assistant
FastAPI-based REST API can be added for:
This project demonstrates core multi-agent concepts. Areas for enhancement:
This project is licensed under the MIT License - see the LICENSE file for details.
For full licensing terms, please refer to the LICENSE file.
Built with:
For issues, feature requests, or contributions, please refer to CONTRIBUTING.md or contact the development team.
This project is part of the AAIDC Module 3 program, demonstrating advanced multi-agent AI systems for practical software development use cases.