👨‍⚖️ AI Legal Agent Team

A beautiful, friendly app that reads your legal PDFs and lets a team of smart AI helpers analyze them for you.

🚀 Quick Start • 🛠️ Detailed Setup • 🧯 Help

A Streamlit application that simulates a full-service legal team using multiple AI agents to analyze legal documents and provide comprehensive legal insights. Each agent represents a different legal specialist role, from research and contract analysis to strategic planning, working together to provide thorough legal analysis and recommendations.

🗂️ Table of Contents

Features
How to Run
🚀 Super-Simple Setup (So easy a 5‑year‑old can follow!)
🎯 What this app does
🧪 Supported Models & Services
🛠️ Detailed Setup (Grown‑ups)
🧭 How it works
🧯 Troubleshooting
❓ FAQ
🌟 Make it yours
📸 Pretty Buttons

Features

Specialized Legal AI Agent Team
- Legal Researcher: Equipped with DuckDuckGo search tool to find and cite relevant legal cases and precedents. Provides detailed research summaries with sources and references specific sections from uploaded documents.
- Contract Analyst: Specializes in thorough contract review, identifying key terms, obligations, and potential issues. References specific clauses from documents for detailed analysis.
- Legal Strategist: Focuses on developing comprehensive legal strategies, providing actionable recommendations while considering both risks and opportunities.
- Team Lead: Coordinates analysis between team members, ensures comprehensive responses, properly sourced recommendations, and references to specific document parts. Acts as an Agent Team coordinator for all three agents.
Document Analysis Types
- Contract Review - Done by Contract Analyst
- Legal Research - Done by Legal Researcher
- Risk Assessment - Done by Legal Strategist, Contract Analyst
- Compliance Check - Done by Legal Strategist, Legal Researcher, Contract Analyst
- Custom Queries - Done by Agent Team - Legal Researcher, Legal Strategist, Contract Analyst

How to Run

Setup Environment

bash# Clone the repository
git clone "repo link"
cd advanced_ai_agents/multi_agent_apps/agent_teams/ai_legal_agent_team

# Install dependencies
pip install -r requirements.txt

Configure API Keys
- Get OpenAI API key from OpenAI Platform
- Get Qdrant API key and URL from Qdrant Cloud

Run the Application

bashstreamlit run legal_agent_team.py

Use the Interface
- Enter API credentials
- Upload a legal document (PDF)
- Select analysis type
- Add custom queries if needed
- View analysis results

🚀 Super-Simple Setup (So easy a 5‑year‑old can follow!)

🧰 What you need
- A computer with internet
- Python 3.10+
- An OpenAI key and a Qdrant account (don’t worry, steps below!)
🎁 Get the tools

📦 Install

bashpip install -r requirements.txt

🔐 Put your secrets in a magic box (.env) Create a file named .env in the project folder and add:

iniOPENAI_API_KEY=your_openai_api_key_here
QDRANT_URL=https://YOUR-CLUSTER-URL.qdrant.io
QDRANT_API_KEY=your_qdrant_api_key_here

▶️ Run the app

bashstreamlit run legal_agent_team.py

🖱️ Click & Go
- Paste keys if not auto-filled
- Upload a PDF
- Pick an analysis
- Press Analyze → ✨ Magic!

🎯 What this app does (Like story time!)

📄 You give it a PDF (a contract or legal doc)
🧠 The app reads it and remembers the important bits
🤖 Three helpful AI friends look at it:
- 🕵️ Legal Researcher: finds references and cases
- 🧾 Contract Analyst: spots key terms and issues
- 🧭 Legal Strategist: gives smart next steps
🧩 A Team Lead combines all answers into one helpful result

🧪 Supported Models & Services

🔊 Chat model: gpt-4o (via OpenAI)
🧩 Embeddings: text-embedding-3-small (via OpenAI)
🧠 Vector database: Qdrant Cloud
🔎 Web search: DuckDuckGo (no key needed)

Tip: Using a local stack? See local_ai_legal_agent_team/local_legal_agent.py (Ollama + local Qdrant).

🛠️ Detailed Setup (Grown‑ups section)

Create accounts/keys

OpenAI → create a project and API key
Qdrant Cloud → create a cluster, copy HTTPS URL + API key

Configure .env

Put OPENAI_API_KEY, QDRANT_URL, QDRANT_API_KEY
The app auto-loads them on start via python-dotenv

Install Python deps

bashpip install -r requirements.txt

Launch

bashstreamlit run legal_agent_team.py

🧭 How it works (Under the hood)

You upload a PDF → it’s turned into chunks
📚 Chunks get embeddings (OpenAI) → stored in Qdrant
🔎 When you ask, agents search the knowledge base
🧩 Team Lead merges answers → you get a clean report

🗃️ Repository Structure

textai_legal_agent_team/
├─ legal_agent_team.py                 # Main Streamlit app (OpenAI + Qdrant Cloud)
├─ local_ai_legal_agent_team/
│  ├─ local_legal_agent.py            # Local app (Ollama + local Qdrant)
│  └─ requirements.txt
├─ requirements.txt                    # Python dependencies
├─ README.md                           # You are here 📘
└─ .gitignore                          # Keeps secrets and junk out of git

🧰 Advanced: Local (No OpenAI) Setup

Run fully local with Ollama + local Qdrant (click to expand)

Install and start Qdrant locally (Docker)

bashdocker run -p 6333:6333 -p 6334:6334 qdrant/qdrant

Install Ollama and pull models

bashhttps://ollama.com/download
ollama pull llama3.1:8b
ollama pull openhermes

Install deps for local app and run

bashpip install -r local_ai_legal_agent_team/requirements.txt
streamlit run local_ai_legal_agent_team/local_legal_agent.py

🧯 Troubleshooting

“ddgs not installed” → run: pip install -r requirements.txt
“Failed to connect to Qdrant” → check QDRANT_URL & QDRANT_API_KEY
“OpenAI key invalid” → verify billing and key value in .env
Blank results → ensure your PDF has selectable text (not just images)

❓ FAQ

Can I use it without OpenAI?
- Yes, try the local app in local_ai_legal_agent_team/ (Ollama + local Qdrant)
What files are supported?
- PDFs for now
Is there a cost?
- OpenAI and Qdrant usage may incur costs

🌟 Make it yours

Change model: edit OpenAIChat(id="gpt-4o")
Change embedding: edit text-embedding-3-small
Add new agents or tools using agno

❤️ Credits

Built with Streamlit, Agno, OpenAI, Qdrant, DuckDuckGo

🤝 Contributing

Fork this repo
Create a feature branch: git checkout -b feat/amazing-idea
Commit changes: git commit -m "feat: add amazing idea"
Push: git push origin feat/amazing-idea
Open a Pull Request 🚀

📜 License

This project is open-source. Add your preferred license in a LICENSE file.

⭐ Star this repo

If this helped you, please star the repo — it motivates continued improvements!

Multi-Agent Legal Squad — AI Agent for legal PDF clause risk triage