LangChain + Vanna AI (with Weather Tool)

A minimal proof-of-concept showing how to integrate Vanna AI — a natural language–to–SQL engine — into a LangChain 1.0 agent, alongside another tool (OpenWeather) to demonstrate multi-tool routing.

---

⚙️ Features

• 🧩 Vanna Tool — Streams answers from Vanna’s /chat_sse endpoint
• 🌤 Weather Tool — Uses OpenWeather API for real-time city forecasts
• 🧠 LangChain Agent — Automatically decides which tool to call
• 🔐 .env-based Config — No hard-coded API keys

---

🚀 Setup

To get started:

1. Clone the repository

   git clone https://github.com/vanna-ai/langchain.git
   cd langchain
   

2. Create and activate a virtual environment

   python3 -m venv venv
   source venv/bin/activate
   

3. Install dependencies

   pip install -r requirements.txt
   

4. Copy the example environment file and fill in your keys

   cp .env.example .env
   

5. Run the agent

   python main.py
   

---

💬 Example Queries

Who is the largest customer, what are total sales?
What's the weather in Paris?

---

🔑 Environment Variables (.env.example)

OPENAI_API_KEY=your_openai_key
VANNA_API_KEY=your_vanna_key
VANNA_AGENT_ID=look-service-account
VANNA_USER_EMAIL=your_email_here
OPENWEATHER_KEY=your_openweather_key

---

📁 Repository Structure

.
├── main.py
├── requirements.txt
├── test_vanna_api.py
├── .env.example
├── .gitignore
└── README.md

---

👨‍💻 Author

Vanna AI
Description: Simple LangChain 1.0 agent integrating Vanna and external APIs.
🌐 https://vanna.ai

---

🧠 About Vanna

Vanna AI is a conversational analytics engine that connects to your databases and lets you ask business questions in natural language — returning SQL, charts, or dataframes as responses.

---