SmartQuery Agent is an intelligent natural language querying system powered by LangChain, Transformers, and a CSV-based data backend. It enables users to ask intuitive questions like "What is the price of the Acura Integra?" and get accurate responses from structured datasets like Cars93.csv.
- ✅ Ask natural language queries about cars (e.g., price, engine size, type)
- ✅ Powered by LangChain Agents and LLMs
- ✅ Integrates with CSV datasets (e.g., Cars93)
- ✅ Easily extendable to other datasets
- ✅ Handles fuzzy matching and relevant output formatting
Cars93.csv — A dataset containing specifications and features of 93 car models including:
Make,ModelPriceEngineSizeHorsepowerMPG.city,MPG.highway- ... and more!
| Tool | Description |
|---|---|
| 🧠 LangChain | For intelligent agent execution |
| 🤗 Transformers | For language model pipelines |
| 📊 Pandas | Data processing and CSV querying |
| 🐍 Python 3.10+ | Core programming language |
git clone https://github.com/your-username/smartquery-agent.git
cd smartquery-agentpip install -r requirements.txtjupyter notebook SmartQuery\ Agent.ipynbEnsure you have
Cars93.csvin the same directory as the notebook.
Input: What is the price of the Acura Integra?
Output: The price of Acura Integra is $15,580.00
📁 smartquery-agent/
│
├── 📘 SmartQuery Agent.ipynb # Main Jupyter Notebook
├── 📄 Cars93.csv # Dataset file
├── 📝 README.md # You are here!
├── 📦 requirements.txt # Dependencies
To add support for another dataset:
- Replace
Cars93.csvwith your file. - Update the search logic in
search_cars93()to match your schema. - Modify the
Toolregistration accordingly.
Suyash Prakash Kusumkar
💼 AI | ML | Full Stack | UI/UX
📫 LinkedIn | GitHub
If you found this project helpful, please ⭐️ star the repo to support the project and its growth!