ETL Pipeline with AI-Chatbot for Stocks Data

• Tech Stack: Python, AWS S3, Postgres, LangChain, OpenAI API, Pandas, Matplotlib
• Github URL: Codebase

Real-Time ETL Pipeline: Designed a pipeline to fetch stock and cryptocurrency data from external APIs, transform it, and store it in AWS S3 and PostgreSQL, ensuring clean, structured, and up-to-date datasets.

Data Integration & Management: Implemented automated data cleaning, merging, and storage routines to handle large volumes of stock market data efficiently, enabling accurate downstream analytics.

GPT-Powered Chatbot Integration: Connected the ETL pipeline to a LangChain + Streamlit chatbot, allowing users to ask natural language questions about stock trends, prices, and volatility, with on-demand visualizations.

Future Enhancements: Planning to expand the chatbot to provide personalized investment insights, predictive analytics, and richer visualizations using historical and live stock data.