Financial Document Q&A Assistant

• 📖Project Description
• 🧑‍💼Business Use Cases
• 📁Data Set Explanation
• 📊Project Evaluation Metrics
• 🚩How to Approach this Project

The Financial Document Q&A Assistant is a web application designed to process financial documents (PDF and Excel) and provide an interactive question-answering system using natural language. Users can query financial data such as revenue, expenses, profits, and other key metrics, and receive clear, contextual answers based on the uploaded documents.

The app is built with Streamlit for an intuitive web interface and uses Hugging Face Transformers for natural language processing.

• Automating financial data extraction from uploaded reports
• Empowering finance teams with quick insights from statements
• Assisting auditors and analysts in verifying financial metrics
• Enhancing productivity by enabling natural language interaction with financial documents

• 📂 Accepts PDF and Excel file uploads containing financial statements
• 🔎 Extracts text and numerical data from financial documents
• 📊 Supports Income Statements, Balance Sheets, Cash Flow Statements
• 💬 Provides conversational Q&A with follow-up support
• 📑 Extracts and presents specific financial metrics
• ⚡ Built with Streamlit + Transformers for performance and usability

• Frontend & UI: Streamlit
• NLP Engine: Hugging Face Transformers (instead of Ollama)
• Deployment: Local environment (no cloud dependency)
• Error Handling: Proper validation and user feedback

• Intuitive drag-and-drop upload for financial documents
• Interactive chat interface for asking questions
• Displays extracted metrics in a readable, structured format
• Provides clear processing feedback and results

1. Clone the repository:

   git clone https://github.com/your-username/financial-doc-qa.git
   cd financial-doc-qa

2. Install dependencies:

   pip install -r requirements.txt

3. Run the Streamlit app:

   streamlit run app.py

4. Upload your financial document (PDF/Excel) and start querying!

• Extraction Accuracy – Correctly parsed data from financial documents
• NLP Response Accuracy – Relevance and correctness of answers
• System Usability – User satisfaction and ease of interaction
• Performance – Speed of file processing and query handling