rshuang1537 / ai-documentqna

Simple LLM-enabled document Q&A app built using Langchain and Streamlit

Simple AI-Enabled Document Q&A App

An intuitive AI-powered tool to extract and interact with textual data from PDF documents. Utilizing Langchain, OpenAI's Large Language Models, and Streamlit, this app is capable of reading, processing, and answering queries based on the content of uploaded PDF documents.

Table of Contents

• Features
• Usage
• Privacy and Terms of Use
• Contributing
• Contact
• License

Features

• Upload multiple PDF documents.
• Extract and process text from PDF documents.
• Index and retrieve textual data efficiently.
• Conduct a conversational Q&A with the uploaded documents.
• Customize the AI's response generation behavior.
• Clear conversation history as needed.

Usage

1. Clone the repository to your local machine.
2. Navigate to the project directory.
3. Run the command streamlit run pdf_app.py to start the Streamlit app.
4. Open the provided URL in your web browser.
5. Follow the instructions within the app to upload PDF documents and interact with the conversational AI.

Privacy and Terms of Use

Detailed in the app under the section "⚠️ Privacy and Terms of Use".

Contributing

Feel free to open issues or provide pull requests to improve the app.

Contact

👨‍💻 Author: Yaksh Birla

• 🔗 LinkedIn
• 📧 Email
• ✍️ Medium

License

This project is a research preview intended for non-commercial use only, subject to the model License of OpenAI's GPT Large Language Models, HuggingFace embedding models, Terms of Use of the data generated by OpenAI and Privacy Practices of Langchain.