- Notifications
You must be signed in to change notification settings - Fork9
Create a ChatGPT for uploaded pdf using Langchain
License
ayushwattal/PDF-ChatGpt
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
The PDF Chatbot is an application that allows users to upload PDF files and interact with pdf using a chatbot. Users can ask questions or provide input, and the chatbot will generate responses based on the provided information.
- Langchain
- Gradio
- OpenAI API
- ChromaDB
- Chat with a chatbot: Ask questions or have a conversation with the chatbot.
- Upload PDF files: Preview PDF files by uploading them to the application.
- Update API Key: Easily update the OpenAI API key used by the chatbot.
Clone the repository:
git clone https://github.com/ayushwattal/PDF-ChatGpt.git
Install the required dependencies:
pip install -r requirements.txt
Run the application:
python app.py
Access the application in your web browser as specified in the console.
Enter your OpenAI API key in the provided input box and press enter.
To preview a PDF file, click the "Upload PDF" button and select the PDF file from your local machine. The application will display a preview of the PDF file.
Use the chatbox to ask questions or have a conversation with the chatbot. The chatbot will generate responses based on the input.
- The application uses the OpenAI API for generating chatbot responses. Make sure to provide a valid OpenAI API key.
Contributions are welcome! If you encounter any issues or have suggestions for improvements, please feel free to open an issue or submit a pull request.
This project is licensed under theApache License 2.0.
This application was developed usinghttps://www.analyticsvidhya.com/blog/2023/05/build-a-chatgpt-for-pdfs-with-langchain/
About
Create a ChatGPT for uploaded pdf using Langchain
Topics
Resources
License
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Releases
Packages0
Uh oh!
There was an error while loading.Please reload this page.