https://github.com/aritrakar/pdf-gpt
📝Upload and chat with your PDFs!
https://github.com/aritrakar/pdf-gpt
langchain openai-api python streamlit
Last synced: 2 months ago
JSON representation
📝Upload and chat with your PDFs!
- Host: GitHub
- URL: https://github.com/aritrakar/pdf-gpt
- Owner: aritrakar
- Created: 2023-06-07T13:21:19.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2023-06-07T13:35:13.000Z (about 3 years ago)
- Last Synced: 2025-10-19T16:01:24.308Z (8 months ago)
- Topics: langchain, openai-api, python, streamlit
- Language: Python
- Homepage:
- Size: 1000 Bytes
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# PDF-GPT
This is a simple application which allows you to upload your PDFs and then "chat" with them, as one does with ChatGPT. Experimenting with LangChain.
**Made with:**
- LangChain (Text splitting, generating embeddings, FAISS, Q&A chain)
- OpenAI's davinci-003 LLM (For "chatting")
- Streamlit (Web UI)
- PyPDF2 (For parsing the PDFs)
**NOTE:**
1. I tested with a paid organization account.
2. Each query costs some small amount, dependeing on the query complexity. It's usually between 2-5 cents.
# How to run locally
1. Clone the repository.
2. Install dependencies: `pip install -r requirements.txt`
3. Add a `.env` file with your `OPENAI_API_KEY`. **Do not rename this environment variable, otherwise LangChain will not work.**
4. Run the Streamlit application: `streamlit run main.py`