đ¸ This project is based on GPT3.5-turbo and can answer user's questions based on the PDF text files provided by the user.
English | ä¸æįŽäŊ
This project is based on GPT3.5-turbo
and can answer user's questions based on the PDF text files provided by the user.
Here is a simple example:
.
âââ .env.example # Example environment variables file
âââ .gitignore # Git ignore rules file
âââ example_history.json # JSON file containing example history
âââ LICENSE # License file
âââ main.py # Main Python script
âââ README.md # Readme file in English
âââ README.zh-CN.md # Readme file in Simplified Chinese
âââ requirements.txt # File listing required dependencies
âââ setup.sh # Shell script for setup
âââ utils.py # Utility Python script
âââ pdf_files # Directory containing PDF files
âââ bert.pdf # PDF file named bert
âââ transformer.pdf # PDF file named transformer
text-embedding-ada-002
.distances_from_embeddings
, and return a list of the most similar texts.GPT3.5-turbo
to generate answers based on the most similar text list.[email protected]:Duguce/Mini-ChatPDF.git && cd Mini-ChatPDF
./setup.sh
Obtain a GPT API key from OpenAI and copy it to the corresponding location in the .env
file.
Add the PDF documents you want to use in the ./pdf_files/
directory.
source .venv/bin/activate
You should see (.venv) ~/Mini-ChatPDF$
when you run the script. If not, please first run source .venv/bin/activate
python main.py
Support reading multiple PDF documents simultaneously.
Support other text encoding vector methods.
Add functionality to save text encoding vectors.
Implement a graphical user interface (GUI).
Optimize the prompt
.
This project is licensed under the MIT License.