https://github.com/raffcodes/ask_pdf
Simple app where you can ask question to your imported PDFs. Chain: PDF->text->chuncks->embeddings->semantic search->question and relevant text chunks are sent to an LLM->answer.
https://github.com/raffcodes/ask_pdf
chatopenai langchain llm openai-api pypdf2 python streamlit
Last synced: 2 months ago
JSON representation
Simple app where you can ask question to your imported PDFs. Chain: PDF->text->chuncks->embeddings->semantic search->question and relevant text chunks are sent to an LLM->answer.
- Host: GitHub
- URL: https://github.com/raffcodes/ask_pdf
- Owner: raffcodes
- Created: 2024-10-24T19:03:54.000Z (over 1 year ago)
- Default Branch: master
- Last Pushed: 2024-10-24T20:08:46.000Z (over 1 year ago)
- Last Synced: 2025-06-14T06:37:42.267Z (about 1 year ago)
- Topics: chatopenai, langchain, llm, openai-api, pypdf2, python, streamlit
- Language: Python
- Homepage:
- Size: 4.88 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
To run it on you machine, you need following steps:
1. Create an OpenAI API Key and save it to your environment variable as OPENAI_API_KEY = ""
2. Create an environment variable with your choosen login credentials, ASK_PDF_CREDENTIALS=":".
On windows, open cmd as an admin and type: setx ASK_PDF_CREDENTIALS ":".
Restart the machine and check on cmd with echo %ASK_PDF_CREDENTIALS%
3. Create a new virtual environment for this project and activate it
4. pip install -r requirements.txt
5. To run the app: streamlit run app.py (not: python app.py)