Create a QnA chatbot on your documents without relying on the internet by utilizing the capabilities of local LLMs. Ensure complete privacy and security as none of your data ever leaves your local execution environment. Seamlessly process and inquire about your documents even without an internet connection. Inspired from SamurAIGPT
Code is up, โญ (Star) the repo meanwhile to receive updates
Follow Akhil on twitter for updates
- Python 3.8 or later
- NodeJS v18.12.1 or later (nvm install 18.12.1 to upgrade)
- Minimum 16GB of memory
-
Go to client folder and run the below commands
npm install
npm run dev
-
Copy the example.env template into .env
cp example.env .env
-
Go to server folder and run the below commands (feel free to use virtual env)
pip install -r requirements.txt # for some it might be pip3 instead of pip
python privateLLAMA.py # for some it might be python3 instead of python
-
Open http://localhost:3000, click on download model to download the required model initially
-
Upload any document of your choice and click on Ingest data. Ingestion is fast
-
Now run any query on your data. Data querying is slow and thus wait for sometime
-
IMPORTANT: If there are errors in model processing download the model manually from here and replace the file in folder /models
Reach out Akhil on twitter to get support
The supported extensions for documents are:
- .csv: CSV,
- .docx: Word Document,
- .enex: EverNote,
- .eml: Email,
- .epub: EPub,
- .html: HTML File,
- .md: Markdown,
- .msg: Outlook Message,
- .odt: Open Document Text,
- .pdf: Portable Document Format (PDF),
- .pptx : PowerPoint Document,
- .txt: Text file (UTF-8),