Home
Softono
VectorDB-Plugin

VectorDB-Plugin

Open source Python
368
Stars
47
Forks
11
Issues
7
Watchers
1 week
Last Commit

About VectorDB-Plugin

Program that lets you ask questions about your documents, audio, and video files.

Platforms

Web Self-hosted

Languages

Python
splash

Create and search a vector database from a wide variety of file types and get more reliable responses from an LLM. This is commonly referred to as "retrieval augmented generation."

Requirements

Tool Purpose
πŸͺŸ Microsoft Windows Only for Windows but open to pull requests
🐍 Python 3.11–3.13 Run the application
🌿 Git Clone / manage the repository
🧲 Git LFS Handle large model files
πŸ“„ Pandoc Document parsing support
πŸ› οΈ Visual C++ Build Tools Required for compiling dependencies
Or you can try running these commands in Powershell on Windows:

Install:

winget install Microsoft.VisualStudio.2022.BuildTools --silent --accept-source-agreements --accept-package-agreements --override "--wait --quiet --add Microsoft.VisualStudio.Component.VC.Tools.x86.x64 --add Microsoft.VisualStudio.Component.Windows11SDK.22621"

Verify installation:

Test-Path "C:\Program Files\Microsoft Visual Studio\2022\BuildTools\VC\Tools\MSVC"

Installation

Download the latest "release," extract, navigate to the src folder, and run the following commands:

python -m venv .
.\Scripts\activate
python setup_windows.py
python gui.py

Inputs β†’ Processing β†’ Vector Database

πŸ“‚ Ingest πŸ“„ .pdf, .docx, .txt, .html, .htm, .md, .csv, .xls, .xlsx, .xlsm, .rtf, .eml, .msg
πŸ–ΌοΈ .png, .jpg, .jpeg, .bmp, .gif, .tif, .tiff
🎡 .mp3, .wav, .m4a, .ogg, .wma, .flac
βš™οΈ Process πŸ“ Extract text from documents
πŸ–ΌοΈ Generate descriptions from images
🎧 Transcribe speech from audio
🧠 Store All processed content is embedded and saved into the vector database for searching.

Query β†’ LLM β†’ Output

❓ Ask ⌨️ Type or πŸŽ™οΈ record a question
🧠 Retrieve Relevant chunks are pulled from the vector database
πŸ€– Generate Sent to an LLM (Local Model, Kobold, LM Studio, or ChatGPT)
πŸ’¬ Respond LLM returns an answer based on the context you provided
πŸ”Š Optional Text-to-speech can read the response aloud

Usage

[!NOTE] Instructions on how to use the program are being consolidated into the Ask Jeeves functionality, which can be accessed from the "Ask Jeeves" menu option. Please create an issue if Jeeves is not working.

Request a Feature or Report a Bug

Feel free to report bugs or request enhancements by creating an issue on github and I will respond promptly.

Contact

I welcome all suggestions - both positive and negative. You can e-mail me directly at "[email protected]" or I can frequently be seen on the KoboldAI Discord server (moniker is vic49). I am always happy to answer any quesitons or discuss anything vector database related! (no formal affiliation with KoboldAI).