🚀 Supercharged Vector Database!

Requirements  •  Installation  •  Using the Program  •  Request a Feature or Report a Bug  •  Contact

Create and search a vector database to get a response from the large language model that's more accurate. This is commonly referred to as "retrieval augmented generation" (RAG)! You can watch an introductory Video or read a Medium article about the program.

Graphic of How This Program Works

Requirements

🐍 Python 3.11 or Python 3.12  •  📁 Git  •  📁 Git LFS  •  🌐 Pandoc  •  🛠️ Compiler

The above link downloads Visual Studio as an example. Make sure to install the required SDKs, however.

EXAMPLE error when no compiler installed:

EXAMPLE of installing the correct SDKs:

Back to Top

Installation

Step 1

Download the ZIP file for the latest "release." Extract its contents and navigate to the src folder.

• NOTE: If you simply clone this repository you will get the development version, which might not be stable.

Step 2

Within the src folder, create a virtual environment:

python -m venv .

Step 3

Activate the virtual environment:

.\Scripts\activate

Step 4

Run the setup script:

Only Windows is supported for now.

python setup_windows.py

Back to Top

🖥️Usage🖥️

🔥Important🔥

• 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.

Start the Program

.\Scripts\activate

python gui.py

🏗️ Create a Vector Database

• Download an embedding model from the Models Tab.
• Set the chunk size and chunk overlap settings within the Settings Tab.
• Within the Create Database Tab, select the files that you want in the vector database.
  • 📄 Non-audio files (including 🖼️ images) can be selected by clicking the Choose Files button.
  • 🎵 Audio files must be transcribed first within the Tools Tab.
• Select the embedding model you want to use.
• Click Create Vector Database.

🔍 Query a Vector Database

• Select the database you want to search within the Query Database Tab.
• Select Local Models, Kobold, LM Studio or ChatGPT for the backend that you want to provide a response to your question.
• Click Submit Question.
  • The chunks only checkbox will display the results from the vector database without getting a response.

❓ Which Backend Should I Use?

If you use either the Kobold or LM Studio you must be familiar with those programs. For example, LM Studio must be running in "server mode" and handles the prompt formatting. However,Kobold automatically starts in server mode but requires you to specify the prompt formatting. For more information:

• Kobold home page, instructions, and Discord server
• LM Studio home page, instructions, and Discord server.

🗑️ Deleting a Database

• In the Manage Databases Tab, select a database and click Delete Database.

Back to Top

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).