knolia-connect-server logo

knolia-connect-server

by Danejw

The Knolia Connect MCP server powers deep and context-aware matchmaking for users seeking meaningful relationships. It uses AI-powered vector matching to connect users with compatible companions for romantic and emotional relationships.

View on GitHub

Last updated: N/A

What is knolia-connect-server?

The Knolia Connect MCP server is a matchmaking service that connects users with compatible companions for romantic and emotional relationships. It leverages AI and vector embeddings to find meaningful connections based on user profiles.

How to use knolia-connect-server?

Users create a structured profile with their goals, personality, preferences, and values. This profile is then embedded as a vector and stored. The server uses cosine similarity to find matches between users based on their embedded profiles. The server provides endpoints to create, update, delete profiles and find matches.

Key features of knolia-connect-server

  • AI-powered vector matching

  • Semantic profile embedding

  • Fast similarity-based matching

  • User profile management

  • Integration with Knolia platform

Use cases of knolia-connect-server

  • Connecting users for romantic relationships

  • Facilitating emotional connections

  • Combating loneliness

  • Providing personalized matchmaking services

  • Finding companions with shared values

FAQ from knolia-connect-server

What is vector matching?

Vector matching uses mathematical representations of user profiles to find similarities and compatibility between users.

How does the server use AI?

The server uses OpenAI's model to embed user profile data into vectors, allowing for semantic understanding and more accurate matching.

What is Supabase with pgvector?

Supabase is a database platform, and pgvector is a Supabase extension that allows for efficient storage and querying of vector embeddings.

How are matches found?

Matches are found by calculating the cosine similarity between the requesting user's embedded profile and other users' profiles.

How do I run the server locally?

You can run the server locally using pip to install the requirements and then running the main python script. Alternatively, you can use Docker to build and run the server.