1. Project Overview

FastWiki

This project is a high-performance knowledge base system built on the latest technology stack, specifically designed for large-scale information retrieval and intelligent search. It leverages Microsoft's Semantic Kernel for deep learning and natural language processing, combined with .NET 8 and the MasaBlazor frontend framework, with MasaFramework powering the backend. Together, these technologies deliver an efficient, user-friendly, and extensible intelligent vector search platform. Our goal is to provide an intelligent search solution capable of understanding and processing complex queries, helping users quickly and accurately find the information they need.

2. Open Source License

Licensed under Apache-2.0

3. Screenshots

4. Feature Overview

Features

• Intelligent Search: Powered by Semantic Kernel's deep learning and natural language processing technologies, it understands complex queries and delivers accurate search results.

• High Performance: Uses PostgreSQL's vector extension to optimize vector search performance, ensuring fast responses even with large datasets.

• Modern Frontend: Uses the MasaBlazor frontend framework to provide responsive design and a user-friendly interface.

• Powerful Backend: Built on the latest .NET 8 and MasaFramework to ensure code efficiency and maintainability.

• Open Source and Community-Driven: Licensed under Apache-2.0, encouraging developers and enterprises to use and contribute to the project.

5. Tech Stack

Tech Stack

• Frontend Framework: MasaBlazor

• Backend Framework: MasaFramework based on .NET 8

• Vector Search Engine: Uses PostgreSQL's vector extension to optimize search performance.

• Deep Learning and NLP: Microsoft Semantic Kernel enhances semantic understanding of search queries.

• License: Apache-2.0, encouraging community contributions and usage.

Quick Start

Preconditions

Make sure you have installed the .NET 8 SDK and PostgreSQL database and configured the corresponding environment.

Installation

1. Clone the repository:

Visit Yifei Open Source: https://code.exmay.com/ Download

2. Install Dependencies:

Run the following command in the project root directory:

dotnet restore

3. Database Configuration:

Make sure your PostgreSQL database is running properly and that the required database has been created. Modify the database connection string in appsettings.json according to your configuration.

Run

Run the following command in the project root directory:

dotnet run

This will start the backend service. For the frontend, refer to the MasaBlazor documentation for the corresponding build and startup steps.

Default Username and Password: admin Aa123456

Environment Variable Parameters

FastWikiService Environment Variable Parameters:

• QUANTIZE_MAX_TASK: Maximum number of concurrent quantization tasks, defaults to 3

• OPENAI_CHAT_ENDPOINT: OpenAI API endpoint URL

• OPENAI_CHAT_EMBEDDING_ENDPOINT: Embedding API endpoint URL

• OPENAI_CHAT_TOKEN: OpenAI API Token

• OPENAI_CHAT_MODEL: Chat model, defaults to gpt-3.5-turbo

• OPENAI_EMBEDDING_MODEL: Embedding model, defaults to text-embedding-3-small

• OPENAI_EMBEDDING_TOKEN: Embedding Token, defaults to empty. If empty, the chat Token is used

FastWiki.Web.Server environment variables:

• FAST_WIKI_SERVICE: FastWikiService endpoint, defaults to [http://localhost:5124](http://localhost:5124)