Ragfish Logo
Get In Touch
Ragfish Logo

Book a Demo

Welcome

Welcome to the official documentation for Ragfish.

Ragfish is a TypeScript-first framework for building AI-powered applications using Retrieval-Augmented Generation (RAG). It provides a modular architecture that enables developers to connect Large Language Models (LLMs), vector databases, and enterprise knowledge sources through a consistent and easy-to-use API.

Whether you're building a document chatbot, an internal knowledge assistant, a customer support AI, or a custom enterprise application, Ragfish provides the core building blocks to simplify development while remaining flexible enough for production environments.

This documentation will guide you from installation to building complete AI assistants using the Ragfish framework.

What is Ragfish?

Ragfish is an extensible framework for building AI assistants that can understand and retrieve information from your organization's knowledge.

The framework provides modules for:

Each component is designed to work independently while integrating seamlessly with the rest of the framework.

  1. AI model integration

  2. Knowledge ingestion

  3. Text chunking

  4. Embedding generation

  5. Vector database integration

  6. Semantic retrieval

  7. Conversational AI

  8. Enterprise connectors

Each component is designed to work independently while integrating seamlessly with the rest of the framework.

Why Use Ragfish?

Building an AI application typically requires integrating several independent technologies, including language models, embedding providers, vector databases, and document processing libraries.

Ragfish brings these components together into a unified framework, allowing developers to focus on building applications instead of managing infrastructure.

Key benefits include:

    1. TypeScript-first developer experience

    2. Modular package architecture

    3. Multiple AI provider support

    4. Multiple vector database integrations

    5. Extensible connector ecosystem

    6. Enterprise-ready architecture

    7. Consistent APIs across the framework

What Can You Build?

Using Ragfish, you can build applications such as:

    1. Enterprise AI Assistants

    2. Knowledge Base Chatbots

    3. Product Documentation Assistants

    4. Customer Support Assistants

    5. HR Knowledge Portals

    6. Compliance Assistants

    7. AI-powered Search Applications

    8. Spreadsheet Intelligence Assistants

The same framework can be used for small proof-of-concept projects as well as large enterprise deployments.

Framework Overview

A typical Ragfish application follows the knowledge pipeline shown below.

Knowledge Sources
        │
        ▼
   Ingestion
        │
        ▼
    Chunking
        │
        ▼
   Embeddings
        │
        ▼
 Vector Store
        │
        ▼
   Retrieval
        │
        ▼
      Chat
        │

        ▼
   AI Assistant

Each stage is modular, allowing you to customize or replace components based on your application's requirements.

Before You Begin

To get started with Ragfish, you should have:

    1. Node.js 20 or later

    2. TypeScript 5.x

    3. npm or pnpm

    4. A basic understanding of JavaScript or TypeScript

    5. An API key for a supported AI provider (such as OpenAI) for the introductory examples

Next Steps

Now that you have an overview of Ragfish, continue to understand the framework's design principles, architecture, and how it simplifies the development of AI-powered applications