Ragfish Logo
Get In Touch
Ragfish Logo

Book a Demo

Store, Search, and Retrieve Knowledge at Scale

Vector databases are the foundation of modern Retrieval-Augmented Generation (RAG) applications. Ragfish integrates with dedicated Vector Store packages, allowing developers to choose the storage technology that best fits their performance, scalability, and deployment requirements.

Get In Touch
View GitHub
Explore Documentation

Why Vector Stores?

Large Language Models cannot remember your organization's documents, policies, product catalogs, or business knowledge on their own. To answer questions using your data, information must first be converted into vector embeddings and stored in a searchable database.

Dashboard Review Mockup

Vector stores make semantic search possible by finding information based on meaning rather than exact keyword matching.

Observability Mockup

This enables AI applications to retrieve the most relevant knowledge before generating a response.

Vector Store Architecture

Ragfish separates vector database implementations into dedicated packages.

Explore Vector stores

This architecture allows developers to change storage technologies without modifying the Core Framework.

Explore Architecture

Vector Store

Vector databases store embeddings and perform similarity searches.

Current Vector Store

Qdrant  Qdrant

Future Vector Stores

Chroma
Pinecone
Milvus
Weaviate
PostgreSQL pgvector
MongoDB Atlas Vector Search

One Framework, Multiple Vector Databases

Ragfish applications communicate with the Core Framework, not directly with a specific database.

This architecture allows every layer to evolve independently, making it easier to adopt new AI models, storage technologies, and data connectors without rewriting your application.

Explore Architecture

Why Separate Vector Stores?

Maintainability

Update or replace vector store packages independently of the Core Framework.

Extensible

Add new AI providers, vector stores, and connectors without modifying the Core Framework.

Flexibility

Choose the database that best matches your deployment strategy.

Scalability

Start small and scale to enterprise workloads without redesigning your application.

Enterprise Ready

Designed for production deployments with long-term scalability in mind.

Consistency

Develop against a unified interface while using different storage technologies.

Part of the Ragfish Ecosystem

Vector Stores work together with every other Ragfish package.

This architecture allows every layer to evolve independently, making it easier to adopt new AI models, storage technologies, and data connectors without rewriting your application.

Explore Architecture

Typical Knowledge Flow

Every user request follows a consistent execution flow.

Documents
Connector
Ingestion
Chunking
Embeddings
Vector Store
AI Response

Built for Extension

The Core Framework intentionally focuses only on orchestration. Additional functionality is delivered through official Ragfish packages.

Built for Enterprise AI

Whether you're deploying a private AI assistant or a large-scale enterprise knowledge platform, Ragfish allows you to choose the vector database that aligns with your operational requirements.

As new databases emerge, additional Vector Store packages can be added without changing the Core Framework or your application logic.

Continue Exploring

Vector Stores are one part of the Ragfish ecosystem.

Ready to Build with RAGfish?

Get In Touch Read Documentation

Next, discover how Connectors bring knowledge into your AI applications from spreadsheets, PDFs, databases, websites, documentation platforms, and other enterprise data sources.