Introduction

FloTorch allows you to retrive information from your existing Vector Storage (Vector Databases). With Knowledgebase, configured with FloTorch, you can search your Vector Database using OpenAI Compatible API. These Knowledgebases can be used to retrive information from your Vector Database using natural language queries.

RAG Entpoints use this Knowledgebase to retrive information from your Vector Database.

Supported Vector Databases

FloTorch currently supports the following Vector Databases:

• AWS Bedrock - AWS Bedrock is a fully managed service that allows you to build, train, and deploy custom language models.
• OpenAI - OpenAI provides powerful language models and embeddings through their API, enabling advanced natural language processing and semantic search capabilities.
• ChromaDB - ChromaDB is an open-source vector database designed for storing and retrieving embeddings, making it ideal for semantic search and AI applications.
• PineconeDB - PineconeDB is a managed vector database service that provides fast, scalable similarity search capabilities for machine learning applications.
• LanceDB - LanceDB is a modern vector database built for AI applications, offering high-performance vector search with support for multiple data formats and cloud-native deployment.

Other Vector Databases are planned to be supported in the future.