ChatBees
  • 👋Welcome
  • Concepts
    • 📖Architecture
    • 📖Security
    • 📖Serverless RAG
    • 📖Namespace and Collection
    • 📖Access Control
    • 🚀Ticket AI Agent
  • Ticket AI Agent
    • Installation
  • WEB APP REFERENCES
    • 🔑Sign-in and Sign-out
    • ⛓️Manage Connectors
    • 🌏Manage Collections
      • 💿Data Sources
        • 📖Configure Periodic Import
      • ❓Chat with collection
      • ⏱️View Q/A history
      • 📖Publish a Collection
    • 🏛️Manage Users
    • 💰[Flex] Billing and Payment
    • 💰[Enterprise] Billing and Payment
    • 📈Account Usage
    • 🗝️API Keys
    • 🖥️Generated Code Sample
  • ChatBots
    • 🪄AI Chat for Confluence
    • 🪄ChatBees Slack Bot
    • 🪄ChatBees Website ChatBot
    • 🪄Pnyx Discord Bot
  • Snowflake Native App
  • API References
    • 📖API Key
    • 📖Collection Operations
      • 📖Create Collection
      • 📖Configure Collection
      • 📖List Collections
      • 📖Delete Collection
    • 📖Document Operations
      • 📖Upload Document
      • 📖Summarize Document
      • 📖Get Document Outlines and FAQs
      • 📖Ask
      • 📖Chat
      • 📖Search
      • 📖Personalize Response
      • 📖List Documents
      • 📖Delete Document
    • 📖Crawl Operations
      • 📖Create Crawl
      • 📖Get Crawl
      • 📖Index Crawl
      • 📖Delete Crawl
    • 📖Ingest Data Sources
      • 📖Create Ingestion
      • 📖Get Ingestion
      • 📖Index Ingestion
      • 📖Delete Ingestion
Powered by GitBook
On this page
  • Data Storage
  • Elastic Service
  1. Concepts

Architecture

PreviousWelcomeNextSecurity

Last updated 1 year ago

ChatBees is an advanced Retrieval Augmented Generation platform provided as a self-managed service. ChatBees enables data storage, processing, and retrieval solutions that are faster, easier to use, and far more flexible than traditional offerings.

ChatBees combines a completely new RAG engine with an innovative architecture natively designed for the cloud. ChatBees uses a central data repository, the cloud storage, for persisted data that is accessible from all compute nodes in the platform.

ChatBees unique architecture consists of two key layers:

Data Storage

When data is loaded into ChatBees, ChatBees parses the data, splits data into chunks, generates the embedding for each chunk, and persists all data into cloud storage. ChatBees reorganizes that data into its internal optimized and compressed format.

ChatBees manages all aspects of how this data is stored — the organization, compression, metadata, statistics, and other aspects of data storage are handled by ChatBees. The data objects are not directly visible nor accessible by customers; they are only accessible through provided APIs.

Elastic Service

The elastic service layer is a collection of services that coordinate activities. These services tie together all of the different components of ChatBees in order to process user requests. The cloud services layer runs on compute instances provisioned by ChatBees from the cloud provider.

Services managed in this layer include:

  • Authentication

  • Access control

  • RAG pipeline

  • Data and Vector Index

  • Security: encryption, secret key management

  • Private LLMs - in the future

📖
Data Storage
Elastic Service