AI Chatbot Hub
HomepageAPI docsDiscordLog inSign up
Documentation
Documentation
  • welcome
    • Quick start guide
    • Creating your first AI chatbot
  • Dashboard
    • Analytics
  • Account
    • Account settings
    • Get OpenAI API key
    • API docs
  • Inbox
    • Navigating the Inbox menu
  • Sources
    • Navigating the Sources menu
    • Best practices for preparing data
    • Adding training data
    • How to work with tables
  • AI agents
    • Creating AI agents
    • Fine-tune intents
    • Supervisor overrides
    • Function calling
    • Bias and stickiness
  • Customizations
    • Settings
      • Security
      • Conversations
      • Custom domains
      • Disclaimer
      • Human support escalation
    • User Data Management
      • File uploader
      • Conversation labeling
      • User data collection
      • Forms
      • Webhooks
      • User identity verification
    • Appearance & Style
      • General
      • Messages
      • Suggested prompts
      • Watermark
      • Button
  • Collaborators
    • Permissions
    • Transfer ownership
  • Preview
    • Overview
  • Go live
    • Integrations
  • Community
    • Partners
    • Affiliates
    • Discord
  • Resources
    • Get a free template
    • Enterprise
    • Glossary
    • Support
Powered by GitBook
On this page
  • Filtering and viewing data sources
  • Chunk curation
  • Citation reference
  • Auto chatbot re-train
  1. Sources

Navigating the Sources menu

Organize AI Chatbot Hub's data sources: search, filter by type or tag, manage columns, assign tags, and track storage and tokens.

PreviousNavigating the Inbox menuNextBest practices for preparing data

Last updated 3 months ago

Filtering and viewing data sources

You can perform multiple actions to organize and search for data:

  • Search sources

  • Select multiple records

  • Filter by type (table, text, image, video, web url...) and tag

  • Toggle on/off columns

  • Ordering columns asc/desc

  • Create and assign tags

  • Track storage size of each source

  • Track of each source

Each source is automatically assigned a title according to the AI. You can then modify these titles by clicking in the checkbox on the left from the source you want to update.

A panel will open on the right and you will see the following:

Let's break down the features from top to bottom:

Chunk curation

This feature is available on the Team and Pro plans.

Click on the first icon on the right to Source properties. It will open the chunk curation feature.

You can go through each section and see how the data is being indexed.

By clicking the Clean Up button the LLM will check for formatting issues, typos and general errors, polishing each chunk for better and more cost-efficient information retrieval.

Here is an example video of the chunk curation process:

Citation reference

When enabled, the AI will cite the selected source in its responses. If the feature is disabled, the AI will still use the source for information but will not display the citation.

You are able to control how source titles appear to users and customize source links for direct access to specific webpages or online resources.

Auto chatbot re-train

This feature is available on the Team and Pro plans.

Set the auto re-train frequency for the selected URL source. This will automatically re-train the source according to the frequency you set: weekly, biweekly, monthly.

chunk curation
chunk curation
tokens