Integrations, connectors & knowledge — found from sitemap — Dust

Cited by

Facts read from this source

• Rag search Report an error

  “With Dust, you can ask your agents to search through your entire selected Data Sources and pick the most relevant documents to tap into to answer. Dust provides RAG capabilities and agents are able to search your data semantically before sending your message to the chosen model”

• Datasource prereq Report an error

  “To be able to use this, you need to have created some Datasources first - Connections, Folders and/or websites.”

• Subpage selection Report an error

  “you can even pick sub-pages or specific channels”

• Label filtering Report an error

  “After selecting your data sources, you can apply additional filtering using labels to refine what content is available to your agent”

• Label filter modes Report an error

  “Exclude specific content : Filter out pages with certain labels (e.g., “deprecated”). Include specific content : Only include pages with specific labels (e.g., from a particular author). In-conversation filtering : Enable dynamic filtering based on conversation context.”

• In conversation filter exact match Report an error

  “This requires exact tag matching.”

• Label support scope Report an error

  “Labels are supported on Folders and on most of our Connections”

• Label filter reset warning Report an error

  “If you remove and re-add a knowledge configuration to pick up new capabilities (as described below for SharePoint), you will lose its existing must-have / must-not-have label filters.”

• Filesystem navigation Report an error

  “Agents can also browse your data sources like a file system, on top of semantic search. They can list folders, browse through directory structures, and open specific files by their exact path.”

• Sharepoint default nav Report an error

  “For SharePoint through Content search, folder and path navigation is turned on by default for new knowledge configurations.”

• Supported sync sources Report an error

  “This method is particularly useful in scenarios where the data might be coming from data sources that you have synced with Dust: Google drive, Confluence, Notion, Slack, etc.”

• Retrieval response links Report an error

  “The model will will generate a response to the user’s question, taking into account the results from the data source and giving the links to the right sources.”

• Dust agent all sources Report an error

  “you can already query all of your data sources using the @dust agent if your workspace is configured with it”

• Granularity recommendation Report an error

  “agents that are plugged to a constrained number of data will usually perform better than the ones with access to everything.”

Scores citing this record

• The Automation Lead Integrations, connectors & knowledge
• The Automation Lead Integrations, connectors & knowledge
• The Customer-Service Director Integrations, connectors & knowledge
• The Customer-Service Director Integrations, connectors & knowledge
• The Data Protection Officer Integrations, connectors & knowledge
• The Data Protection Officer Integrations, connectors & knowledge
• The Head of IT Admin, identity & access controls
• The Head of IT Integrations, connectors & knowledge
• The Head of IT Integrations, connectors & knowledge
• The Skeptic Integrations, connectors & knowledge
• The Skeptic Integrations, connectors & knowledge
• The Works Council Member Integrations, connectors & knowledge
• The Works Council Member Integrations, connectors & knowledge