File Search

Search and retrieve information from your folders to enrich workflows with organizational knowledge.

Knowledge Folders are now called Folders. Find them in the Library → Folders.

Overview

The File Search node queries your folders to retrieve relevant information and context. Connect your workflow to your organization's knowledge base - search through documents, files, and data stored in folders to enrich AI responses, validate information, or provide context for decisions.

Best for: Knowledge retrieval, document search, context enrichment, RAG (Retrieval Augmented Generation), and accessing organizational knowledge.

When to Use File Search

Perfect for:

• Searching company documentation and knowledge bases
• Retrieving relevant context for AI agent responses
• Finding specific information across multiple documents
• Implementing RAG (Retrieval Augmented Generation) patterns
• Validating information against internal knowledge
• Enriching workflows with organizational data

Not ideal for:

• Real-time web search (use Web Search node)
• Fetching data from external APIs (use HTTP Request node)
• Processing individual files (use direct file attachments)

Configuration

Folder

Select the folder to search from your workspace's available folders.

Options:

• Choose from connected folders
• Each folder contains your uploaded documents and files
• Folders support document files such as PDFs, Word docs, and text files. Spreadsheets and CSV files cannot be uploaded to Folders.

Search Query

The search query to find relevant information. Supports Manual, Auto, and Prompt AI modes.

Manual mode examples:

{{trigger.output.customer_question}}

Find information about {{trigger.output.product_name}} pricing and features

Prompt mode:

Generate a search query to find relevant information about the customer's question: {{trigger.output.question}}

Max Results

The maximum number of relevant results to return (default: 10)

Recommendations:

• 1-3 results: Focused, specific queries
• 5-10 results: Broader context needed
• 10+ results: Comprehensive searches (may impact performance)

How It Works

1. Query is processed against the selected folder
2. Semantic search finds the most relevant document chunks
3. Results are ranked by relevance score
4. Top N results are returned based on max results setting
5. Retrieved information is available to subsequent nodes

Example Use Cases

Customer Support with Knowledge Base

Form Trigger (Customer question)
→ File Search: Query folder with {{trigger.output.question}}
  Folder: "Support Documentation"
  Max Results: 5
→ Agent: Answer question using search results
  Context: {{file_search.output.results}}
  Question: {{trigger.output.question}}
→ Notification: Send answer to customer

Product Information Lookup

Integration Trigger (Slack question about product)
→ File Search: Search product knowledge
  Folder: "Product Information"
  Query: {{trigger.output.message}}
  Max Results: 3
→ Agent: Summarize relevant product details
→ Action: Reply in Slack thread

Document Validation

Form Trigger (User claim submission)
→ File Search: Find relevant policies
  Folder: "Company Policies"
  Query: "{{trigger.output.claim_type}} policy requirements"
  Max Results: 5
→ Agent: Validate claim against policies
  Policies: {{file_search.output.results}}
  Claim: {{trigger.output.claim_details}}
→ Condition: Approved or requires review?

Accessing Search Results

Access the retrieved information in subsequent nodes:

{{file_search.output.results}}
{{file_search.output.results[0].text}}
{{file_search.output.results[0].similarity}}
{{file_search.output.results[0].fileName}}

Result Structure

Each result contains:

• text: The relevant text chunk from the document
• similarity: Relevance score (0-1, higher is more relevant)
• fileName: Name of the source file
• fileUrl: URL to access the source file
• mimeType: MIME type of the source file
• subsource: Additional source reference
• subname: Additional name reference
• fileId: Unique identifier for the source file
• externalId: External reference ID from the connected source system
• fileSize: Size of the file in bytes
• connectionId: ID of the integration connection that provided the file
• syncParams: Sync parameters from the source integration
• pageCount: Number of pages in the file

Using in Agent prompts:

Context from knowledge base:
{{file_search.output.results}}

Based on the above context, answer this question:
{{trigger.output.question}}

Limitations

• Folder Scope: Only searches within the selected folder
• Result Quality: Depends on quality and completeness of uploaded documents
• Chunk Size: Large documents are split into chunks; relevant information might span multiple results
• Real-time Updates: Document changes require reprocessing before they appear in search results

Important: Ensure your folders are regularly updated with current information for accurate search results.

Best Practices

More specific queries return more relevant results. Include key terms, product names, or topics rather than generic searches.



Start with 5 results and adjust based on response quality. Too few might miss important context, too many can dilute relevance.



Organize folders by topic or domain for more targeted searches. Separate technical docs from marketing content.



File Search is most powerful when combined with Agent nodes. The agent can synthesize and interpret the retrieved information.



Test your file search with actual questions users might ask to ensure folder content is sufficient and queries return relevant results.



Add a condition after file search to handle cases where no relevant results are found. Provide fallback responses or escalation paths.

Next Steps

• Agent Node — Process and synthesize search results with AI

• Folders — Learn how to set up and manage folders

• Web Search — Search the internet for current information

• Condition Node — Route based on search result quality