Skip to main content

Overview

Content sources are the building blocks of a Knowledge Base. Each content source represents a collection of related information that has been ingested, processed, and indexed for semantic search.

Content source types

There are two types of content sources:

Manual

Files uploaded directly through the Knowledge Base admin interface

Workflow

JSON content ingested through workflow operations

Viewing content sources

Navigate to your Knowledge Base to see all content sources. The content sources list displays:
Content Sources List

Content source information

Each content source shows:
Type
string
  • Manual: Files uploaded in the Knowledge Base page
  • Workflow: Content ingested through workflow variables
Content Source
string
The unique name of the content source within the Knowledge Base
Status
string
Current processing state:
  • Uploading: Content is being uploaded
  • Chunking: Content is being processed into chunks
  • Available: Content is ready and can be queried
  • Failed: An error occurred during processing
Updated by
string
  • Username: For files uploaded in the Knowledge Base page
  • Workflow name: For content ingested through workflows
Updated at
timestamp
Timestamp of the last upload or workflow operation execution

Uploading documents

1

Navigate to Knowledge Base

Open your Knowledge Base in FlowX Designer
2

Click Upload Document

Click the Upload Document button in the Content Sources section
3

Select file

Choose a PDF file from your computer
4

Name the content source

Enter a unique name for the content source. By default, the file name (without extension) is used.
5

Upload

Click Upload to start the ingestion process
Upload Document

File requirements

Supported formats (current release):
  • PDF files only
File size:
  • Maximum file size: TBD
Future releases will support:
  • Images
  • PowerPoint presentations
  • Word documents
  • Excel spreadsheets

Content source naming

When uploading a document, you must provide a unique content source name:
Content source name rules:
  • Must be unique within the Knowledge Base
  • Default name is the file name without extension
  • Choose descriptive names for easy identification
  • Consider using versioning in names (e.g., β€œProduct Guide v2.1”)

Duplicate content sources

If you select a file with the same name as an existing content source, you’ll see a warning:
A Content Source with this name already exists. We recommend updating the existing content source instead.
Available options:
  • Append Content: Add the new document’s content to the existing content source
  • Replace Content: Replace the existing content with the new document
  • Cancel: Choose a different name or file

Managing content sources

Once content is uploaded and processed, you can perform the following operations:

Append content

Add new content to an existing content source without removing the existing chunks.
1

Select content source

Click on the content source you want to update
2

Choose Append Content

Select the Append Content operation
3

Upload new file

Select a new PDF file with additional content
4

Confirm

The new content will be processed and added to the existing chunks
Use case: Adding a new chapter to existing documentation or supplementing information without losing the original content.

Replace content

Replace all existing content in a content source with new content.
1

Select content source

Click on the content source you want to replace
2

Choose Replace Content

Select the Replace Content operation
3

Upload new file

Select a new PDF file that will replace the existing content
4

Confirm

All existing chunks will be deleted and new chunks will be created from the new content
Replace Content will permanently delete all existing chunks from the content source. This operation cannot be undone.
Use case: Updating documentation to a new version where the old content is no longer relevant.

Delete content source

Remove a content source and all its associated chunks from the Knowledge Base.
1

Select content source

Click on the content source you want to delete
2

Choose Delete

Select the Delete Content Source operation
3

Confirm deletion

Confirm that you want to permanently delete the content source
Deleting a content source will:
  • Remove all chunks generated from that content
  • Permanently delete the content from the Knowledge Base
  • This operation cannot be undone

Content source states

Content sources progress through different states during their lifecycle:

Uploading

The initial state when content is being uploaded to the Knowledge Base. What’s happening:
  • File is being transferred to the FlowX platform
  • Content is being validated
Duration: Usually a few seconds, depending on file size

Chunking

Content is being processed and split into smaller chunks for indexing. What’s happening:
  • Content is being extracted from the document
  • Text is being split into semantically meaningful chunks
  • Chunks are being embedded and indexed in the vector database
Duration: Can take from seconds to minutes depending on content size

Available

Content source is fully processed and ready to use. What you can do:
  • Query the content source in AI agents
  • View individual chunks
  • Append or replace content
  • Delete the content source

Failed

An error occurred during processing. What to do:
  1. Check the error message in the Content Source History modal
  2. Verify the file format and content
  3. Retry the operation
Failed State

Error handling

When processing fails, the content source will show a warning indicator.

Error states and recovery

Cause: File upload was interrupted or the file format is invalidSolution:
  • Verify the file format (must be PDF)
  • Check your network connection
  • Try uploading again
Cause: Error occurred while processing the contentSolution:
  • Check the Content Source History for specific error details
  • Verify the file is not corrupted
  • Contact support if the issue persists
When retrying a failed operation:
  • Any chunks already created will be deleted
  • The content will be processed entirely from the beginning
  • No duplicate chunks will be created

Warning indicators

When a content source has a failed update:
  • Yellow warning icon appears on the content source row
  • Tooltip message: β€œLast Content Source update failed. Check history.”
  • Dismiss trigger: The warning is automatically dismissed after a successful update

Viewing content source history

Content Source History is a low-priority feature that may be available in future releases.
Content Source History will show all operations performed on a content source:
OperationDescription
Upload DocumentCreates content source and inserts content
Append ContentAdds new content to existing chunks
Replace ContentDeletes existing content and inserts new content
Delete Content SourceRemoves the content source and all chunks
Each history entry will include:
  • Timestamp
  • User or workflow name
  • Operation type (Manual/Workflow/Test)
  • Operation performed
  • View option (for uploaded files or JSON payloads)

Working with chunks

Chunks are the individual pieces of content that AI agents query. To view and test chunks:
1

Navigate to Chunks tab

Click the Chunks tab in your Knowledge Base
2

Search chunks

Enter a query to search for relevant chunks
3

Filter results

Apply filters to refine the search results
4

Review chunks

Examine the returned chunks, their relevance scores, and metadata
Chunks View

Chunk information

Each chunk displays:
Relevance Score
percentage
How relevant the chunk is to your query (0-100%)
Content Source
string
The content source that generated this chunk (clickable link)
Submitted Content
link
Link to the original document or JSON payload that created this chunk
Chunk Content
text
The actual text content of the chunk
Chunk Metadata
object
System metadata associated with the chunk:
  • source: manual_upload or from_workflow
  • path: Document filepath or JSON payload
  • chunk_id: UUID from the vector database
  • knowledge_base: Knowledge Base ID

Searching chunks

Use the search interface to test how chunks will be retrieved by AI agents:
Query Prompt
string
Enter a natural language question or search query
Content Source
string
Filter by a specific content source. Default: All content sources
Max. Number of Results
number
Maximum number of chunks to return. Range: 1-10
Min. Relevance Score
percentage
Only return chunks with relevance score above this threshold. Range: 0-100%
Metadata
object
Filter chunks by metadata (exact match with AND logic)
Use chunk search to understand what information AI agents will receive for different queries. This helps you optimize your Knowledge Base content and structure.

Best practices

Content organization

Organize by topic or version:
  • Create separate content sources for different topics
  • Use versioning in content source names (e.g., β€œUser Guide v1.0”, β€œUser Guide v2.0”)
  • Group related documents in the same content source using Append Content

Content updates

Choose the right operation:
  • Use Append Content when adding supplementary information
  • Use Replace Content when updating to a new version
  • Test queries after updates to verify the changes work as expected

Error prevention

Avoid common errors:
  • Ensure PDF files are not corrupted before uploading
  • Use unique, descriptive names for content sources
  • Monitor the status of content sources during processing
  • Check Content Source History when errors occur

Next steps

Knowledge Base Overview

Understanding Knowledge Base capabilities