Skip to main content

​
Overview

Knowledge Bases can be integrated into workflows to enable AI agents and Context Retrieval nodes to query them for contextual information when generating responses.
Not available in v5.4: Workflow-based content ingestion (adding, updating, or deleting Knowledge Base content from workflows) is planned for a future release. Currently, you can only upload content manually through the Knowledge Base interface.

​
Choosing the right approach

There are two ways to query Knowledge Bases in workflows:
ApproachNodeWhen to use
Integrated RAGCustom AgentYou want the AI to retrieve chunks and generate a response in a single step
Standalone retrievalContext RetrievalYou want raw chunks returned without LLM processing, so you can filter, transform, or route them before generation

​
Using knowledge bases in custom agent nodes

Custom Agent nodes can query Knowledge Bases to retrieve contextual information when generating responses.

​
Configuring custom agent with knowledge base

1

Add Custom Agent node

Add a Custom Agent node to your workflow
2

Configure the agent

Set up the basic agent configuration (operation prompt, etc.)
3

Enable Knowledge Base

In the Knowledge Base section, enable the Knowledge Base feature
4

Select Knowledge Base

Choose a Knowledge Base from the available options
5

Configure query parameters

Set the query parameters for retrieving chunks
Custom Agent with KB

​
Knowledge base query configuration

​
Knowledge Base
select
required
Select the Knowledge Base that the agent should query
​
Content Source Filter
select
Options:
  • All content sources (default)
  • Specific content source(s)
Filter which content sources the agent should search
​
Max. Number of Results
number
Maximum number of chunks to retrieve (1-10). Default: 5
​
Min. Relevance Score
percentage
Minimum relevance score threshold (0-100%). Only chunks above this score will be included. Default: 70%
​
Metadata Filters
object
Filter retrieved chunks based on their metadata properties. Click the Metadata Filters button to open a modal where you can define structured filter conditions.Each filter is a key-value pair:
  • Select a metadata property key from the dropdown (e.g., source)
  • Set the value to match based on the key’s type (string, number, boolean, enum, or date)
  • Multiple filters are combined with AND logic
The button label shows how many filters are currently active (e.g., “3 Filters Applied” or “No Filters Applied”).
​
Use advance metadata filters
boolean
Toggle ON to enable advanced metadata filter expressions for more complex filtering logic. When turned on, you can write expression-based filters instead of using the structured filter UI.Default: false

​
Using knowledge bases in context retrieval nodes

Available starting with FlowX.AI 5.6.0
Context Retrieval nodes retrieve relevant data from Knowledge Bases or conversation memory using semantic, keyword, or hybrid search. Unlike Custom Agent nodes, Context Retrieval nodes are dedicated to chunk retrieval without agent reasoning — they are available under Data Operations in the workflow node palette.

​
Configuring context retrieval with knowledge base

1

Add Context Retrieval node

Add a Context Retrieval node from the Data Operations category in the workflow editor
2

Select a source

Choose between Knowledge Base or Memory (Memory is only available in conversational workflows)
3

Select Knowledge Base

If using Knowledge Base as the source, select a Knowledge Base from the available options
4

Define the user query

Enter the search query, typically a process variable expression (e.g., ${userMessage})
5

Configure settings

Expand Settings to configure search type, max chunks, min relevance, metadata filters, and re-ranking

​
Context retrieval configuration

​
Source
select
required
The data source to retrieve context from.Options:
  • Knowledge Base — search a connected Knowledge Base
  • Memory — search conversation memory (conversational workflows only)
​
Knowledge Base
select
Select the Knowledge Base to query. Only visible when Source is set to Knowledge Base.
​
User Query
string
required
The search query used to retrieve relevant chunks. Supports process variable expressions.Example: ${userMessage}
​
Search Type
select
The strategy used for retrieving context.Options:
  • Hybrid (default) — combines semantic and keyword search
  • Semantic — vector-based similarity search
  • Keywords — traditional keyword matching
​
Max Number of Chunks
number
How many relevant chunks to return (1-10).Default: 5
​
Min Relevance Score
percentage
The threshold a chunk must meet to be included in results (0-100%). Only visible when search type is Hybrid or Semantic.Default: 70%
​
Metadata Filters
object
Refine results by filtering chunks based on their metadata properties. Click the button to open a modal where you can define structured filter conditions.Each filter is a key-value pair:
  • Select a metadata property key from the dropdown
  • Set the value to match based on the key’s type
  • Multiple filters are combined with AND logic
The button label shows how many filters are currently active.
​
Use advance metadata filters
boolean
Toggle ON to enable advanced metadata filter expressions for more complex filtering logic.Default: false
​
Use Re-rank
boolean
Toggle ON to re-rank retrieved chunks before they are returned, improving result quality.Default: false

​
How the agent uses knowledge base

When a Custom Agent node executes with Knowledge Base enabled:
  1. Query generation: The agent analyzes the user’s input and generates a search query
  2. Chunk retrieval: The Knowledge Base is queried using semantic search
  3. Relevance filtering: Only chunks meeting the minimum relevance score are returned
  4. Context inclusion: Retrieved chunks are added to the agent’s context
  5. Response generation: The agent generates a response using the retrieved information

​
ReAct model with knowledge base

When using the ReAct (Reasoning and Acting) model, the agent can:
  • Reason: Determine if Knowledge Base information is needed
  • Act: Query the Knowledge Base as a tool
  • Iterate: Make multiple queries if needed for comprehensive answers
Example ReAct flow: 
User: "What are the new features in version 2.5?"

Agent Reasoning: I need to search the Knowledge Base for version 2.5 information

Agent Action: Query Knowledge Base with "new features version 2.5"

Knowledge Base: Returns 3 relevant chunks about version 2.5 features

Agent Reasoning: I have enough information to answer the question

Agent Response: "Version 2.5 introduces three major features..."

​
Viewing Knowledge Base results

Available starting with FlowX.AI 5.6.0
When a Custom Agent node queries a Knowledge Base during a workflow run, you can inspect the retrieved chunks directly in the workflow run console.

​
Knowledge Base tab

A Knowledge Base tab appears in the node console (alongside Logs, Input, Output, and Tools) when a node has KB results. For each Knowledge Base queried, the tab displays:
FieldDescription
Knowledge Base nameThe name of the queried KB (links to the KB data source configuration)
Number of ResultsThe topK value used for the query
Min. Relevance ScoreThe minimum relevance threshold (as a percentage)
ChunksExpandable list of retrieved chunks
Each chunk entry shows:
  • Relevance score — how closely the chunk matches the query (percentage)
  • Content Source — the name of the content source the chunk belongs to
  • Chunk content — the actual text (expandable, collapsed to 6 lines by default)
  • Submitted Content — button to view the full chunk content in an overlay panel
  • Metadata — any metadata associated with the chunk (if present)
Use the Knowledge Base tab to debug retrieval quality. If the agent returns inaccurate answers, check whether the retrieved chunks contain the expected information and whether relevance scores are appropriate.
KB results also appear inline in the Logs tab for AI nodes and are aggregated at the workflow level in the overall workflow console.

​
Example workflows

​
Dynamic documentation updates

Update product documentation whenever a new release is deployed: 
Workflow: Product Release
Nodes:
  1. Receive Release Data
  2. Knowledge Base Operation
     - KB: "Product Documentation KB"
     - Operation: "Replace Content"
     - Content Source: "Release Notes ${release.version}"
     - Content: "${release.documentation}"
  3. Notify Support Team

​
Customer support with contextual AI

Use Knowledge Base in a customer support chatbot: 
Workflow: Customer Support Chat
Nodes:
  1. Receive Customer Message
  2. Custom Agent Node
     - Model: GPT-4
     - Knowledge Base: "Support Documentation KB"
     - Content Sources: All
     - Min. Relevance: 75%
     - Max Results: 5
  3. Send Response to Customer

​
Multi-source knowledge ingestion

Aggregate information from multiple systems: 
Workflow: Weekly Knowledge Update
Nodes:
  1. Fetch from CRM System
  2. Append to KB
     - Content Source: "CRM Updates"
  3. Fetch from Documentation Site
  4. Append to KB
     - Content Source: "Documentation"
  5. Fetch from Support Tickets
  6. Append to KB
     - Content Source: "Support Insights"

​
Error handling

​
Common errors and solutions

Error: Content source "Example" does not exist in Knowledge Base "KB Name"Cause: Attempting to append or replace content in a non-existent content sourceSolution:
  • Verify the content source name is correct
  • Use “Append Content” which creates the content source if it doesn’t exist
  • Check for typos in content source names
Error: Failed to parse JSON contentCause: The content provided is not valid JSONSolution:
  • Ensure workflow variables contain valid JSON
  • Validate JSON structure before passing to Knowledge Base operation
  • Check for special characters that may break JSON formatting
Error: Knowledge Base "KB Name" not found or not accessibleCause: The Knowledge Base doesn’t exist or you don’t have permissionsSolution:
  • Verify the Knowledge Base exists in the project or dependencies
  • Check access permissions for the Knowledge Base
  • Ensure the Knowledge Base is published if using from dependencies
Error: Failed to process content into chunksCause: Error occurred while creating chunks from the contentSolution:
  • Check console logs for detailed error messages
  • Verify the content is in the expected format
  • Retry the operation
  • Contact support if the issue persists

​
Best practices

​
Agent configuration

Custom Agent with Knowledge Base:
  • Start with a higher minimum relevance score (70-80%) to avoid irrelevant results
  • Adjust max results based on your use case (fewer for focused answers, more for comprehensive coverage)
  • Test different queries to understand chunk retrieval behavior
  • Monitor console logs to optimize configuration

​
Relevance score management

Optimizing relevance scores:
  • Chunk size matters: If chunks are too large and queries are small, relevance scores will be low because the query doesn’t cover all the content. If you find yourself setting minimum relevance score to 0%, this may indicate your chunks are too large.
  • Let the agent determine relevance: Consider ordering chunks by relevance (descending) and letting the agent evaluate which chunks are relevant, rather than filtering by minimum relevance score. The agent can see if chunks are relevant and make better decisions.
  • System prompt guidance: If you want to manage relevance filtering, add instructions to your system prompt such as: “If you don’t find any relevant information in the provided chunks, just say ‘I cannot find this information’.”
  • Empty results handling: The Knowledge Base tool returns an empty list when no results are found. Ensure your agent handles empty results gracefully and informs users when information is not available.

​
Performance

Optimize performance:
  • Keep content sources focused and organized by topic
  • Use content source filters when you know which source contains relevant information
  • Avoid ingesting extremely large documents without proper structuring
  • Regular cleanup of deprecated content sources
  • Consider removing max results limit: Instead of limiting the number of chunks, order them by relevance (descending) and let the agent process all relevant chunks. This allows the agent to make better decisions about which information to use.

​
Limitations

Current limitations:
  • Only one Knowledge Base per Custom Agent node or Context Retrieval node
  • Cannot ingest documents directly from Document Plugin
  • Structured metadata filters use exact match with AND logic only; toggle Use advance metadata filters for expression-based filtering

​
Using Context Retrieval nodes

The Context Retrieval node performs a standalone RAG search against a Knowledge Base and returns raw chunks without calling an LLM. This gives you full control over how retrieved information is used in your workflow.

​
When to use Context Retrieval

  • You need to inspect or filter chunks before passing them to an AI node
  • You want to combine results from multiple Knowledge Bases
  • You need chunk metadata (relevance scores, content sources) for routing decisions
  • You’re building a multi-step RAG pipeline with custom processing between retrieval and generation
For full configuration details, see the Context Retrieval node documentation.

​
Next steps

Managing Content

Understand content source management in detail

Custom Agent Nodes

Complete guide to Custom Agent nodes

Context Retrieval

Standalone Knowledge Base retrieval without LLM

Integration Designer

Overview of all workflow node types including Context Retrieval

Workflow Data Models

Understanding workflow variables and data
Last modified on March 16, 2026