Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.flowx.ai/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

Available starting with FlowX.AI 5.6.0
The Context Retrieval node is a specialized Integration Designer workflow node that performs RAG (Retrieval-Augmented Generation) searches against a Knowledge Base. Unlike the Custom Agent node, Context Retrieval does not call an LLM — it retrieves and returns matching chunks directly, giving you full control over how the results are processed downstream.
Context Retrieval node configuration with Source, User Query, Search Type, and relevance settings
Use Context Retrieval when you want to separate the retrieval step from the generation step. This lets you inspect, filter, or transform retrieved chunks before passing them to an AI node for response generation.

​
When to use Context Retrieval vs Custom Agent

ScenarioRecommended node
You need the AI to reason about retrieved information and generate a responseCustom Agent with Knowledge Base enabled
You want raw chunks to process, filter, or route in your workflowContext Retrieval
You need to combine chunks from multiple Knowledge BasesContext Retrieval (one per KB) + downstream merge
You want a simple question-answer flow with RAGCustom Agent with Knowledge Base enabled

​
Configuration

​
Knowledge Base

​
Knowledge Base
select
required
Select one or more Knowledge Base resource references to query.

​
Source

​
Source
enum
The source type to query.Options:
  • KNOWLEDGE_BASE — Search the selected Knowledge Base (default)
  • MEMORY — Search conversation memory
The MEMORY option is only available in conversational workflows.Default: KNOWLEDGE_BASE

​
Settings

The settings below are available inside the Settings expander on the node configuration panel.

​
Search type

Available starting with FlowX.AI 5.7.0Search type and re-ranking options give you control over how chunks are retrieved from the Knowledge Base.
​
Search Type
enum
The strategy used for retrieving context from the Knowledge Base.Options:
  • Hybrid — Combines semantic and keyword search for balanced results (default)
  • Semantic — Uses vector similarity for meaning-based search
  • Keywords — Uses traditional keyword matching
Default: HYBRID
When Keywords is selected, the Min Relevance Score slider is hidden because keyword search does not produce a relevance score.

​
Query parameters

​
Max Number of Chunks
number
Maximum number of relevant chunks to return. Configurable from 1 to 10.Default: 4
​
Min Relevance Score
number
Minimum relevance score threshold, expressed as a percentage (0–100). Only chunks with a relevance score above this threshold are returned. Not available when search type is set to Keywords.Default: 50

​
Metadata filters

​
Metadata Filters
button
Opens a query builder modal where you compose conditions as field / operator / value triples. Operators depend on the metadata key type (equals, not equals, contains, in, not in, before, after, exists, etc.). Conditions can be grouped and combined with AND or OR.To filter by store, add a condition on the system metadata key source.
Enhanced in FlowX.AI 5.7.0 — typed operators and AND/OR grouping are now supported. See Filtering by metadata for the full operator list.
​
Use advance metadata filters
boolean
Toggle to turn on advanced metadata filter expressions for more complex filtering logic. When turned on, a JSON expression field becomes available for defining property-based filters.Default: false

​
Re-ranking

Available starting with FlowX.AI 5.7.0
​
Use Re-Rank
boolean
When turned on, applies a re-ranking model to the retrieved chunks, reordering them by relevance to the query. This can improve result quality at the cost of slightly higher latency.Default: false

​
Operation prompt

The operation prompt defines the query text sent to the Knowledge Base. It supports ${} placeholder syntax for dynamic values from workflow input and configuration parameters. Example: 
${userQuery}
Both runtime input variables and configuration parameters are available for placeholder resolution.

​
Output format

The Context Retrieval node returns an array of chunk objects. Each chunk contains:
FieldTypeDescription
chunkContentstringThe text content of the retrieved chunk
chunkMetadataobjectMetadata associated with the chunk (key-value pairs)
relevanceScorenumberSimilarity score between the query and the chunk (0–1)
contentSourcestringThe name of the store the chunk belongs to (field name preserved for API compatibility)

​
Example output

[
  {
    "chunkContent": "The onboarding process requires identity verification...",
    "chunkMetadata": {
      "source": "onboarding-guide.pdf",
      "page": "3"
    },
    "relevanceScore": 0.92,
    "contentSource": "Product Documentation"
  },
  {
    "chunkContent": "KYC checks must be completed within 48 hours...",
    "chunkMetadata": {
      "source": "compliance-policy.pdf",
      "page": "12"
    },
    "relevanceScore": 0.85,
    "contentSource": "Compliance Policies"
  }
]

​
Error handling

If the Context Retrieval node fails, the workflow produces a WORKFLOW_NODE_CONTEXT_RETRIEVAL_ERROR error. Common causes include:
The referenced Knowledge Base does not exist or is not accessible.Solution: Verify the Knowledge Base exists in your project or dependencies and that you have the required permissions.
The operation prompt resolved to an empty or invalid query.Solution: Check that the ${} placeholders in your operation prompt reference valid input or config variables.
The RAG search exceeded the configured timeout.Solution: The default timeout is 300 seconds (flowx.ai-service.nodeRunnerTimeoutSeconds). Consider simplifying your query or reducing the topK value.

​
Best practices

Optimizing Context Retrieval:
  • Start with Hybrid search type for the best balance of precision and recall
  • Use Semantic when your queries are natural-language questions; use Keywords for exact-match lookups
  • The default minimum relevance threshold (50%) is a good starting point — increase it to filter out lower-quality matches
  • Turn on Use Re-Rank when result quality is more important than latency
  • Use metadata filters to narrow results to specific stores (via the source key) or metadata values
  • Keep Max Number of Chunks reasonable (3–10) to avoid overwhelming downstream nodes with too much context
Building RAG pipelines:
  • Chain Context Retrieval → Script Node → Custom Agent to build custom RAG flows with intermediate processing
  • Use the relevanceScore field to implement your own relevance filtering logic in a Script node
  • Combine results from multiple Context Retrieval nodes (querying different KBs) using a Script node before passing to generation

Knowledge Base overview

Create and manage Knowledge Bases

Using Knowledge Base in workflows

Query Knowledge Bases with Custom Agent nodes

Custom Agent node

AI agents with MCP tools and Knowledge Base access

Integration Designer

Build and manage integration workflows
Last modified on April 24, 2026