Knowledge Base

Search ByteChef's internal knowledge base to retrieve relevant document chunks using semantic similarity search powered by vector embeddings.

Categories: Artificial Intelligence

Type: knowledgeBase/v1

Actions

Load Data

Name: load

Loads data into the vector store using LLM embeddings.

Properties

Name	Label	Type	Description	Required
knowledgeBaseId	Knowledge Base	INTEGER	The knowledge base to load documents into.	true

Example JSON Structure

{
  "label" : "Load Data",
  "name" : "load",
  "parameters" : {
    "knowledgeBaseId" : 1
  },
  "type" : "knowledgeBase/v1/load"
}

Output

This action does not produce any output.

Search Data

Name: search

Query data from the knowledge base. Supports three modes: tag-only search, vector search, or combined tag filtering with vector search.

Properties

Name	Label	Type	Description	Required
knowledgeBaseId	Knowledge Base	INTEGER	The knowledge base to search.	true
query	Query	STRING	The search query for semantic similarity search. Leave empty for tag-only search.	false
tagIds	Tags	ARRAY Items [INTEGER]	Filter results by tags. Documents with ANY of the selected tags will be returned (OR logic).	false
topK	Top K	INTEGER	Maximum number of results to return.	false
similarityThreshold	Similarity Threshold	NUMBER	Minimum similarity score (0.0 to 1.0). Only results with similarity above this threshold will be returned.	false

Example JSON Structure

{
  "label" : "Search Data",
  "name" : "search",
  "parameters" : {
    "knowledgeBaseId" : 1,
    "query" : "",
    "tagIds" : [ 1 ],
    "topK" : 1,
    "similarityThreshold" : 0.0
  },
  "type" : "knowledgeBase/v1/search"
}

Output

The output for this action is dynamic and may vary depending on the input parameters. To determine the exact structure of the output, you need to execute the action.

On this page