vectorSearch

Performs similarity search across one or more datasets stored in the vector database. Fans out the query to the relevant data cluster(s) and returns a ranked list of text chunks with similarity scores.

Parameters

Param	Type	Required	Default	Description
query	string	Yes	—	Search query text. Minimum length: 1
dataset_ids	integer[]	Yes	—	List of dataset IDs to search. Minimum 1 element
k	integer	No	5	Number of results to return

Output

Field	Type	Description
documents	SearchResult[]	Ordered list of matching chunks
count	integer	Number of results returned
query	string	The original search query

Each SearchResult:

Field	Type	Description
page_content	string	The text content of the matched chunk
metadata	object	Key/value metadata attached to the chunk
score	float	Similarity score from the vector database

Example

{
  "id": "vectorSearch",
  "type": "vectorSearch",
  "data": {
    "label": "Vector Search",
    "isExecuted": false,
    "handles": ["inputs", "outputs"],
    "schema": {},
    "params": {
      "query": { "value": "{{ $input.query }}", "isExpression": true, "isAttachedToInputNode": false },
      "dataset_ids": { "value": [42, 87], "isExpression": false, "isAttachedToInputNode": false },
      "k": { "value": 10, "isExpression": false, "isAttachedToInputNode": false }
    },
    "inputs": [], "outputs": [], "errors": []
  },
  "position": { "x": 0, "y": 0 },
  "isSelected": false,
  "isDragging": false
}