Back to Mindsdb

Query Knowledge Base

docs/rest/knowledge_bases/query.mdx

26.1.02.2 KB
Original Source

POST /api/sql/query

This API endpoint queries a knowledge base using the POST method. Learn more about querying knowledge bases using semantic search and metadata filtering here.

<Tip> Learn more about knowledge bases following [this doc page](/mindsdb_sql/knowledge_bases/overview). </Tip>

Path Parameters

None.

Body

<ParamField body='query' type='string' required> A query that is sent to the MindsDB instance. </ParamField>

Response

Contains data stored in the knowledge base.

<RequestExample>
shell
curl -X POST http://127.0.0.1:47334/api/sql/query \
     --header 'Content-Type: application/json' \
     --data '{
        "query": "SELECT * FROM my_kb;"
     }'
</RequestExample> <ResponseExample>
json
{
  "type": "table",
  "column_names": [
    "id",
    "chunk_id",
    "chunk_content",
    "metadata",
    "relevance",
    "distance"
  ],
  "data": [
    [
      "A1B",
      "A1B:notes:1of1:0to20",
      "Request color: black",
      {
        "chunk_index": 0,
        "content_column": "notes",
        "end_char": 20,
        "original_doc_id": "A1B",
        "original_row_index": "0",
        "product": "Wireless Mouse",
        "source": "TextChunkingPreprocessor",
        "start_char": 0
      },
      null,
      null
    ],
    [
      "3XZ",
      "3XZ:notes:1of1:0to19",
      "Gift wrap requested",
      {
        "chunk_index": 0,
        "content_column": "notes",
        "end_char": 19,
        "original_doc_id": "3XZ",
        "original_row_index": "1",
        "product": "Bluetooth Speaker",
        "source": "TextChunkingPreprocessor",
        "start_char": 0
      },
      null,
      null
    ],
    [
      "Q7P",
      "Q7P:notes:1of1:0to22",
      "Prefer aluminum finish",
      {
        "chunk_index": 0,
        "content_column": "notes",
        "end_char": 22,
        "original_doc_id": "Q7P",
        "original_row_index": "2",
        "product": "Aluminum Laptop Stand",
        "source": "TextChunkingPreprocessor",
        "start_char": 0
      },
      null,
      null
    ]
  ],
  "context": {
    "show_secrets": false,
    "db": "mindsdb"
  }
}
</ResponseExample>