Index and search text

Use the Text Store for preconfigured vector search, or Tables for low-level control over schema, indices, and search operations.

The Search API provides two ways to store and retrieve text:

• Text Store — preconfigured vector storage with hybrid search, deduplication, and grouping. No schema or index setup required.
• Tables — low-level access to the vector database with full control over schema, indices, filters, and search operations.

Start with Text Store for most use cases. Use Tables when you need custom schemas, explicit index management, or advanced filter expressions.

If you need an external-facing example that shows GraphRAG outperforming flat retrieval on a defined benchmark, see GraphRAG evaluation.

Create a text store

Provide a name and the embedding dimension for your vectors.

CLI

mka1 search text-store create \
  -H 'X-On-Behalf-Of: <end-user-id>' \
  --body '{
    "store_name": "product_catalog",
    "dimension": 3
  }'

Add texts to a text store

Add texts with their pre-computed embedding vectors. Duplicate texts are automatically skipped. The group field tags entries so you can delete or retrieve them as a set later.

CLI

mka1 search text-store add-texts \
  --store-name product_catalog \
  --body '{
    "texts": [
      "Noise-cancelling over-ear headphones with 30-hour battery.",
      "Compact wireless earbuds with active noise cancellation.",
      "Studio monitor headphones with flat frequency response."
    ],
    "vectors": [
      [0.16, -0.08, 0.29],
      [0.14, -0.06, 0.31],
      [0.09, -0.12, 0.22]
    ],
    "group": "headphones"
  }'

Search a text store

Pass a text query and its embedding vector. The service runs a hybrid search combining full-text and vector similarity.

CLI

mka1 search text-store search-texts \
  --store-name product_catalog \
  --body '{
    "query": "noise-cancelling headphones",
    "vector": [0.16, -0.08, 0.29],
    "limit": 5
  }'

Delete text from a text store

Remove specific entries by their exact text values.

CLI

mka1 search text-store delete-texts \
  --store-name product_catalog \
  --body '{
    "texts": [
      "Studio monitor headphones with flat frequency response."
    ]
  }'

Delete texts by group from a text store

Remove all entries that belong to one or more groups.

CLI

mka1 search text-store delete-texts \
  --store-name product_catalog \
  --body '{
    "groups": ["headphones"]
  }'

Delete a text store

Remove the store and all of its data.

CLI

mka1 search text-store delete --store-name product_catalog

Advanced Usage: Tables

Tables give you direct access to the underlying vector database. You define the schema, choose which fields to index, insert structured rows, and compose search operations yourself.

Schema fields

Each field in a table schema has a name, type, and optional properties.

Type	Description	Index support
string	Text data	FTS (full-text search)
int	32-bit integer	BTREE, BITMAP, LABEL_LIST
float	64-bit floating point	BTREE, BITMAP, LABEL_LIST
datetime	Timestamp with optional timezone	BTREE
vector	Fixed-dimension embedding	IVF_FLAT, IVF_PQ, IVF_HNSW_PQ, IVF_HNSW_SQ
list	List of strings, ints, or floats	—

Set nullable to false for required fields. Add "index": "FTS" on a string field to enable full-text search at creation time. Vector fields require a dimensions property that matches your embedding size.

Create a search table

Define a table with a schema that describes your records. The example below creates a support knowledge base with a text field indexed for full-text search and a vector field for semantic search.

CLI

mka1 search tables create \
  --body '{
    "name": "support_kb",
    "schema": {
      "fields": [
        { "name": "id", "type": "string", "nullable": false },
        { "name": "content", "type": "string", "nullable": false, "index": "FTS" },
        { "name": "category", "type": "string", "nullable": false },
        { "name": "rating", "type": "float", "nullable": true },
        { "name": "embedding", "type": "vector", "nullable": false, "dimensions": 3 }
      ]
    }
  }'

Insert rows

Insert records that match the table schema. You can send multiple rows in a single request.

CLI

mka1 search tables insert-data \
  --table-name support_kb \
  --body '{
    "data": [
      {
        "id": "doc_001",
        "content": "Reset your password from the account settings page.",
        "category": "account",
        "rating": 4.7,
        "embedding": [0.13, -0.09, 0.41]
      },
      {
        "id": "doc_002",
        "content": "Use two-factor authentication for added account security.",
        "category": "security",
        "rating": 4.9,
        "embedding": [0.07, -0.02, 0.36]
      }
    ]
  }'

Search operations

Table search lets you compose multiple operations in a single request. Operations run in order — start with a primary search, then refine with filters, limits, or offsets.

Primary operations initialize the result set:

Operation	Description
vector_search	Find rows closest to a query vector. Supports cosine, l2, dot, and hamming distance types.
fts	Full-text keyword search on one or more string fields.

Secondary operations refine the results:

Operation	Description
filter	Apply a SQL-like expression. Set prefilter to true to filter before ranking.
limit	Cap the number of returned rows.
offset	Skip the first N rows for pagination.

Use returnColumns to control which fields come back in the response.

Search the table

The example below combines a vector search with a pre-filter on the category field.

CLI

mka1 search tables search-data \
  --table-name support_kb \
  --body '{
    "operations": [
      {
        "type": "vector_search",
        "field": "embedding",
        "vector": [0.11, -0.06, 0.37],
        "distanceType": "cosine",
        "limit": 5
      },
      {
        "type": "filter",
        "expression": "category = '\''security'\''",
        "prefilter": true
      }
    ],
    "returnColumns": ["id", "content", "category", "rating"]
  }'

Delete rows

Remove rows from a table using a filter expression.

CLI

mka1 search tables delete-data \
  --table-name support_kb \
  --body '{
    "filter": "id IN ('\''doc_001'\'', '\''doc_002'\'')"
  }'

Delete a table

Remove the table and all of its data.

CLI

mka1 search tables delete --table-name support_kb