create_vector_index_hash
Set up a Redis vector similarity index using HNSW algorithm for approximate nearest neighbor search on hash data with float32 embeddings.
Instructions
Create a Redis 8 vector similarity index using HNSW on a Redis hash.
This function sets up a Redis index for approximate nearest neighbor (ANN) search using the HNSW algorithm and float32 vector embeddings.
Args: index_name: The name of the Redis index to create. Unless specifically required, use the default name for the index. prefix: The key prefix used to identify documents to index (e.g., 'doc:'). Unless specifically required, use the default prefix. vector_field: The name of the vector field to be indexed for similarity search. Unless specifically required, use the default field name dim: The dimensionality of the vectors stored under the vector_field. distance_metric: The distance function to use (e.g., 'COSINE', 'L2', 'IP').
Returns: A string indicating whether the index was created successfully or an error message.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| index_name | No | vector_index | |
| prefix | No | doc: | |
| vector_field | No | vector | |
| dim | No | ||
| distance_metric | No | COSINE |
Implementation Reference
- src/tools/redis_query_engine.py:64-101 (handler)The core implementation of the 'create_vector_index_hash' tool. This async function, decorated with @mcp.tool(), creates a Redis vector similarity index using HNSW index on hash data structures. It handles parameters for index configuration and performs the index creation via Redis commands.@mcp.tool() async def create_vector_index_hash( index_name: str = "vector_index", prefix: str = "doc:", vector_field: str = "vector", dim: int = 1536, distance_metric: str = "COSINE", ) -> str: """ Create a Redis 8 vector similarity index using HNSW on a Redis hash. This function sets up a Redis index for approximate nearest neighbor (ANN) search using the HNSW algorithm and float32 vector embeddings. Args: index_name: The name of the Redis index to create. Unless specifically required, use the default name for the index. prefix: The key prefix used to identify documents to index (e.g., 'doc:'). Unless specifically required, use the default prefix. vector_field: The name of the vector field to be indexed for similarity search. Unless specifically required, use the default field name dim: The dimensionality of the vectors stored under the vector_field. distance_metric: The distance function to use (e.g., 'COSINE', 'L2', 'IP'). Returns: A string indicating whether the index was created successfully or an error message. """ try: r = RedisConnectionManager.get_connection() index_def = IndexDefinition(prefix=[prefix]) schema = VectorField( vector_field, "HNSW", {"TYPE": "FLOAT32", "DIM": dim, "DISTANCE_METRIC": distance_metric}, ) r.ft(index_name).create_index([schema], definition=index_def) return f"Index '{index_name}' created successfully." except RedisError as e: return f"Error creating index '{index_name}': {str(e)}"
- src/tools/redis_query_engine.py:64-64 (registration)The @mcp.tool() decorator registers the 'create_vector_index_hash' function as an MCP tool.@mcp.tool()
- The function signature and docstring define the input schema (parameters with types and defaults) and output (str: success/error message).async def create_vector_index_hash( index_name: str = "vector_index", prefix: str = "doc:", vector_field: str = "vector", dim: int = 1536, distance_metric: str = "COSINE", ) -> str: """ Create a Redis 8 vector similarity index using HNSW on a Redis hash. This function sets up a Redis index for approximate nearest neighbor (ANN) search using the HNSW algorithm and float32 vector embeddings. Args: index_name: The name of the Redis index to create. Unless specifically required, use the default name for the index. prefix: The key prefix used to identify documents to index (e.g., 'doc:'). Unless specifically required, use the default prefix. vector_field: The name of the vector field to be indexed for similarity search. Unless specifically required, use the default field name dim: The dimensionality of the vectors stored under the vector_field. distance_metric: The distance function to use (e.g., 'COSINE', 'L2', 'IP'). Returns: A string indicating whether the index was created successfully or an error message.