microsoft/semantic-kernel · error · MemoryConnectorInitializationError

Failed to create Redis settings.

Error message

Failed to create Redis settings.

What it means

Raised by RedisMemoryStore.__init__() when constructing RedisSettings raises a pydantic ValidationError (e.g. connection_string missing/invalid). It is wrapped as MemoryConnectorInitializationError (a MemoryConnectorException, not a ServiceException) with the original ValidationError chained via `from ex`.

Source

Thrown at python/semantic_kernel/connectors/memory_stores/redis/redis_memory_store.py:100

        Args:
            connection_string (str): Provide connection URL to a Redis instance
            vector_size (str): Size of vectors, defaults to 1536
            vector_distance_metric (str): Metric for measuring vector distances, defaults to COSINE
            vector_type (str): Vector type, defaults to FLOAT32
            vector_index_algorithm (str): Indexing algorithm for vectors, defaults to HNSW
            query_dialect (int): Query dialect, must be 2 or greater for vector similarity searching, defaults to 2
            env_file_path (str | None): Use the environment settings file as a fallback to
                environment variables, defaults to False
            env_file_encoding (str | None): Encoding of the environment settings file, defaults to "utf-8"
        """
        try:
            redis_settings = RedisSettings(
                connection_string=connection_string,
                env_file_path=env_file_path,
                env_file_encoding=env_file_encoding,
            )
        except ValidationError as ex:
            raise MemoryConnectorInitializationError("Failed to create Redis settings.", ex) from ex

        if vector_size <= 0:
            raise MemoryConnectorInitializationError("Vector dimension must be a positive integer")

        self._database = redis.Redis.from_url(redis_settings.connection_string.get_secret_value())
        self._ft = self._database.ft

        self._query_dialect = query_dialect
        self._vector_distance_metric = vector_distance_metric
        self._vector_index_algorithm = vector_index_algorithm
        self._vector_type_str = vector_type
        self._vector_type = np.float32 if vector_type == "FLOAT32" else np.float64
        self._vector_size = vector_size

    async def close(self):
        """Closes the Redis database connection."""
        logger.info("Closing Redis connection")
        self._database.close()

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Set REDIS_CONNECTION_STRING (or pass connection_string explicitly), e.g. 'redis://localhost:6379'.
2. If using a .env file, pass env_file_path correctly and ensure encoding matches.
3. Inspect the chained ValidationError (ex) for the exact failing field.
4. Validate the URL format (scheme redis:// or rediss://) before constructing the store.

Example fix

// before
store = RedisMemoryStore(connection_string=os.getenv('REDIS_URL'))  # None if unset
// after
store = RedisMemoryStore(connection_string='redis://localhost:6379')
# or set env: export REDIS_CONNECTION_STRING=redis://localhost:6379

import os
conn = os.getenv('REDIS_CONNECTION_STRING')
assert conn and conn.startswith(('redis://', 'rediss://')), 'valid REDIS_CONNECTION_STRING required'
store = RedisMemoryStore(connection_string=conn)

def valid_redis_url(s: str) -> bool:
    return isinstance(s, str) and s.startswith(('redis://', 'rediss://')) and len(s) > len('redis://')

from semantic_kernel.exceptions.memory_connector_exceptions import MemoryConnectorInitializationError
try:
    store = RedisMemoryStore(connection_string=conn)
except MemoryConnectorInitializationError as e:
    raise RuntimeError(f'invalid redis settings: {e.__cause__}') from e

When it happens

Trigger: Constructing RedisMemoryStore(connection_string=...) where the value fails RedisSettings validation: empty/None connection_string, or the REDIS_CONNECTION_STRING env var (env_prefix 'REDIS_') is unset when no value is passed.

Common situations: REDIS_CONNECTION_STRING not set in the environment; .env file not loaded (env_file_path wrong); malformed redis:// URL; secret stripped to empty by config loader.

Related errors

• Vector dimension must be a positive integer
• Failed to create collection {collection_name}
• Failed to initialize the Amazon Bedrock Agent settings: {e}
• Expected OpenAISettings, got {type(settings).__name__}
• Failed to create OpenAI settings.

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/5b7efae7201aec16. Report an issue: GitHub.