microsoft/semantic-kernel · error · MemoryConnectorInitializationError

Failed to create AstraDB settings.

Error message

Failed to create AstraDB settings.

What it means

Raised in the `AstraDBMemoryStore` constructor when constructing the pydantic `AstraDBSettings` model raises a `ValidationError`. The validation error is wrapped in a `MemoryConnectorInitializationError` (chained via `from ex`) so callers see a connector-level failure. It means one or more required settings (app token, db id, region, keyspace) are missing or invalid.

Source

Thrown at python/semantic_kernel/connectors/memory_stores/astradb/astradb_memory_store.py:75

            keyspace_name (str): The Astra keyspace
            embedding_dim (int): The dimensionality to use for new collections.
            similarity (str): TODO
            session: Optional session parameter
            env_file_path (str | None): Use the environment settings file as a
                fallback to environment variables. (Optional)
            env_file_encoding (str | None): The encoding of the environment settings file. (Optional)
        """
        try:
            astradb_settings = AstraDBSettings(
                app_token=astra_application_token,
                db_id=astra_id,
                region=astra_region,
                keyspace=keyspace_name,
                env_file_path=env_file_path,
                env_file_encoding=env_file_encoding,
            )
        except ValidationError as ex:
            raise MemoryConnectorInitializationError("Failed to create AstraDB settings.", ex) from ex

        self._embedding_dim = embedding_dim
        self._similarity = similarity
        self._session = session

        if self._embedding_dim > MAX_DIMENSIONALITY:
            raise MemoryConnectorInitializationError(
                f"Dimensionality of {self._embedding_dim} exceeds the maximum allowed value of {MAX_DIMENSIONALITY}."
            )

        self._client = AstraClient(
            astra_id=astradb_settings.db_id,
            astra_region=astradb_settings.region,
            astra_application_token=(
                astradb_settings.app_token.get_secret_value() if astradb_settings.app_token else None
            ),
            keyspace_name=astradb_settings.keyspace,
            embedding_dim=embedding_dim,

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Set the required Astra env vars: `ASTRA_DB_APP_TOKEN`, `ASTRA_DB_ID`, `ASTRA_DB_REGION`, `ASTRA_DB_KEYSPACE` (or pass them as constructor args).
2. Point `env_file_path` at an existing `.env` file with these values, and confirm `env_file_encoding` matches.
3. Inspect the chained `ValidationError` (`exc.__cause__`) for the exact missing/invalid field names.
4. Verify secrets are actually exported in the runtime environment (container/CI), not just in a local file.

Example fix

// before
store = AstraDBMemoryStore(embedding_dim=1536)  # no token/id/region -> ValidationError

// after
store = AstraDBMemoryStore(
    astra_application_token=os.environ["ASTRA_DB_APP_TOKEN"],
    astra_id=os.environ["ASTRA_DB_ID"],
    astra_region=os.environ["ASTRA_DB_REGION"],
    keyspace_name=os.environ["ASTRA_DB_KEYSPACE"],
    embedding_dim=1536,
)

import os

def astra_env_ready() -> bool:
    required = ["ASTRA_DB_APP_TOKEN", "ASTRA_DB_ID", "ASTRA_DB_REGION", "ASTRA_DB_KEYSPACE"]
    return all(os.getenv(v) for v in required)

# assert astra_env_ready() before constructing the store

from semantic_kernel.exceptions import MemoryConnectorInitializationError
try:
    store = AstraDBMemoryStore(...)
except MemoryConnectorInitializationError as e:
    cause = e.__cause__  # pydantic ValidationError -> missing fields
    raise SystemExit(f"Astra settings invalid: {cause}") from e

When it happens

Trigger: Instantiating `AstraDBMemoryStore(...)` without supplying `astra_application_token`, `astra_id`, `astra_region`, and/or `keyspace_name`, and the corresponding environment variables (`ASTRA_DB_APP_TOKEN`, `ASTRA_DB_ID`, etc.) plus the `.env` file (via `env_file_path`) are also absent. Pydantic raises `ValidationError`; the constructor converts it to `MemoryConnectorInitializationError`.

Common situations: Missing `.env` file or wrong `env_file_path`; environment variables not exported in the deployment shell; `.gitignore` excluding the secrets file; CI/container missing the Astra secrets; typo in an env var name; passing an empty string where a required field is expected.

Related errors

• Failed to create Azure Cognitive Search settings.
• Dimensionality of {self._embedding_dim} exceeds the maximum
• Failed to create Azure OpenAI settings: {exc}
• Failed to validate Google AI settings: {e}
• Failed to validate Google AI settings: {e}

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/134ab96ce5cef0fe. Report an issue: GitHub.