microsoft/semantic-kernel · error · MemoryConnectorInitializationError

WeaviateMemoryStore requires a URL or API key, or to use emb

Error message

WeaviateMemoryStore requires a URL or API key, or to use embed.

What it means

Raised by the (deprecated) WeaviateMemoryStore constructor (MemoryConnectorInitializationError) when none of the client-creation branches match: use_embed is false, not (api_key AND url), and not url. In other words you provided neither an embedded client, nor a usable URL. This old store only understands url/api_key/use_embed — it does NOT support local_host/local_port modes that the newer WeaviateSettings/WeaviateStore support.

Source

Thrown at python/semantic_kernel/connectors/memory_stores/weaviate/weaviate_memory_store.py:152

        """
        self.settings = WeaviateSettings(
            url=url,
            api_key=api_key,
            use_embed=use_embed,
            env_file_path=env_file_path,
            env_file_encoding=env_file_encoding,
        )
        if self.settings.use_embed:
            self.client = weaviate.Client(embedded_options=weaviate.EmbeddedOptions())
        elif self.settings.api_key and self.settings.url:
            self.client = weaviate.Client(
                url=str(self.settings.url),
                auth_client_secret=weaviate.auth.AuthApiKey(api_key=self.settings.api_key.get_secret_value()),
            )
        elif self.settings.url:
            self.client = weaviate.Client(url=str(self.settings.url))
        else:
            raise MemoryConnectorInitializationError("WeaviateMemoryStore requires a URL or API key, or to use embed.")

    async def create_collection(self, collection_name: str) -> None:
        """Creates a new collection in Weaviate."""
        schema = SCHEMA.copy()
        schema["class"] = collection_name
        await asyncio.get_running_loop().run_in_executor(None, self.client.schema.create_class, schema)

    async def get_collections(self) -> list[str]:
        """Returns a list of all collections in Weaviate."""
        schemas = await asyncio.get_running_loop().run_in_executor(None, self.client.schema.get)
        return [schema["class"] for schema in schemas["classes"]]

    async def delete_collection(self, collection_name: str) -> bool:
        """Deletes a collection in Weaviate."""
        await asyncio.get_running_loop().run_in_executor(None, self.client.schema.delete_class, collection_name)

    async def does_collection_exist(self, collection_name: str) -> bool:
        """Checks if a collection exists in Weaviate."""

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Set WEAVIATE_URL (and WEAVIATE_API_KEY for WCD) env vars, or pass url= and api_key= explicitly.
2. For local dev/embedded, set WEAVIATE_USE_EMBED=true (or pass use_embed=True).
3. Migrate to the non-deprecated WeaviateStore + collection, which also supports WEAVIATE_LOCAL_HOST/PORT for Docker.

Example fix

// before
store = WeaviateMemoryStore()  # raises
// after
store = WeaviateMemoryStore(url='https://xxx.weaviate.network', api_key='secret')
// or
store = WeaviateMemoryStore(use_embed=True)

import os
url = os.environ.get('WEAVIATE_URL')
api_key = os.environ.get('WEAVIATE_API_KEY')
use_embed = os.environ.get('WEAVIATE_USE_EMBED', '').lower() == 'true'
assert use_embed or url, 'set WEAVIATE_URL (+WEAVIATE_API_KEY) or WEAVIATE_USE_EMBED=true'
store = WeaviateMemoryStore(url=url, api_key=api_key, use_embed=use_embed)

from semantic_kernel.exceptions.memory_connector_exceptions import MemoryConnectorInitializationError
try:
    store = WeaviateMemoryStore(url=url, api_key=api_key)
except MemoryConnectorInitializationError:
    store = WeaviateMemoryStore(use_embed=True)  # local fallback

When it happens

Trigger: Constructing `WeaviateMemoryStore()` with no arguments and no WEAVIATE_URL / WEAVIATE_USE_EMBED env vars; or supplying only an api_key without a url; or wanting a local Docker instance via local_host (unsupported by this deprecated class).

Common situations: Missing/misspelled WEAVIATE_URL or WEAVIATE_API_KEY env vars; .env file not loaded; pointing at Weaviate Cloud without the API key; trying local Docker mode with the deprecated store (use WeaviateStore instead).

Related errors

• Path of persist directory is not set
• Persist directory is not set
• Failed to create Azure OpenAI settings: {exc}
• Please provide an Azure OpenAI endpoint
• Please provide an Azure OpenAI deployment name

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/95bca0983b9f04bf. Report an issue: GitHub.