mem0ai/mem0 · error · ValueError

Either a client or URL and token must be provided.

Error message

Either a client or URL and token must be provided.

What it means

Raised in UpstashVector.__init__ when the constructor gets neither an injected `client` nor both `url` and `token`. The branching is strict: only `url and token` together form a valid Index; passing just one of them (or neither) lands in the else. Unlike some stores there is no environment-variable fallback in this module — credentials must come from config or an injected client.

Source

Thrown at mem0/vector_stores/upstash_vector.py:64

        token: Optional[str] = None,
        client: Optional[Index] = None,
        enable_embeddings: bool = False,
    ):
        """
        Initialize the UpstashVector vector store.

        Args:
            url (str, optional): URL for Upstash Vector index. Defaults to None.
            token (int, optional): Token for Upstash Vector index. Defaults to None.
            client (Index, optional): Existing `upstash_vector.Index` client instance. Defaults to None.
            namespace (str, optional): Default namespace for the index. Defaults to None.
        """
        if client:
            self.client = client
        elif url and token:
            self.client = Index(url, token)
        else:
            raise ValueError("Either a client or URL and token must be provided.")

        self.collection_name = collection_name

        self.enable_embeddings = enable_embeddings

    def insert(
        self,
        vectors: List[list],
        payloads: Optional[List[Dict]] = None,
        ids: Optional[List[str]] = None,
    ):
        """
        Insert vectors

        Args:
            vectors (list): List of vectors to insert.
            payloads (list, optional): List of payloads corresponding to vectors. These will be passed as metadatas to the Upstash Vector client. Defaults to None.
            ids (list, optional): List of IDs corresponding to vectors. Defaults to None.

View on GitHub (pinned to 001c235229)

Solutions

1. Supply both credentials in the vector store config: `"config": {"url": ..., "token": ..., "collection_name": "mem"}`.
2. Or build the client yourself and pass `client=Index(url, token)`.
3. If using env vars, wire them explicitly: `"url": os.environ["UPSTASH_VECTOR_REST_URL"]`.

Example fix

# before
memory = Memory.from_config({
    "vector_store": {"provider": "upstash_vector", "config": {"collection_name": "mem"}}
})  # ValueError

# after
import os
memory = Memory.from_config({
    "vector_store": {
        "provider": "upstash_vector",
        "config": {
            "collection_name": "mem",
            "url": os.environ["UPSTASH_VECTOR_REST_URL"],
            "token": os.environ["UPSTASH_VECTOR_REST_TOKEN"],
        },
    }
})

import os

def upstash_config() -> dict:
    url = os.environ.get("UPSTASH_VECTOR_REST_URL")
    token = os.environ.get("UPSTASH_VECTOR_REST_TOKEN")
    if not (url and token):
        raise SystemExit("Upstash Vector requires both UPSTASH_VECTOR_REST_URL and UPSTASH_VECTOR_REST_TOKEN")
    return {"provider": "upstash_vector", "config": {"url": url, "token": token, "collection_name": "mem"}}

try:
    store = UpstashVector(collection_name="mem", url=url, token=token)
except ValueError as e:
    if "client or URL and token" in str(e):
        raise RuntimeError("Upstash credentials incomplete: need both url and token") from e
    raise

When it happens

Trigger: `UpstashVector(collection_name="mem")` with no url/token/client; config with `"token": ...` but a missing or misnamed `"url"` key; passing url but relying on an env var for the token that this class never reads.

Common situations: Assuming UPSTASH_VECTOR_REST_URL/TOKEN env vars are picked up automatically (the hosted platform does that, this OSS store may not, depending on config wiring); typos in config keys; partially redacted config templates.

Related errors

• Either a client or URL and token must be provided.
• When embeddings are enabled, all payloads must contain a 'da
• Failed to parse googleServiceAccountJson: ${err.message}
• Vertex AI could not determine a Google Cloud project ID. Set
• Unsupported vector store provider: ${provider}

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/98106e3938cf7a5f. Report an issue: GitHub.