mem0ai/mem0 · error · TimeoutError

Index {name} creation timed out after {max_retries} seconds

Error message

Index {name} creation timed out after {max_retries} seconds

What it means

TimeoutError raised after create_col polls for up to 180 seconds (1s sleep per attempt, counted once per failed probe) waiting for the newly created OpenSearch index to answer a match_all search. If the index never becomes queryable in that window, the loop gives up and the constructor/create path fails.

Source

Thrown at mem0/vector_stores/opensearch.py:149

        if not self.client.indices.exists(index=name):
            logger.warning(f"Creating index {name}, it might take 1-2 minutes...")
            self.client.indices.create(index=name, body=index_settings)

            # Wait for index to be ready
            max_retries = 180  # 3 minutes timeout
            retry_count = 0
            while retry_count < max_retries:
                try:
                    # Check if index is ready by attempting a simple search
                    self.client.search(index=name, body={"query": {"match_all": {}}})
                    time.sleep(1)
                    logger.info(f"Index {name} is ready")
                    return
                except Exception:
                    retry_count += 1
                    if retry_count == max_retries:
                        raise TimeoutError(f"Index {name} creation timed out after {max_retries} seconds")
                    time.sleep(0.5)

    def insert(
        self, vectors: List[List[float]], payloads: Optional[List[Dict]] = None, ids: Optional[List[str]] = None
    ) -> List[OutputData]:
        """Insert vectors into the index."""
        if not ids:
            ids = [str(i) for i in range(len(vectors))]

        if payloads is None:
            payloads = [{} for _ in range(len(vectors))]

        for idx, vec in enumerate(vectors):
            if vec is None:
                raise ValueError(
                    f"Vector at index {idx} is null. "
                    f"This usually means the embedding model failed to generate an embedding. "
                    f"Check that your embedding model is configured correctly and returning valid vectors."

View on GitHub (pinned to 001c235229)

Solutions

1. Check cluster health and index state: GET _cluster/health and GET <index>/_search, and look for red status or unassigned shards
2. Freeze capacity: fix disk watermarks/heap, scale the cluster, then retry create_col
3. For serverless, pre-warm the collection or raise the retry budget by constructing when the cluster is warm
4. If creation genuinely failed, delete the half-created index and recreate

Example fix

# before
store = OpenSearch(...)  # create_col internally times out after 180s

# after
# pre-check cluster, then construct with warm cluster
import opensearchpy
c = opensearchpy.OpenSearch(...)
assert c.cluster.health()["status"] in ("green", "yellow")
store = OpenSearch(...)

from opensearchpy import OpenSearch as OSClient

client = OSClient(...)
health = client.cluster.health()
if health.get("status") == "red":
    raise RuntimeError("cluster red; fix shards/disk before creating indexes")
# index creation is then likely to converge inside the poll window

try:
    store = OpenSearch(...)
except TimeoutError as e:
    if "creation timed out" in str(e):
        time.sleep(30)
        store = OpenSearch(...)  # retry once cluster has settled
    else:
        raise

When it happens

Trigger: Creating an index on a cold/slow OpenSearch cluster (serverless cold start, undersized nodes), a cluster still forming shards, or one where index creation actually failed server-side while the poll only sees 'exception'.

Common situations: AWS OpenSearch Serverless first-hit latency; local OpenSearch under heavy load or low disk (watermark blocking shard allocation); security-timeout misconfig where search is rejected but creation 'succeeded'.

Understand the failure class

• Timeouts: ETIMEDOUT, deadlines, and hung requests — what actually expires when a request times out.

Related errors

• Timed out waiting for Databricks endpoint ${this.endpointNam
• Baidu Mochow table '${this.tableName}' was not ${what} after
• Timed out waiting for Databricks index ${this.fullIndexName}
• Vector at index ${index} is null or undefined.
• Vector at index ${index} is empty. Expected dimension ${this

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/b369281ea6dbda46. Report an issue: GitHub.