BerriAI/litellm · error · TimeoutError

OpenSearch collection did not become active in time

Error message

OpenSearch collection did not become active in time

What it means

Timeout after polling batch_get_collection for ~5 minutes: the newly created OpenSearch Serverless collection never reached ACTIVE status (stuck in CREATING/FAILED, often due to slow policy propagation or capacity limits). The collection id is recorded in _created_resources but is unusable; retry or investigate the collection in AWS.

Source

Thrown at litellm/rag/ingestion/bedrock_ingestion.py:342

        # Create collection
        response: Final = oss.create_collection(
            name=collection_name,
            type="VECTORSEARCH",
        )
        collection_id: Final = response["createCollectionDetail"]["id"]
        self._created_resources["opensearch_collection"] = collection_name

        # Wait for collection to be active (use asyncio.sleep to avoid blocking)
        verbose_logger.debug("Waiting for OpenSearch collection to be active...")
        for _ in range(60):  # 5 min timeout
            status_response = oss.batch_get_collection(ids=[collection_id])
            status = status_response["collectionDetails"][0]["status"]
            if status == "ACTIVE":
                break
            await asyncio.sleep(5)
        else:
            raise TimeoutError("OpenSearch collection did not become active in time")

        collection_arn: Final = status_response["collectionDetails"][0]["arn"]
        verbose_logger.info("Created OpenSearch collection: %s", collection_name)

        # Wait for data access policy to propagate before returning
        # AWS recommends waiting 60+ seconds for policy propagation
        verbose_logger.debug("Waiting for data access policy to propagate (60s)...")
        await asyncio.sleep(60)

        return collection_name, collection_arn

    async def _create_opensearch_index(self, collection_name: str):
        """Create vector index in OpenSearch collection with retry logic."""
        from opensearchpy import OpenSearch, RequestsHttpConnection
        from requests_aws4auth import AWS4Auth

        # Get credentials for signing
        credentials: Final = self.get_credentials(

View on GitHub (pinned to 77b7c6c40c)

Solutions

1. Retry the operation; check the OpenSearch collection status in the AWS console and increase wait time if needed.

When it happens

Trigger: Thrown at litellm/rag/ingestion/bedrock_ingestion.py:342 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of BerriAI/litellm@77b7c6c40c (2026-08-18). Data as JSON: /api/errors/9b67e3c4ede785ab. Report an issue: GitHub.