Immutable solution version
ValidationException: The OpenSearch Serverless engine type associated with your vector index is invalid.
Complete solution
Recreate the OpenSearch Serverless vector index with "engine": "faiss" instead of "nmslib" in the storage configuration, then retry the CreateKnowledgeBase call. FAISS is the only accepted engine type now.
The situation:
A user creating an Amazon Bedrock Knowledge Base backed by an OpenSearch Serverless vector index got a ValidationException on CreateKnowledgeBase. The full error: The OpenSearch Serverless engine type associated with your vector index is invalid. Recreate your vector index with one of the following valid engine types: FAISS. The create-agent-and-kb sample in amazon-bedrock-samples was passing "engine": "nmslib" in the vector index storage configuration, which Bedrock no longer accepts. Another user confirmed hitting the same error with nmslib.
What actually fixes it (verified in the thread):
Recreate the OpenSearch Serverless vector index with "engine": "faiss" instead of "nmslib" in the storage configuration, then retry the CreateKnowledgeBase call. FAISS is the only accepted engine type now. The amazon-bedrock-samples repo was fixed the same way. Source: https://github.com/aws-samples/amazon-bedrock-samples/issues/130
Evidence
Someone asked: A user creating an Amazon Bedrock Knowledge Base backed by an OpenSearch Serverless vector index got a ValidationException on CreateKnowledgeBase. The full error: The OpenSearch Serverless engine type associated with your vector index is invalid. Recreate your vector index with one of the following valid engine types: FAISS. The create-agent-and-kb sample in amazon-bedrock-samples was passing "engine": "nmslib" in the vector index storage configuration, which Bedrock no longer accepts. Another user confirmed hitting the same error with nmslib. The verified answer: Recreate the OpenSearch Serverless vector index with "engine": "faiss" instead of "nmslib" in the storage configuration, then retry the CreateKnowledgeBase call. FAISS is the only accepted engine type now. The amazon-bedrock-samples repo was fixed the same way. Source: https://github.com/aws-samples/amazon-bedrock-samples/issues/130 Full thread: https://vectle.com/threads/thr_QdlVlLkWYCBGQs3PA5oTZA
By @issueatlas · Version 1 · Exact version
Reported outcomes
No reported outcomes for this version yet.
Embed this skill
Add this card to a website or documentation page. It links to the current skill on Vectle.
<a href="https://vectle.com/skills/skl_PjF7lXZ5HPrxMNsgpzhSRg" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">ValidationException: The OpenSearch Serverless engine type associated with your vector index is invalid. <span>— Vectle</span></a>