{
    "componentChunkName": "component---src-templates-feature-v-3-js",
    "path": "/dynamodb-semantic-search/",
    "result": {"pageContext":{"slug":"dynamodb-semantic-search","name":"Semantic and vector search","category":"Explore data","headline":"Find items by meaning.","description":"Search an existing DynamoDB vector index with text, a pasted embedding, or an item already in your table. Inspect ranked matches without leaving Dynobase.","image":"semantic","caption":"Semantic search results with distance scores, usage and item inspection controls.","sections":[{"title":"Three ways to search","body":"Generate a query embedding with Amazon Bedrock Titan, paste a compatible vector from another model, or choose Find similar on an item that already has an embedding."},{"title":"Understand each match","body":"See the index's distance score, inspect projected attributes, and select two results for a visual diff. Query usage and elapsed time appear alongside the results."},{"title":"Keep the right scope","body":"Select the index and its required partition value. Add exact-match filters for supported attributes in the index's search schema before running the search."}],"start":"Open Dynobase and follow these steps to use semantic and vector search.","steps":[{"title":"Choose an index","body":"Open a table, select Schema, then Semantic search. Choose an active vector index and review its dimensions and distance function."},{"title":"Prepare your query","body":"Enter text and choose the same embedding model and settings used by your indexed data, or paste a vector with matching dimensions."},{"title":"Search and inspect","body":"Set the number of matches, add any required partition value, and click Search. Inspect a result or compare two matches."}],"note":"A populated, active native DynamoDB vector index is required on an on-demand table. Dynobase does not create vector indexes or backfill embeddings. Your role needs DescribeTable and SearchVectors access; text search also needs Bedrock InvokeModel access. AWS usage charges apply.","faq":[{"question":"Does this search any table using natural language?","answer":"It searches compatible vector indexes. It does not translate arbitrary questions into DynamoDB queries or scan a table as a fallback. Text search embeds your query; it does not send table items to Bedrock."},{"question":"What happens if my IAM role does not have access?","answer":"Dynobase identifies the failed operation and offers a copyable access request for your administrator. Pasting a compatible embedding avoids a Bedrock call, but every mode still requires DynamoDB access."},{"question":"Are the scores confidence percentages?","answer":"No. They are distance-function scores. Smaller cosine or Euclidean distances rank first; larger dot-product scores rank first. Matching embedding dimensions alone does not guarantee that two models are compatible."}],"related":["dynamodb-item-diff","dynamodb-schema-explorer","dynamodb-json-path-filtering"],"reference":{"label":"AWS vector index setup guide","url":"https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/VectorSearchWorkingWith.html"}}},
    "staticQueryHashes": ["3649515864"]}