Migrate search to v5

​

Migration details

​

Request mapping

POST /v4/search
{"q":"What did the user decide?","containerTag":"user_1","limit":10,"searchMode":"memories"}

POST /ns/user_1/search
{"query":"What did the user decide?","limit":10,"searchMode":"memories","threshold":0.6,"rewriteQuery":false}

​

With the SDK

const memories = await client.search.memories({
  q: "What did the user decide?",
  containerTag: "user_1",
  limit: 10,
})

const docs = await client.search.execute({
  q: "launch plan",
  containerTags: ["user_1"],
})

const memories = await supermemory.search("user_1", {
  query: "What did the user decide?",
  threshold: 0.6,
  rewriteQuery: false,
  searchMode: "memories",
  limit: 10,
})

const chunks = await supermemory.search("user_1", {
  query: "launch plan",
  searchMode: "chunks",
})

const hybrid = await supermemory.search("user_1", {
  query: "launch plan",
})

​

Changed defaults

​

Search modes

​

Included context and ranking

• include.documents adds the most relevant source document to each result.
• include.related adds parent, child, and sibling memories. Related memories come only from the same namespace and must match the request’s filter, so they never surface content the search itself would exclude.
• include.forgotten lets forgotten and expired memories appear in results, including as primary results.
• rerank accepts none, order, or aggregate; rewriteQuery controls retrieval-oriented query rewriting.

​

Response mapping

​

Verification

• Compare IDs using explicit v4-equivalent defaults, then test v5 hybrid behavior separately.
• Cover all three modes, thresholds at 0 and 1, each rerank option, and query rewriting.
• Cover every include alone and in combination, including empty results.
• Verify filters, namespace isolation, result limits, and invalid body/query placement.