Skip to main content
Complete parameter reference for all three search endpoints: document search, memory search, and execute search.

​
Common Parameters

These parameters work across all search endpoints:
​
q
string
required
Search query stringThe text you want to search for. Can be natural language, keywords, or questions.
q: "machine learning neural networks"
q: "What are the applications of quantum computing?"
q: "python tutorial beginner"
​
limit
number
default:"10"
Maximum number of results to returnControls how many results you get back. Higher limits increase response time and size.
limit: 5    // Fast, focused results
limit: 20   // Comprehensive results
limit: 100  // Maximum recommended
​
containerTags
Array<string>
Filter by container tagsOrganizational tags for filtering results. Uses exact array matching - must match all tags in the same order.
containerTags: ["user_123"]                    // Single tag
containerTags: ["user_123", "project_ai"]      // Multiple tags (exact match)
​
filters
string
Metadata filtering with SQL-like structureJSON string containing AND/OR logic for filtering by metadata fields. Uses the same structure as memory listing filters.
filters: JSON.stringify({
  AND: [
    { key: "category", value: "tutorial", negate: false },
    { key: "difficulty", value: "beginner", negate: false }
  ]
})
See Metadata Filtering Guide for complete syntax and examples.
​
rerank
boolean
default:"false"
Re-score results for better relevanceApplies a secondary ranking algorithm to improve result quality. Adds ~100-200ms latency but increases accuracy.
rerank: true   // Better accuracy, slower
rerank: false  // Faster, standard accuracy
​
rewriteQuery
boolean
default:"false"
Expand and improve the queryRewrites your query to find more relevant results. Particularly useful for abbreviations and domain-specific terms. Adds ~400ms latency.
// Query rewriting examples:
"ML" → "machine learning artificial intelligence"
"JS" → "JavaScript programming language"
"API" → "application programming interface REST"
Query rewriting significantly increases latency. Only use when search quality is more important than speed.

​
Document Search Parameters (POST /v3/search)

These parameters are specific to client.search.documents():
​
chunkThreshold
number
default:"0.5"
Sensitivity for chunk selectionControls which text chunks are included in results:
  • 0.0 = Least sensitive (more chunks, more results)
  • 1.0 = Most sensitive (fewer chunks, higher quality)
chunkThreshold: 0.2   // Broad search, many chunks
chunkThreshold: 0.8   // Precise search, only relevant chunks
​
documentThreshold
number
default:"0.5"
Sensitivity for document selectionControls which documents are considered for search:
  • 0.0 = Search more documents (comprehensive)
  • 1.0 = Search only highly relevant documents (focused)
documentThreshold: 0.1   // Cast wide net
documentThreshold: 0.9   // Only very relevant documents
​
docId
string
Search within a specific documentLimit search to chunks within a single document. Useful for finding content in large documents.
docId: "doc_abc123"  // Only search this document
​
onlyMatchingChunks
boolean
default:"false"
Return only exact matching chunksBy default, Supermemory includes surrounding chunks for context. Set to true to get only the exact matching text.
onlyMatchingChunks: false  // Include context chunks (default)
onlyMatchingChunks: true   // Only matching chunks
Context chunks help LLMs understand the full meaning. Only disable if you need precise text extraction.
​
includeFullDocs
boolean
default:"false"
Include complete document contentAdds the full document text to each result. Useful for chatbots that need complete context.
includeFullDocs: true   // Full document in response
includeFullDocs: false  // Only chunks and metadata
Including full documents can make responses very large. Use sparingly and with appropriate limits.
​
includeSummary
boolean
default:"false"
Include document summariesAdds AI-generated document summaries to results. Good middle-ground between chunks and full documents.
includeSummary: true   // Include document summaries
includeSummary: false  // No summaries
​
filters
string
Filter by metadata using SQL queries

// Use this instead:
filters: JSON.stringify({
  OR: [
    { key: "category", value: "technology", negate: false },
    { key: "category", value: "science", negate: false }
  ]
})

​
Memory Search Parameters (POST /v4/search)

These parameters are specific to client.search.memories():
​
threshold
number
default:"0.5"
Sensitivity for memory selectionControls which memories are returned based on similarity:
  • 0.0 = Return more memories (broad search)
  • 1.0 = Return only highly similar memories (precise search)
threshold: 0.3   // Broader memory search
threshold: 0.8   // Only very similar memories
​
searchMode
string
default:"memories"
Search mode - memories only or hybrid searchControls whether to search only memories or also include document chunks:
  • "memories" (default): Searches only memory entries. Returns results with memory field.
  • "hybrid": Searches memories first, then falls back to document chunks if needed. Returns mixed results with either memory field (for memory results) or chunk field (for chunk results).
In hybrid mode, results are automatically merged and deduplicated. Results contain objects with either a memory key (for memory results) or a chunk key (for chunk results from document search).
searchMode: "memories"  // Only search memories (default)
searchMode: "hybrid"    // Search memories + fallback to chunks
When to use hybrid mode:
  • When you want comprehensive search across both memories and documents
  • When memories might not exist for certain queries but document content is available
  • When you need the flexibility to get either memory or document chunk results
​
containerTag
string
Filter by single container tagNote: Memory search uses containerTag (singular) while document search uses containerTags (plural array).
containerTag: "user_123"  // Single tag for memory search
​
include
object
Control what additional data to includeObject specifying what contextual information to include with memory results.
​
include.documents
boolean
default:"false"
Include associated documents for each memory
​
include.relatedMemories
boolean
default:"false"
Include parent and child memories (contextual relationships)
​
include.summaries
boolean
default:"false"
Include memory summaries
include: {
  documents: true,        // Show related documents
  relatedMemories: true,  // Show parent/child memories
  summaries: true         // Include summaries
}