Search

ModelsExpand Collapse

SearchExecuteResponse object { results, timing, total }

results: array of object { chunks, createdAt, documentId, 7 more }

chunks: array of object { content, isRelevant, score }

Matching content chunks from the document

content: string

Content of the matching chunk

isRelevant: boolean

Whether this chunk is relevant to the query

score: number

Similarity score for this chunk

maximum1

minimum0

createdAt: string

Document creation date

formatdatetime

documentId: string

ID of the matching document

metadata: map[unknown]

Document metadata

score: number

Relevance score of the match

maximum1

minimum0

title: string

Document title

type: string

Document type

updatedAt: string

Document last update date

formatdatetime

content: optional string

Full document content (only included when includeFullDocs=true)

summary: optional string

Document summary

timing: number

total: number

SearchDocumentsResponse object { results, timing, total }

results: array of object { chunks, createdAt, documentId, 7 more }

chunks: array of object { content, isRelevant, score }

Matching content chunks from the document

content: string

Content of the matching chunk

isRelevant: boolean

Whether this chunk is relevant to the query

score: number

Similarity score for this chunk

maximum1

minimum0

createdAt: string

Document creation date

formatdatetime

documentId: string

ID of the matching document

metadata: map[unknown]

Document metadata

score: number

Relevance score of the match

maximum1

minimum0

title: string

Document title

type: string

Document type

updatedAt: string

Document last update date

formatdatetime

content: optional string

Full document content (only included when includeFullDocs=true)

summary: optional string

Document summary

timing: number

total: number

SearchMemoriesResponse object { results, timing, total }

results: array of object { id, metadata, similarity, 9 more }

Array of matching memory entries and chunks with similarity scores. Contains memory results when searchMode=‘memories’, both memory and chunk results when searchMode=‘hybrid’, or only chunk results when searchMode=‘documents’. Memory results have ‘memory’ field, chunk results have ‘chunk’ field. BACKWARD COMPATIBILITY: When using deprecated include.chunks=true, only memory results are returned with chunks embedded in them (old format).

id: string

Memory entry ID or chunk ID

metadata: map[unknown]

Memory metadata

similarity: number

Similarity score between the query and memory entry

maximum1

minimum0

updatedAt: string

Memory last update date

formatdatetime

chunk: optional string

The chunk content (only present for chunk results from hybrid search)

chunks: optional array of object { content, documentId, position, score }

Relevant chunks from associated documents (only included when chunks=true)

content: string

Content of the chunk

documentId: string

ID of the document this chunk belongs to

position: number

Position of chunk in the document (0-indexed)

score: number

Similarity score between the query and chunk

maximum1

minimum0

context: optional object { children, parents, related }

Object containing version history (parents/children via updates) and related memories (extends/derives)

children: optional array of object { memory, relation, updatedAt, 2 more }

memory: string

The contextual memory content

relation: "updates" or "extends" or "derives"

Relation type between this memory and its parent/child

One of the following:

"updates"

"extends"

"derives"

updatedAt: string

Contextual memory last update date

formatdatetime

metadata: optional map[unknown]

Contextual memory metadata

version: optional number

Relative version distance from the primary memory (+1 for direct child, +2 for grand-child, etc.)

parents: optional array of object { memory, relation, updatedAt, 2 more }

memory: string

The contextual memory content

relation: "updates" or "extends" or "derives"

Relation type between this memory and its parent/child

One of the following:

"updates"

"extends"

"derives"

updatedAt: string

Contextual memory last update date

formatdatetime

metadata: optional map[unknown]

Contextual memory metadata

version: optional number

Relative version distance from the primary memory (-1 for direct parent, -2 for grand-parent, etc.)

One of the following:

documents: optional array of object { id, createdAt, updatedAt, 4 more }

Associated documents for this memory entry

id: string

Document ID

createdAt: string

Document creation date

formatdatetime

updatedAt: string

Document last update date

formatdatetime

metadata: optional map[unknown]

Document metadata (only included when documents=true)

summary: optional string

Document summary (only included when summaries=true)

title: optional string

Document title (only included when documents=true)

type: optional string

Document type (only included when documents=true)

filepath: optional string

Filepath of the source document this memory or chunk came from

isAggregated: optional boolean

Indicates if this memory was created by aggregating multiple source memories

memory: optional string

The memory content (only present for memory results)

version: optional number

Version number of this memory entry

timing: number

Search execution time in milliseconds

total: number

Total number of results returned

Search

Search documents

Search documents

Search memory entries

ModelsExpand Collapse