Package ai.vectros.types

Class SearchResult.Builder

java.lang.Object

ai.vectros.types.SearchResult.Builder

Enclosing class:

SearchResult

public static final class SearchResult.Builder
extends Object

Method Summary

Modifier and Type	Method	Description
SearchResult.Builder	additionalProperties(Map<String,Object> additionalProperties)
SearchResult.Builder	additionalProperty(String key, Object value)
SearchResult	build()
SearchResult.Builder	chunkText(String chunkText)
SearchResult.Builder	chunkText(Optional<String> chunkText)	The exact text chunk that matched the query.
SearchResult.Builder	contextText(String contextText)
SearchResult.Builder	contextText(Optional<String> contextText)	A broader passage surrounding the matched chunk.
SearchResult.Builder	createdAt(String createdAt)
SearchResult.Builder	createdAt(Optional<String> createdAt)	When the source item was created, as an ISO-8601 UTC timestamp.
SearchResult.Builder	documentId(String documentId)
SearchResult.Builder	documentId(Optional<String> documentId)	The ID of the source document or record this chunk belongs to.
SearchResult.Builder	from(SearchResult other)
SearchResult.Builder	metadata(Map<String,Object> metadata)
SearchResult.Builder	metadata(Optional<Map<String,Object>> metadata)	The metadata you supplied for this item when you ingested it, such as its title, folder ID, and any custom fields you included.
SearchResult.Builder	score(Double score)
SearchResult.Builder	score(Optional<Double> score)	The combined relevance score that fuses the text and semantic signals (reciprocal rank fusion).
SearchResult.Builder	semanticScore(Double semanticScore)
SearchResult.Builder	semanticScore(Optional<Double> semanticScore)	The semantic (vector similarity) component of the score.
SearchResult.Builder	snippet(String snippet)
SearchResult.Builder	snippet(Optional<String> snippet)	A short excerpt with the matched query terms highlighted.
SearchResult.Builder	sourceType(SearchResultSourceType sourceType)
SearchResult.Builder	sourceType(Optional<SearchResultSourceType> sourceType)	Indicates what kind of source item this result came from: PartnerDocument for documents ingested via POST /v1/documents or POST /v1/documents/upload, and GenericRecord for typed records created via POST /v1/records.
SearchResult.Builder	textScore(Double textScore)
SearchResult.Builder	textScore(Optional<Double> textScore)	The keyword (BM25) relevance component of the score.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Method Details

from

public SearchResult.Builder from(SearchResult other)

documentId

public SearchResult.Builder documentId(Optional<String> documentId)

The ID of the source document or record this chunk belongs to. Use it with GET /v1/documents/{id} or GET /v1/records/{id} (depending on sourceType) to retrieve the full item.

documentId

public SearchResult.Builder documentId(String documentId)

score

public SearchResult.Builder score(Optional<Double> score)

The combined relevance score that fuses the text and semantic signals (reciprocal rank fusion). This is the primary sort key — a higher value means a more relevant result.

score

public SearchResult.Builder score(Double score)

textScore

public SearchResult.Builder textScore(Optional<Double> textScore)

The keyword (BM25) relevance component of the score. It is non-zero in HYBRID mode when the keyword engine contributes to the match. It is always 0 in TEXT mode, because that path does not expose per-hit scores — in TEXT mode the order of the results array is the ranking signal, not this field.

textScore

public SearchResult.Builder textScore(Double textScore)

semanticScore

public SearchResult.Builder semanticScore(Optional<Double> semanticScore)

The semantic (vector similarity) component of the score. Non-zero when the search mode is SEMANTIC or HYBRID.

semanticScore

public SearchResult.Builder semanticScore(Double semanticScore)

chunkText

public SearchResult.Builder chunkText(Optional<String> chunkText)

The exact text chunk that matched the query. Pass this to your model as the retrieved context.

chunkText

public SearchResult.Builder chunkText(String chunkText)

contextText

public SearchResult.Builder contextText(Optional<String> contextText)

A broader passage surrounding the matched chunk. Use this instead of chunkText when you need more context — for example to avoid fragmentation when building a long-context prompt for a model.

contextText

public SearchResult.Builder contextText(String contextText)

snippet

public SearchResult.Builder snippet(Optional<String> snippet)

A short excerpt with the matched query terms highlighted. Suitable for display in a search results UI.

snippet

public SearchResult.Builder snippet(String snippet)

sourceType

public SearchResult.Builder sourceType(Optional<SearchResultSourceType> sourceType)

Indicates what kind of source item this result came from: PartnerDocument for documents ingested via POST /v1/documents or POST /v1/documents/upload, and GenericRecord for typed records created via POST /v1/records. Use this to branch when rendering a mix of documents and records from a unified search.

sourceType

public SearchResult.Builder sourceType(SearchResultSourceType sourceType)

metadata

public SearchResult.Builder metadata(Optional<Map<String,Object>> metadata)

The metadata you supplied for this item when you ingested it, such as its title, folder ID, and any custom fields you included.

metadata

public SearchResult.Builder metadata(Map<String,Object> metadata)

createdAt

public SearchResult.Builder createdAt(Optional<String> createdAt)

When the source item was created, as an ISO-8601 UTC timestamp.

createdAt

public SearchResult.Builder createdAt(String createdAt)

build

public SearchResult build()

additionalProperty

public SearchResult.Builder additionalProperty(String key,
 Object value)

additionalProperties

public SearchResult.Builder additionalProperties(Map<String,Object> additionalProperties)