d8fd067a8c
3.1: Sentence-aware chunk splitting at ". ", "? ", "! " boundaries when paragraphs exceed ChunkConfig.Size. Overlap now aligns to word boundaries to avoid mid-word splits. 3.2: VectorStore interface gains ListCollections and CollectionInfo methods. New collections.go with ListCollections, DeleteCollection, CollectionStats helpers returning backend-agnostic CollectionInfo. Mock updated accordingly. 3.3: KeywordFilter re-ranks QueryResults by boosting scores for keyword matches (case-insensitive, +10% per keyword). QueryConfig.Keywords flag enables automatic extraction and filtering. 3.4: Mock-only benchmarks for chunking, query, ingest, formatting, and keyword filtering. Co-Authored-By: Virgil <virgil@lethean.io>
40 lines
1.6 KiB
Go
40 lines
1.6 KiB
Go
package rag
|
|
|
|
import "context"
|
|
|
|
// VectorStore defines the interface for vector storage and search.
|
|
// QdrantClient satisfies this interface.
|
|
type VectorStore interface {
|
|
// CreateCollection creates a new vector collection with the given
|
|
// name and vector dimensionality.
|
|
CreateCollection(ctx context.Context, name string, vectorSize uint64) error
|
|
|
|
// CollectionExists checks whether a collection with the given name exists.
|
|
CollectionExists(ctx context.Context, name string) (bool, error)
|
|
|
|
// DeleteCollection deletes the collection with the given name.
|
|
DeleteCollection(ctx context.Context, name string) error
|
|
|
|
// ListCollections returns all collection names in the store.
|
|
ListCollections(ctx context.Context) ([]string, error)
|
|
|
|
// CollectionInfo returns metadata about a collection. Implementations
|
|
// should populate at least PointCount and VectorSize in the returned
|
|
// CollectionInfo struct.
|
|
CollectionInfo(ctx context.Context, name string) (*CollectionInfo, error)
|
|
|
|
// UpsertPoints inserts or updates points in the named collection.
|
|
UpsertPoints(ctx context.Context, collection string, points []Point) error
|
|
|
|
// Search performs a vector similarity search, returning up to limit results.
|
|
// An optional filter map restricts results by payload field values.
|
|
Search(ctx context.Context, collection string, vector []float32, limit uint64, filter map[string]string) ([]SearchResult, error)
|
|
}
|
|
|
|
// CollectionInfo holds backend-agnostic metadata about a collection.
|
|
type CollectionInfo struct {
|
|
Name string
|
|
PointCount uint64
|
|
VectorSize uint64
|
|
Status string // e.g. "green", "yellow", "red", "unknown"
|
|
}
|