module

Memo::Storage

Low-level storage operations for embeddings and chunks

Instance methods

compute_hash(text : String) : Bytes

Compute SHA256 hash for text content

create_chunk(db : DB::Database, hash : Bytes, source_type : String, source_id : Int64, offset : Int32 | Nil, size : Int32, pair_id : Int64 | Nil = nil, parent_id : Int64 | Nil = nil) : Int64

Create chunk reference (or ignore if already exists)

Returns chunk id if inserted, or 0 if chunk already existed (was ignored)

deserialize_embedding(blob : Bytes) : Array(Float64)

Deserialize embedding from binary blob

get_rowid(db : DB::Database, hash : Bytes, service_id : Int64) : Int64 | Nil

Get the rowid of an embedding by hash and service_id.

get_service_by_format_model(db : DB::Database, format : String, model : String) : Tuple(Int64, String, String | Nil, String, Int32, Int32, Float64) | Nil

Returns service record by format and model, or nil if not found

get_service_by_name(db : DB::Database, name : String) : Tuple(Int64, String, String | Nil, String, Int32, Int32, Float64) | Nil

Get service by name

increment_match_count(db : DB::Database, chunk_ids : Array(Int64))

Increment match_count for chunks

increment_read_count(db : DB::Database, chunk_ids : Array(Int64))

Increment read_count for chunks

register_service(db : DB::Database, name : String | Nil, format : String, base_url : String | Nil, model : String, dimensions : Int32, max_tokens : Int32) : Int64

serialize_embedding(embedding : Array(Float64)) : Bytes

Serialize embedding to binary blob (Int16 for 50% storage reduction)

store_embedding(db : DB::Database, hash : Bytes, token_count : Int32, service_id : Int64) : Tuple(Bool, Int64)

Returns {inserted, rowid} where inserted is true if new, rowid is the USearch key.

update_tokens_per_byte(db : DB::Database, service_id : Int64, observed_ratio : Float64)

Update tokens_per_byte ratio using exponential moving average