Package com.tnsai.memory.advanced

package com.tnsai.memory.advanced

Advanced memory module: vector search, BM25 text search, Reciprocal Rank Fusion hybrid retrieval, skill memory, importance scoring, staleness detection, and session persistence.

Related Packages

Package	Description
com.tnsai.memory	Memory management and persistence for agent conversation history.
com.tnsai.memory.strategy	Memory management strategies for conversation history within token budgets.
com.tnsai.memory.vector

Class	Description
BM25Index	BM25 (Okapi BM25) index for text-based memory retrieval.
EmbeddingDimensionMismatchException	Raised when an embedding vector does not match the dimension of its target.
EmbeddingFunction	Functional interface for computing text embeddings.
EmbeddingFunctions	Decorators for composing EmbeddingFunction instances.
HybridMemoryRetriever	Combines BM25 text search and vector semantic search via Reciprocal Rank Fusion.
MemoryImportanceScorer	Computes importance scores for memory entries based on a weighted combination of recency, frequency, and relevance.
ReciprocalRankFusion	Reciprocal Rank Fusion (RRF) for combining multiple ranked result lists.
ScoredEntry	A memory entry paired with a retrieval score.
SessionRestorer	Restores TieredMemoryStore state from a JSON session file.
SessionSerializer	Serializes TieredMemoryStore state to JSON for session persistence.
Skill	A structured skill extracted from agent experience.
SkillMemoryStore	File-based store for structured Markdown skill files.
StalenessDetector	Detects contradictions between memory entries via Jaccard similarity on token sets.
VectorIndex	Storage backend for VectorMemoryStore.
VectorMemoryStore	In-memory vector store for semantic search over memory entries.