Skip to content

v0.9.0 — Hybrid & Advanced Retrieval

Choose a tag to compare

View all tags
@Rushour0 Rushour0 released this 04 Jul 14:59
v0.9.0
508fd56

Hybrid & Advanced Retrieval — BM25+Vector fusion, temporal decay, MMR, domain routing

This release introduces a fully configurable, multi-strategy retrieval pipeline for fabri's memory system. All changes are backward-compatible — existing configs and databases work without modification.

Retrieval strategies

Controlled by memory.retrieval_strategy:

Strategy Description
dense Original cosine vector similarity (default, unchanged)
sparse BM25-only via SQLite FTS5 (built-in) or rank_bm25 for Qdrant
hybrid RRF fusion of dense + sparse
hybrid+mmr Hybrid + Maximal Marginal Relevance diversification

Reciprocal Rank Fusion (RRF) — entries appearing in both dense and sparse results get double credit. MMR — diversifies the final pool by balancing relevance vs redundancy (memory.mmr_lambda, default 0.7).

Scoring pipeline (all opt-in)

  • Temporal decay (memory.temporal_decay: true) — score *= exp(-ln(2) * age_days / half_life_days). Default half-life: 30 days.
  • Importance boost (memory.importance_weight: 0.2) — min(1, hit_count/10 + 0.3 if strategic).
  • Domain routing (memory.domain_routing: true) — zero-latency keyword heuristic; matching entries get a 1.15× boost, never hard-filters.

SQLite FTS5 index (zero extra install)

FTS5 is Python built-in. Porter tokenizer. Synced on every upsert/delete. Auto-migration: existing DBs are bulk-populated from guidelines on first upgrade — no manual step needed.

Memory schema enrichment

MemoryEntry gains four new optional fields (all default-safe for old payloads): domain, outcome, agent_id, task_embedding_hash. Deterministic ID hash unchanged — no DB migration needed.

New config keys (all default to pre-v0.9.0 behavior)

memory:
  retrieval_strategy: dense        # dense | sparse | hybrid | hybrid+mmr
  temporal_decay: false
  temporal_half_life_days: 30.0
  mmr_lambda: 0.7
  domain_routing: false
  importance_weight: 0.2
  query_expansion: false           # reserved

Optional dependency

pip install 'fabri[bm25]'   # client-side BM25 for Qdrant hybrid retrieval

SQLite users get full hybrid retrieval with zero extra installs.

Bug fix

agent_runner_tool.py hardcoded QdrantMemoryStore; now uses build_memory_store(mem_cfg) so SQLite users get hybrid retrieval in sub-agent runs too.

Quick start

# agent.yaml
memory:
  backend: sqlite
  retrieval_strategy: hybrid+mmr
  temporal_decay: true
  domain_routing: true
Assets 2
Loading