Skip to main content
The Knowledge module supports advanced retrieval strategies beyond basic vector similarity search. Combine full-text search (BM25), diversity reranking (MMR), and temporal decay to get better, more diverse, and fresher results.

​
Hybrid Search (Vector + Full-Text)

Hybrid search merges vector similarity results with BM25 full-text search for better recall, especially for keyword-heavy queries. 
from definable.knowledge import Knowledge, FTSIndex, HybridSearchConfig
from definable.vectordb import InMemoryVectorDB

fts = FTSIndex()  # SQLite FTS5-backed
await fts.initialize()

knowledge = Knowledge(
    vector_db=InMemoryVectorDB(),
    fts_index=fts,
    hybrid_config=HybridSearchConfig(
        vector_weight=0.6,   # 60% vector similarity
        text_weight=0.4,     # 40% BM25 text match
    ),
)

# Documents are automatically indexed in both stores
await knowledge.aadd("Python was created by Guido van Rossum in 1991.")
await knowledge.aadd("JavaScript was created by Brendan Eich in 1995.")

# Hybrid search merges both result sets
results = await knowledge.asearch("Who created Python?", top_k=5)

​
HybridSearchConfig

​
vector_weight
float
default:"0.6"
Weight for vector similarity scores in the merged results.
​
text_weight
float
default:"0.4"
Weight for BM25 full-text search scores.
​
merge_strategy
str
default:"rrf"
"rrf" (Reciprocal Rank Fusion) or "weighted" (normalized score combination).
​
rrf_k
int
default:"60"
RRF smoothing constant. Higher values reduce the impact of rank differences.
​
fts_fetch_multiplier
int
default:"3"
Fetch this many times limit from FTS to ensure good coverage before merging.

​
FTSIndex

The full-text search index uses SQLite FTS5 for fast keyword matching. 
from definable.knowledge import FTSIndex

fts = FTSIndex(
    db_path=":memory:",            # Or a file path for persistence
    table_name="fts_documents",    # FTS5 virtual table name
)
await fts.initialize()

# Standalone usage
await fts.add("hash123", documents)
results = await fts.search("Python programming", limit=10)
# Returns: List[Tuple[doc_id, bm25_score, content]]
When used with Knowledge, the FTS index is populated automatically during aadd() — no manual indexing needed.

​
Merge Strategies

RRF (Reciprocal Rank Fusion) — default. Combines rankings from both sources using score = sum(1 / (k + rank)). Works well when score distributions differ between vector and text search. Weighted — normalizes both score sets to [0, 1] then combines: score = vector_weight * vector_score + text_weight * text_score. Best when scores are comparable.

​
MMR (Maximal Marginal Relevance)

MMR reranking balances relevance with diversity. It prevents returning near-duplicate results by penalizing documents that are too similar to already-selected ones. 
from definable.knowledge import Knowledge, MMRConfig

knowledge = Knowledge(
    vector_db=InMemoryVectorDB(),
    mmr=MMRConfig(
        lambda_param=0.7,  # 70% relevance, 30% diversity
    ),
)
​
lambda_param
float
default:"0.5"
Balance between relevance (1.0 = pure relevance) and diversity (0.0 = maximum diversity).
​
enabled
bool
default:"true"
Whether MMR reranking is active.
The MMR algorithm uses greedy iterative selection:
  1. Compute relevance score for each document (cosine similarity to query embedding, or Jaccard text similarity as fallback)
  2. For each selection step: MMR = lambda * relevance - (1 - lambda) * max_similarity_to_selected
  3. Select the document with the highest MMR score
MMR works best with embeddings. If documents lack embeddings, it falls back to Jaccard text similarity, which is less accurate but still provides diversity.

​
Temporal Decay

Score documents lower as they age. Useful for news, social media, and other time-sensitive content. 
from definable.knowledge import Knowledge, TemporalDecay

knowledge = Knowledge(
    vector_db=InMemoryVectorDB(),
    temporal_decay=TemporalDecay(
        half_life_days=30.0,  # Score halves every 30 days
    ),
)
​
half_life_days
float
default:"30.0"
Number of days until a document’s score is halved. Smaller values = faster decay.
​
enabled
bool
default:"true"
Whether temporal decay is active.

​
Timestamps

Temporal decay reads timestamps from document metadata: 
from definable.knowledge import Document
import time

doc = Document(
    content="Breaking news: ...",
    meta_data={
        "inserted_at": time.time(),  # Primary timestamp
        # or "created_at": time.time()  # Fallback
    },
)

​
Evergreen Documents

Mark documents as evergreen to exempt them from decay: 
doc = Document(
    content="Company mission statement",
    meta_data={"evergreen": True},
)

​
Combining Strategies

All scoring strategies compose. The search pipeline applies them in order: 
Vector Search → Hybrid Merge → Reranker → Temporal Decay → MMR

from definable.knowledge import (
    Knowledge, FTSIndex, HybridSearchConfig,
    TemporalDecay, MMRConfig,
)
from definable.knowledge.reranker import CohereReranker
from definable.vectordb import InMemoryVectorDB

fts = FTSIndex()
await fts.initialize()

knowledge = Knowledge(
    vector_db=InMemoryVectorDB(),
    reranker=CohereReranker(),
    fts_index=fts,
    hybrid_config=HybridSearchConfig(vector_weight=0.6, text_weight=0.4),
    temporal_decay=TemporalDecay(half_life_days=14.0),
    mmr=MMRConfig(lambda_param=0.7),
    top_k=10,
)

# Full pipeline: vector → hybrid merge → rerank → decay → diversity
results = await knowledge.asearch("latest AI developments")

​
Fallback Embedder

Automatically fail over across multiple embedding providers: 
from definable.knowledge import FallbackEmbedder
from definable.embedder import OpenAIEmbedder, VoyageAIEmbedder

embedder = FallbackEmbedder(providers=[
    OpenAIEmbedder(),       # Primary
    VoyageAIEmbedder(),     # Fallback
])

knowledge = Knowledge(
    vector_db=InMemoryVectorDB(),
    embedder=embedder,
)
The fallback embedder:
  • Tries providers in order (primary first)
  • Automatically classifies errors (auth, rate limit, timeout, network)
  • Switches to the next provider on failure
  • Call embedder.reset() to return to the primary provider

​
Imports

# Hybrid search
from definable.knowledge import FTSIndex, HybridSearchConfig

# Scoring
from definable.knowledge import TemporalDecay, MMRConfig

# Fallback embedder
from definable.knowledge import FallbackEmbedder