Module search 

Search engine with keyword, semantic, and hybrid retrieval modes.

This module provides the application-level entry points for search. The core algorithm (normalization, hybrid merge, aggregation) lives in context-harness-core::search and operates through the [Store] trait. This wrapper handles config parsing, database connection, embedding, and CLI output formatting.

Search Modes

• Keyword — FTS5 full-text search using BM25 scoring.
• Semantic — Cosine similarity over stored embedding vectors.
• Hybrid — Weighted merge of keyword and semantic results.

Structs

ChunkCandidate

A candidate chunk returned from keyword or vector search.

ScoreExplanation

Scoring breakdown for a search result.

SearchParams

Retrieval tuning parameters, decoupled from application config.

SearchRequest

Bundles all inputs for a single search invocation.

SearchResultItem

A search result matching the SCHEMAS.md context.search response shape.

Functions

normalize_scores

Min-max normalize raw scores to [0.0, 1.0].

run_search

CLI entry point — calls search_documents and prints results to stdout.

search_documents

Core search function returning structured results.