fix: Relax SearchResult validation to support DBSF fusion scores > 1.0

Fix false-positive validation error where DBSF (Distribution-Based Score
Fusion) correctly produces scores > 1.0 but SearchResult validation
incorrectly rejected them.

**Root Cause**: SearchResult.__post_init__() enforced scores in [0.0, 1.0]
range, but DBSF sums normalized scores from multiple retrieval systems
(dense semantic + sparse BM25), resulting in scores like 1.55 when both
systems strongly agree a document is relevant.

**Changes**:
- Relaxed validation to allow any score ≥ 0.0 (algorithms.py:147-157)
- Updated SearchResult and SemanticSearchResult documentation to explain
  score ranges for RRF ([0.0, 1.0]) vs DBSF (unbounded)
- Added comprehensive test coverage for both fusion methods
- Added DBSF fusion option to vector visualization UI
- Updated viz routes and vizApp() to support fusion parameter selection

**Testing**: All 157 unit tests pass, type checking passes, ruff passes

Fixes error: "Configuration error: Score must be between 0.0 and 1.0, got 1.1528953"

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Chris Coutinho
2025-11-17 06:32:30 +01:00
co-authored by Claude
parent ea01ce7673
commit 3464b21845
8 changed files with 709 additions and 264 deletions
@@ -677,12 +677,15 @@ async def user_info_html(request: Request) -> HTMLResponse:
return {{
query: '',
algorithm: 'bm25_hybrid',
fusion: 'rrf', // Default fusion method for BM25 Hybrid
showAdvanced: false,
docTypes: [''], // Default to "All Types"
limit: 50,
scoreThreshold: 0.0,
loading: false,
results: [],
expandedChunks: {{}}, // Track which chunks are expanded (result_id -> chunk data)
chunkLoading: {{}}, // Track loading state per result
async executeSearch() {{
this.loading = true;
@@ -696,6 +699,11 @@ async def user_info_html(request: Request) -> HTMLResponse:
score_threshold: this.scoreThreshold,
}});
// Add fusion parameter for BM25 Hybrid
if (this.algorithm === 'bm25_hybrid') {{
params.append('fusion', this.fusion);
}}
// Add doc_types parameter (filter out empty string for "All Types")
const selectedTypes = this.docTypes.filter(t => t !== '');
if (selectedTypes.length > 0) {{
@@ -778,6 +786,51 @@ async def user_info_html(request: Request) -> HTMLResponse:
default:
return `${{baseUrl}}`;
}}
}},
hasChunkPosition(result) {{
// Check if result has position metadata
return result.chunk_start_offset != null && result.chunk_end_offset != null;
}},
isChunkExpanded(resultKey) {{
return this.expandedChunks[resultKey] !== undefined;
}},
async toggleChunk(result) {{
const resultKey = `${{result.doc_type}}_${{result.id}}`;
// If already expanded, collapse
if (this.isChunkExpanded(resultKey)) {{
delete this.expandedChunks[resultKey];
return;
}}
// Otherwise, fetch and expand
this.chunkLoading[resultKey] = true;
try {{
const params = new URLSearchParams({{
doc_type: result.doc_type,
doc_id: result.id,
start: result.chunk_start_offset,
end: result.chunk_end_offset,
context: 500 // 500 chars before/after
}});
const response = await fetch(`/app/chunk-context?${{params}}`);
const data = await response.json();
if (data.success) {{
this.expandedChunks[resultKey] = data;
}} else {{
alert('Failed to load chunk: ' + data.error);
}}
}} catch (error) {{
alert('Error loading chunk: ' + error.message);
}} finally {{
delete this.chunkLoading[resultKey];
}}
}}
}}
}}