BobAi
4166d0a362
🎯 Complete transformation from 5.9GB bloated system to 70MB optimized solution ✨ Key Features: - Hybrid embedding system (Ollama + ML fallback + hash backup) - Intelligent chunking with language-aware parsing - Semantic + BM25 hybrid search with rich context - Zero-config portable design with graceful degradation - Beautiful TUI for beginners + powerful CLI for experts - Comprehensive documentation with 8+ Mermaid diagrams - Professional animated demo (183KB optimized GIF) 🏗️ Architecture Highlights: - LanceDB vector storage with streaming indexing - Smart file tracking (size/mtime) to avoid expensive rehashing - Progressive chunking: Markdown headers → Python functions → fixed-size - Quality filtering: 200+ chars, 20+ words, 30% alphanumeric content - Concurrent batch processing with error recovery 📦 Package Contents: - Core engine: claude_rag/ (11 modules, 2,847 lines) - Entry points: rag-mini (unified), rag-tui (beginner interface) - Documentation: README + 6 guides with visual diagrams - Assets: 3D icon, optimized demo GIF, recording tools - Tests: 8 comprehensive integration and validation tests - Examples: Usage patterns, config templates, dependency analysis 🎥 Demo System: - Scripted demonstration showing 12 files → 58 chunks indexing - Semantic search with multi-line result previews - Complete workflow from TUI startup to CLI mastery - Professional recording pipeline with asciinema + GIF conversion 🛡️ Security & Quality: - Complete .gitignore with personal data protection - Dependency optimization (removed python-dotenv) - Code quality validation and educational test suite - Agent-reviewed architecture and documentation Ready for production use - copy folder, run ./rag-mini, start searching\!
75 lines
3.3 KiB
Python
75 lines
3.3 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Test script for adjacent chunk retrieval functionality.
|
|
"""
|
|
|
|
from pathlib import Path
|
|
from claude_rag.search import CodeSearcher
|
|
from claude_rag.embeddings import CodeEmbedder
|
|
|
|
def test_context_retrieval():
|
|
"""Test the new context retrieval functionality."""
|
|
|
|
# Initialize searcher
|
|
project_path = Path(__file__).parent
|
|
try:
|
|
embedder = CodeEmbedder()
|
|
searcher = CodeSearcher(project_path, embedder)
|
|
|
|
print("Testing search with context...")
|
|
|
|
# Test 1: Search without context
|
|
print("\n1. Search WITHOUT context:")
|
|
results = searcher.search("chunk metadata", limit=3, include_context=False)
|
|
for i, result in enumerate(results, 1):
|
|
print(f" Result {i}: {result.file_path}:{result.start_line}-{result.end_line}")
|
|
print(f" Type: {result.chunk_type}, Name: {result.name}")
|
|
print(f" Has context_before: {result.context_before is not None}")
|
|
print(f" Has context_after: {result.context_after is not None}")
|
|
print(f" Has parent_chunk: {result.parent_chunk is not None}")
|
|
|
|
# Test 2: Search with context
|
|
print("\n2. Search WITH context:")
|
|
results = searcher.search("chunk metadata", limit=3, include_context=True)
|
|
for i, result in enumerate(results, 1):
|
|
print(f" Result {i}: {result.file_path}:{result.start_line}-{result.end_line}")
|
|
print(f" Type: {result.chunk_type}, Name: {result.name}")
|
|
print(f" Has context_before: {result.context_before is not None}")
|
|
print(f" Has context_after: {result.context_after is not None}")
|
|
print(f" Has parent_chunk: {result.parent_chunk is not None}")
|
|
|
|
if result.context_before:
|
|
print(f" Context before preview: {result.context_before[:50]}...")
|
|
if result.context_after:
|
|
print(f" Context after preview: {result.context_after[:50]}...")
|
|
if result.parent_chunk:
|
|
print(f" Parent chunk: {result.parent_chunk.name} ({result.parent_chunk.chunk_type})")
|
|
|
|
# Test 3: get_chunk_context method
|
|
print("\n3. Testing get_chunk_context method:")
|
|
# Get a sample chunk_id from the first result
|
|
df = searcher.table.to_pandas()
|
|
if not df.empty:
|
|
sample_chunk_id = df.iloc[0]['chunk_id']
|
|
print(f" Getting context for chunk_id: {sample_chunk_id}")
|
|
|
|
context = searcher.get_chunk_context(sample_chunk_id)
|
|
|
|
if context['chunk']:
|
|
print(f" Main chunk: {context['chunk'].file_path}:{context['chunk'].start_line}")
|
|
if context['prev']:
|
|
print(f" Previous chunk: lines {context['prev'].start_line}-{context['prev'].end_line}")
|
|
if context['next']:
|
|
print(f" Next chunk: lines {context['next'].start_line}-{context['next'].end_line}")
|
|
if context['parent']:
|
|
print(f" Parent chunk: {context['parent'].name} ({context['parent'].chunk_type})")
|
|
|
|
print("\nAll tests completed successfully!")
|
|
|
|
except Exception as e:
|
|
print(f"Error during testing: {e}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
|
|
if __name__ == "__main__":
|
|
test_context_retrieval() |