Generated: 2025-12-11 14:58:20
Total: 29
Passed: 29
Failed: 0
Skipped: 0
Duration: 90.37s
| Status | Test Name | Message |
|---|---|---|
| PASS | sentence-transformers import | |
| PASS | Re-ranking functions import | |
| PASS | Cross-encoder model loaded | |
| PASS | Re-ranking accuracy | C3 (1.000) > C2 (0.000) |
| PASS | Hybrid search with re-ranking | Found 5 results |
| PASS | GraphRAG functions import | |
| PASS | Concepts table populated | Count: 35 |
| PASS | Fuzzy concept lookup | Found: Masonry |
| PASS | Related concepts traversal | Found 56 related concepts |
| PASS | GraphRAG search | Concepts: 5, Paths: 38, Results: 5 |
| PASS | Chunk context retrieval | Context returned |
| PASS | SentenceTransformer import | |
| PASS | SemanticChunker import | |
| PASS | SemanticChunker initialization | |
| PASS | Embedding model loaded | all-MiniLM-L6-v2 |
| PASS | Semantic boundary detection | No boundaries (text may be too uniform) |
| PASS | Semantic chunking | Created 1 chunks |
| PASS | Semantic chunk metadata | chunk_method='semantic' |
| PASS | Research agent import | |
| PASS | LLM interface initialized | Mode: cloud, Model: gpt-4o |
| PASS | Research agent initialization | |
| PASS | Query planning | Generated 5 sub-queries |
| PASS | Agent search execution | Found 10 results |
| PASS | Full research session | Iterations: 2, Chunks: 15 |
| PASS | Report generation | Length: 4660 chars |
| PASS | Keyword search baseline | Found 0 results |
| PASS | GraphRAG multi-hop | Chunks: 0 (no paths found) |
| PASS | Re-ranking changes order | Top-3 results differ |
| PASS | Precision query test | Top result score: 0.0013990899315103889 |