fischer-agentkit/tests/unit/rag_platform
chiguyong 5c562dbff3 feat(rag_platform): U5 — rerank + question generation + termbase
Add rerank.py: Reranker with Cohere/BGE provider support, data export risk annotation, graceful degradation
Add question_gen.py: LLM-based question generation following ContextualChunker pattern, with caching
Add termbase.py: jieba custom dictionary management, add/remove/load terms

Tests: 58 new tests (14 rerank + 19 question_gen + 25 termbase), 205 total passing
2026-06-25 12:31:43 +08:00
..
__init__.py feat(rag_platform): U1 — RAG platform skeleton + LlamaIndex integration 2026-06-25 10:49:35 +08:00
test_acl.py feat(rag_platform): U2 — KB persistence + per-KB ACL 2026-06-25 11:01:04 +08:00
test_document_processor.py feat(rag_platform): U3+U7 — document processing pipeline + upload security 2026-06-25 11:21:42 +08:00
test_fulltext.py feat(rag_platform): U4 — dual-index retrieval (pgvector semantic + PG fulltext jieba) 2026-06-25 12:20:48 +08:00
test_pipeline.py feat(rag_platform): U1 — RAG platform skeleton + LlamaIndex integration 2026-06-25 10:49:35 +08:00
test_question_gen.py feat(rag_platform): U5 — rerank + question generation + termbase 2026-06-25 12:31:43 +08:00
test_rerank.py feat(rag_platform): U5 — rerank + question generation + termbase 2026-06-25 12:31:43 +08:00
test_retrieval.py feat(rag_platform): U4 — dual-index retrieval (pgvector semantic + PG fulltext jieba) 2026-06-25 12:20:48 +08:00
test_sanitize.py feat(rag_platform): U3+U7 — document processing pipeline + upload security 2026-06-25 11:21:42 +08:00
test_store.py feat(rag_platform): U2 — KB persistence + per-KB ACL 2026-06-25 11:01:04 +08:00
test_termbase.py feat(rag_platform): U5 — rerank + question generation + termbase 2026-06-25 12:31:43 +08:00