mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-04-30 19:06:21 +02:00
bcd7a1694a
The extract-with-ontologies prompt is a JSONL prompt, which means the prompt service returns a PromptResult with response_type="jsonl" and the parsed items in `.objects` (plural). The ontology extractor was reading `.object` (singular) — the field used for response_type="json" — which is always None for JSONL prompts. Effect: the parser received None on every chunk, hit its "Unexpected response type: <class 'NoneType'>" branch, returned no ExtractionResult, and extract_with_simplified_format returned []. Every extraction silently produced zero triples. Graphs populated only with the seed ontology schema (TBox) and document/chunk provenance — no instance triples at all. The e2e test threshold of >=100 edges per collection was met by schema + provenance alone, so the failure mode was invisible until RAG queries couldn't find any content. Regression introduced in v2.3 with the token-usage work (commit |
||
|---|---|---|
| .. | ||
| test_agent | ||
| test_base | ||
| test_chunking | ||
| test_cli | ||
| test_clients | ||
| test_concurrency | ||
| test_config | ||
| test_cores | ||
| test_decoding | ||
| test_direct | ||
| test_embeddings | ||
| test_extract | ||
| test_gateway | ||
| test_knowledge_graph | ||
| test_librarian | ||
| test_provenance | ||
| test_pubsub | ||
| test_query | ||
| test_rdf | ||
| test_reliability | ||
| test_retrieval | ||
| test_rev_gateway | ||
| test_storage | ||
| test_structured_data | ||
| test_tables | ||
| test_text_completion | ||
| test_translators | ||
| __init__.py | ||
| test_prompt_manager.py | ||
| test_prompt_manager_edge_cases.py | ||
| test_python_api_client.py | ||