refactor(rag/nlp): standardize knowledge graph retrieval to use DocumentChunk and add debug logging
The knowledge graph retrieval logic in `search.py` was updated to consistently return `DocumentChunk` instances instead of raw dictionaries, improving type safety and alignment with the RAG pipeline's expected data structure. Additionally, debug logging was enhanced in `draft_run_service.py` to log the full `retrieve_chunks_result` before extracting page content, aiding troubleshooting.
This commit is contained in:
@@ -133,7 +133,10 @@ def knowledge_retrieval(
|
||||
from app.core.rag.common.settings import kg_retriever
|
||||
doc = kg_retriever.retrieval(question=query, workspace_ids=workspace_ids, kb_ids=kb_ids, emb_mdl=embedding_model, llm=chat_model)
|
||||
if doc:
|
||||
all_results.insert(0, doc)
|
||||
all_results.insert(0, DocumentChunk(
|
||||
page_content=doc.get("page_content", ""),
|
||||
metadata=doc.get("metadata", {})
|
||||
))
|
||||
except Exception as graph_error:
|
||||
print(f"Failed to retrieve from knowledge graph: {str(graph_error)}")
|
||||
|
||||
@@ -262,7 +265,10 @@ def _retrieve_for_knowledge(
|
||||
llm=chat_model,
|
||||
)
|
||||
if graph_doc:
|
||||
rs.insert(0, graph_doc)
|
||||
rs.insert(0, DocumentChunk(
|
||||
page_content=graph_doc.get("page_content", ""),
|
||||
metadata=graph_doc.get("metadata", {})
|
||||
))
|
||||
except Exception as graph_error:
|
||||
logger.warning(f"Graph retrieval failed for kb {db_knowledge.id}: {graph_error}")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user