RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Go agent-harnessagent-native-databaseagentic-aiagentic-retrievalagentic-searchaiai-agentscontext-enginecontext-engineeringcontext-managementharness-engineeringknowledge-compilationragretrieval-augmented-generationretrieval-harnesssearch-harness
fix(dataflow): preserve scalar text output shape (#18921)
huyua9db74811549a4
diff --git a/rag/svr/task_executor.py b/rag/svr/task_executor.pyindex fbda9b9669..20b2790447 100644--- a/rag/svr/task_executor.py+++ b/rag/svr/task_executor.py@@ -793,6 +793,19 @@ async def embedding(docs, mdl, parser_config=None, callback=None):return tk_count, vector_size+def _normalize_dataflow_output(chunks):+ """Normalize pipeline output into the chunk shape used by indexing."""+ if "chunks" in chunks:+ return copy.deepcopy(chunks["chunks"]), "chunks"+ if "json" in chunks:+ return copy.deepcopy(chunks["json"]), "json"+ for output_type in ("markdown", "text", "html"):+ if output_type in chunks:+ payload = chunks[output_type]+ return ([{"text": payload}] if payload else []), output_type+ return [], "empty"++@timed_with_recordingasync def run_dataflow(task: dict):from api.db.services.canvas_service import UserCanvasService@@ -837,24 +850,7 @@ async def run_dataflow(task: dict):embedding_token_consumption = chunks.get("embedding_token_consumption", 0)# The output key may exist with an empty payload; check presence, not truthiness.- if "chunks" in chunks:- chunks = copy.deepcopy(chunks["chunks"])- output_type = "chunks"- elif "json" in chunks:- chunks = copy.deepcopy(chunks["json"])- output_type = "json"- elif "markdown" in chunks:- chunks = [{"text": [chunks["markdown"]]}] if chunks["markdown"] else []- output_type = "markdown"- elif "text" in chunks:- chunks = [{"text": [chunks["text"]]}] if chunks["text"] else []- output_type = "text"- elif "html" in chunks:- chunks = [{"text": [chunks["html"]]}] if chunks["html"] else []- output_type = "html"- else:- chunks = []- output_type = "empty"+ chunks, output_type = _normalize_dataflow_output(chunks)get_recording_context().record("pipeline_output_type", output_type)get_recording_context().record("pipeline_output_count", len(chunks))diff --git a/test/unit_test/rag/svr/test_task_executor_dataflow_output.py b/test/unit_test/rag/svr/test_task_executor_dataflow_output.pynew file mode 100644index 0000000000..399c116b20--- /dev/null+++ b/test/unit_test/rag/svr/test_task_executor_dataflow_output.py@@ -0,0 +1,29 @@+import ast+from pathlib import Path++import pytest+++def normalize_dataflow_output():+ repo_root = Path(__file__).resolve().parents[4]+ source = (repo_root / "rag" / "svr" / "task_executor.py").read_text(encoding="utf-8")+ tree = ast.parse(source)+ helper = next(node for node in tree.body if isinstance(node, ast.FunctionDef) and node.name == "_normalize_dataflow_output")+ namespace = {"copy": __import__("copy")}+ exec(compile(ast.Module(body=[helper], type_ignores=[]), "task_executor.py", "exec"), namespace)+ return namespace["_normalize_dataflow_output"]++[email protected]("output_type", ["markdown", "text", "html"])+def test_scalar_dataflow_output_keeps_text_as_string(normalize_dataflow_output, output_type):+ chunks, normalized_type = normalize_dataflow_output({output_type: "hello"})++ assert normalized_type == output_type+ assert chunks == [{"text": "hello"}]+ assert isinstance(chunks[0]["text"], str)++[email protected]("output_type", ["markdown", "text", "html"])+def test_empty_scalar_dataflow_output_has_no_chunks(normalize_dataflow_output, output_type):+ assert normalize_dataflow_output({output_type: ""}) == ([], output_type)