Skip to content

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

fix: allow adding RAG source content from valid URLs (#3831)

Lucas Gomide5abf9763735b
diff --git a/lib/crewai-tools/src/crewai_tools/adapters/crewai_rag_adapter.py b/lib/crewai-tools/src/crewai_tools/adapters/crewai_rag_adapter.py
index f23cea85c..9716ca4e9 100644
--- a/lib/crewai-tools/src/crewai_tools/adapters/crewai_rag_adapter.py
+++ b/lib/crewai-tools/src/crewai_tools/adapters/crewai_rag_adapter.py
@@ -229,6 +229,7 @@ class CrewAIRagAdapter(Adapter):
continue
else:
metadata: dict[str, Any] = base_metadata.copy()
+ source_content = SourceContent(source_ref)
if data_type in [
DataType.PDF_FILE,
@@ -239,13 +240,12 @@ class CrewAIRagAdapter(Adapter):
DataType.XML,
DataType.MDX,
]:
- if not os.path.isfile(source_ref):
+ if not source_content.is_url() and not source_content.path_exists():
raise FileNotFoundError(f"File does not exist: {source_ref}")
loader = data_type.get_loader()
chunker = data_type.get_chunker()
- source_content = SourceContent(source_ref)
loader_result: LoaderResult = loader.load(source_content)
chunks = chunker.chunk(loader_result.content)