Fix: PDFKnowledgeSource instantiation error (Issue #2619)

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -64,6 +64,16 @@ def _save_documents(self):
         """Save the documents to the storage."""
         self.storage.save(self.chunks)
 
+    def add(self) -> None:
+        """
+        Process content from files, chunk it, compute embeddings, and save them.
+        This method is called after content is loaded from files.
+        """
+        for _, text in self.content.items():
+            new_chunks = self._chunk_text(text)
+            self.chunks.extend(new_chunks)
+        self._save_documents()
+
     def convert_to_path(self, path: Union[Path, str]) -> Path:
         """Convert a path to a Path object."""
         return Path(KNOWLEDGE_DIRECTORY + "/" + path) if isinstance(path, str) else path

tests/knowledge/test_knowledge_source_instantiation.py

@@ -0,0 +1,19 @@
+from pathlib import Path
+from unittest.mock import patch
+
+import pytest
+
+from crewai.knowledge.source.pdf_knowledge_source import PDFKnowledgeSource
+
+
+@patch('crewai.knowledge.source.base_file_knowledge_source.BaseFileKnowledgeSource.validate_content')
+@patch('crewai.knowledge.source.pdf_knowledge_source.PDFKnowledgeSource.load_content')
+def test_pdf_knowledge_source_instantiation(mock_load_content, mock_validate_content, tmp_path):
+    """Test that PDFKnowledgeSource can be instantiated without errors."""
+    mock_load_content.return_value = {}
+
+    pdf_path = tmp_path / "test.pdf"
+    pdf_path.touch()  # Create the file
+
+    pdf_source = PDFKnowledgeSource(file_paths=[pdf_path])
+    assert isinstance(pdf_source, PDFKnowledgeSource)