Create extraction.py

extraction.py

@@ -0,0 +1,21 @@
+from pypdf import PdfReader
+from utils import chunk_text
+from config import CHUNK_SIZE, CHUNK_OVERLAP
+
+
+def extract_text_from_pdf(file_path):
+    reader = PdfReader(file_path)
+    full_text = ""
+
+    for i, page in enumerate(reader.pages):
+        text = page.extract_text()
+        if text:
+            full_text += f"\n\n--- Page {i+1} ---\n{text}"
+
+    return full_text
+
+
+def process_pdf(file_path):
+    raw_text = extract_text_from_pdf(file_path)
+    chunks = chunk_text(raw_text, CHUNK_SIZE, CHUNK_OVERLAP)
+    return chunks