Create extract_text.py

extract_text.py

@@ -0,0 +1,22 @@
+import PyPDF2
+import json
+
+# Load the medical book PDF
+pdf_path = "gale_of_medicin.pdf"
+
+def extract_text(pdf_path):
+    with open(pdf_path, "rb") as file:
+        reader = PyPDF2.PdfReader(file)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text() + "\n"
+        return text
+
+# Extract and save text as JSON dataset
+text_data = extract_text(pdf_path)
+
+dataset = [{"prompt": "Medical Query", "response": text_data}]
+with open("medical_dataset.json", "w", encoding="utf-8") as f:
+    json.dump(dataset, f, ensure_ascii=False, indent=4)
+
+print("✅ Extracted text saved as `medical_dataset.json`")