Upload main.py

main.py

@@ -42,8 +42,14 @@ class PDFProcessor:
         self.output_dir.mkdir(exist_ok=True)
 
     def _initialize_emb_model(self, model_name):
-        model = SentenceTransformer("sentence-transformers/" + model_name)
-        model.save('models/'+ model_name)
+        # model = SentenceTransformer("sentence-transformers/" + model_name)
+        # model = SentenceTransformer(model_name)
+        # model.save('models/'+ model_name)
+        # Load model directly
+        from transformers import AutoTokenizer, AutoModel
+
+        tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/all-MiniLM-L6-v2")
+        model = AutoModel.from_pretrained("sentence-transformers/all-MiniLM-L6-v2")
         return model
 
     def _initialize_llm(self, model_name):
@@ -187,4 +193,4 @@ def process_pdf_catalog(pdf_path: str):
         return result, "Processing completed successfully!"
     except Exception as e:
         logger.error(f"Processing failed: {e}")
-        return {}, "Error processing PDF"
+        return {}, "Error processing PDF"