Update app.py

app.py

@@ -80,11 +80,9 @@ qa_pipeline = pipeline("text2text-generation", model="google/flan-t5-base")
 def document_qna_tool(pdf_path: str, question: str) -> str:
     """
     A tool that answers natural language questions about a given PDF document.
-    
     Args:
         pdf_path (str): Path to the local PDF file.
         question (str): Question about the content of the PDF.
-    
     Returns:
         str: Answer to the question based on the content.
     """
@@ -116,24 +114,17 @@ def document_qna_tool(pdf_path: str, question: str) -> str:
             return "[ERROR] No readable text in the PDF."
 
         print(f"[DEBUG] Extracted {len(text_chunks)} text chunks.")
-        print(f"[DEBUG] First text chunk preview:\n{text_chunks[0][:300]}...")
 
+        embedding_model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
         embeddings = embedding_model.encode(text_chunks, convert_to_tensor=True)
         question_embedding = embedding_model.encode(question, convert_to_tensor=True)
 
         print("[DEBUG] Performing semantic search...")
         scores = util.pytorch_cos_sim(question_embedding, embeddings)[0]
-
-        print(f"[DEBUG] Similarity scores: {scores}")
-
-        if scores.shape[0] == 0:
-            return "[ERROR] No semantic matches found in PDF text."
-
         best_match_idx = scores.argmax().item()
         best_context = text_chunks[best_match_idx]
 
-        print(f"[DEBUG] Best context preview:\n{best_context[:300]}...")
-
+        qa_pipeline = pipeline("text2text-generation", model="google/flan-t5-base")
         prompt = f"Context: {best_context}\nQuestion: {question}"
         print("[DEBUG] Calling QA model...")
         answer = qa_pipeline(prompt, max_new_tokens=100)[0]['generated_text']
@@ -177,8 +168,5 @@ agent = CodeAgent(
     description=None,
     prompt_templates=prompt_templates
 )
-print("[DEBUG] Registered Tools:")
-for t in agent.tools:
-    print(f" - {getattr(t, 'name', str(t))}")
 
 GradioUI(agent).launch()