Update backend.py

backend.py

@@ -33,7 +33,6 @@ def generate_testcases(user_story):
 
     # Few-shot learning examples to guide the model
     few_shot_examples = """
-
     "if its not a DropBury or ODAC Portal User Story, then we perform testing in Tech360 iOS App"
     "Generate as many as testcases possible minimum 6 ,maximum it can be anything"
     "Understand the story thoroughly"
@@ -41,34 +40,33 @@ def generate_testcases(user_story):
     """
 
     # Combine the few-shot examples with the user story for the model to process
-    prompt = few_shot_examples + f"\nUser Story: {user_story}\n" 
+    prompt = few_shot_examples + f"\nUser Story: {user_story}\n"
 
     try:
         # Call the Nvidia llama API with the refined prompt
         completion = client.chat.completions.create(
-            model="meta/llama-3.1-405b-instruct",  # Using llama3.1 405b model
+            model="meta/llama-3.1-405b-instruct",
             messages=[
                 {"role": "user", "content": prompt}
             ],
-            temperature=0.03,  # Further lowering temperature for precise and deterministic output
-            top_p=0.7,  # Prioritize high-probability tokens even more
-            max_tokens=4096,  # Increase max tokens to allow longer content
-            stream=True  # Streaming the response for faster retrieval
+            temperature=0.03,
+            top_p=0.7,
+            max_tokens=4096,
+            stream=True
         )
 
         # Initialize an empty string to accumulate the response
         test_cases_text = ""
-        
+
         # Accumulate the response from the streaming chunks
         for chunk in completion:
             if chunk.choices[0].delta.content is not None:
                 test_cases_text += chunk.choices[0].delta.content
 
-
         # Ensure the entire response is captured before cleaning
         if test_cases_text.strip() == "":
             return [{"test_case": "No test cases generated or output was empty."}]
-        
+
         # Clean the output by unescaping HTML entities and replacing <br> tags
         test_cases_text = clean_test_case_output(test_cases_text)
 
@@ -77,14 +75,13 @@ def generate_testcases(user_story):
             test_cases = json.loads(test_cases_text)
             if isinstance(test_cases, list):
                 return test_cases  # Return structured test cases
-
             else:
                 return [{"test_case": test_cases_text}]  # Return as a list with the text wrapped in a dict
 
         except json.JSONDecodeError:
             # Fallback: return the raw text if JSON parsing fails
             return [{"test_case": test_cases_text}]
-    
+
     except requests.exceptions.RequestException as e:
         print(f"API request failed: {str(e)}")
         return []
@@ -94,17 +91,9 @@ def export_test_cases(test_cases):
         return "No test cases to export."
 
     # Use pandas to export the test cases to Excel
-    df = pd.DataFrame(test_cases)
     output = io.BytesIO()
-    df.to_excel(output, index=False)
-    output.seek(0)
-    return output.getvalue()
-
-def save_test_cases_as_file(test_cases):
-    if not test_cases:
-        return "No test cases to save."
-
-    # Use pandas to save the test cases to an Excel file
     df = pd.DataFrame(test_cases)
-    df.to_excel('test_cases.xlsx', index=False)
-    return 'excel file saved'
+    df.to_excel(output, index=False, engine='openpyxl')  # Use 'openpyxl' engine
+    output.seek(0)  # Rewind the buffer
+
+    return output.getvalue()