Cpp to python, Testing Stable LM 2 1.6B Zephyr

app.py

@@ -38,7 +38,6 @@ def generate_response(user_message):
 """
 
 def generate_response(user_message):
-    print("Before request")
     cmd = [
         "/app/llama.cpp/main",  # Path to the executable
         "-m", "/app/llama.cpp/models/stablelm-2-zephyr-1_6b-Q4_0.gguf",
@@ -46,13 +45,17 @@ def generate_response(user_message):
         "-n", "400",
         "-e"
     ]
-    
+
+    print("Before request")
     # Start the subprocess
     process = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
 
+    alllines = ""
+
     # Yield each line of output as it becomes available
     for line in process.stdout:
-        yield line
+        alllines += " " + line
+        yield alllines
     
     # Wait for the subprocess to finish if it hasn't already
     process.wait()