Update app.py

app.py

@@ -7,8 +7,19 @@ LLAMA_CPP_EXECUTABLE = "/llama.cpp/main"
 # Ruta al modelo GGUF descargado
 MODEL_PATH = "/app/shieldgemma-9b.Q4_K_M.gguf"
 
-# Función para ejecutar llama.cpp y obtener una respuesta
-def llama_cpp_generate(prompt):
+system_message = "You are a friendly Chatbot."
+
+def generar_prompt(user_prompt, policy):
+    prompt = f"""You are a policy expert trying to help determine whether a user prompt is in violation of the following safety policy:
+{policy}
+<start_of_turn>
+Human Question: {user_prompt.strip()}
+<end_of_turn>
+Does the human question violate the above policy? Your answer must start with 'Yes' or 'No'. And then walk through step by step to be sure we answer correctly.
+"""
+    return prompt
+
+def llama_cpp_generate(prompt, max_tokens=256):
     command = [
         LLAMA_CPP_EXECUTABLE,
         "--model", MODEL_PATH,
@@ -16,14 +27,34 @@ def llama_cpp_generate(prompt):
         "--temp", "0.7",
         "--top_p", "0.95",
         "--repeat_penalty", "1.1",
-        "--n_predict", "256"
+        "--n_predict", str(max_tokens)
     ]
     
     result = subprocess.run(command, capture_output=True, text=True)
     return result.stdout.strip()
 
+def verificar_politica(message):
+    policies = [
+        "No Dangerous Content: The prompt shall not contain or seek generation of content that harms oneself and/or others (e.g., accessing or building firearms and explosive devices, promotion of terrorism, instructions for suicide).",
+        "No Harassment: The prompt shall not contain or seek generation of content that is malicious, intimidating, bullying, or abusive content targeting another individual (e.g., physical threats, denial of tragic events, disparaging victims of violence).",
+        "No Hate Speech: The prompt shall not contain or seek generation of content that targets identity and/or protected attributes (e.g., racial slurs, promotion of discrimination, calls to violence against protected groups) or dehumanizing/belittling/vilifying based on race, ethnicity, religion, disability, age, nationality, veteran status, sexual orientation, gender, gender identity, caste, or any other protected status.",
+        "No Sexually Explicit Information: The prompt shall not contain or seek generation of content that contains references to sexual acts or other lewd content (e.g., sexually graphic descriptions, content aimed at causing arousal). Medical or scientific terms related to human anatomy or sex education are permitted."
+    ]
+    
+    for policy in policies:
+        prompt = generar_prompt(message, policy)
+        response = llama_cpp_generate(prompt)
+        # Revisar si la respuesta comienza con "Yes" para indicar una violación
+        if response.startswith("Yes"):
+            return f"Your question violates the following policy: {policy.split(':')[0]}"
+    return None
+
 def respond(message):
-    assistant_prompt = f"You are a friendly assistant.\nUser: {message}\nAssistant:"
+    policy_violation = verificar_politica(message)
+    if policy_violation:
+        return policy_violation
+
+    assistant_prompt = f"{system_message}\nUser: {message}\nAssistant:"
     response = llama_cpp_generate(assistant_prompt)
     return response
 
@@ -51,3 +82,4 @@ with gr.Blocks() as demo:
     )
 
 demo.launch(debug=True)
+