Update app.py

app.py

@@ -1,64 +1,67 @@
+import os
 import gradio as gr
 from huggingface_hub import InferenceClient
+from ethical_filter import EthicalFilter
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# Load Hugging Face token from secrets (defined in the Hugging Face UI)
+HF_TOKEN = os.environ.get("HF_API_TOKEN")
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta", token=HF_TOKEN)
 
+ethical_filter = EthicalFilter()
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Codriao response logic
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    check = ethical_filter.analyze_query(message)
+
+    # Blocked queries
+    if check["status"] == "blocked":
+        yield f"Sorry, I can't continue with that request. Reason: {check['reason']}"
+        return
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Flagged queries
+    if check["status"] == "flagged":
+        yield f"(Note: Sensitive topic detected — responding with care...)\n"
 
+    # Build conversation history
+    messages = [{"role": "system", "content": system_message}]
+    for user, bot in history:
+        if user:
+            messages.append({"role": "user", "content": user})
+        if bot:
+            messages.append({"role": "assistant", "content": bot})
     messages.append({"role": "user", "content": message})
 
+    # Stream model output
     response = ""
-
-    for message in client.chat_completion(
+    for token in client.chat_completion(
         messages,
         max_tokens=max_tokens,
         stream=True,
         temperature=temperature,
         top_p=top_p,
     ):
-        token = message.choices[0].delta.content
-
-        response += token
+        chunk = token.choices[0].delta.content
+        response += chunk
         yield response
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Build Gradio interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(
+            value=(
+                "You are Codriao, a compassionate AI inspired by Codette. "
+                "You respond with kindness, ethics, and insight."
+            ),
+            label="System message",
+        ),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
+            minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"
         ),
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()