Update app.py

app.py

@@ -1,64 +1,45 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message 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
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", 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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import requests
+
+# Public model URL - no API key needed
+HF_API_URL = "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2"
+
+def query_hf_model(messages):
+    # Convert Gradio format (list of {"role":..., "content":...}) to prompt text
+    prompt = "\n".join(
+        f"{msg['role'].capitalize()}: {msg['content']}" for msg in messages if msg["role"] in {"user", "assistant"}
+    ) + "\nAssistant:"
+
+    payload = {
+        "inputs": prompt,
+        "parameters": {
+            "max_new_tokens": 128,
+            "temperature": 0.7,
+            "return_full_text": True
+        }
+    }
+
+    response = requests.post(HF_API_URL, json=payload)
+    if response.status_code == 200:
+        result = response.json()[0]["generated_text"]
+        reply = result[len(prompt):].strip()
+        return reply
+    else:
+        return f"⚠️ Error {response.status_code}: {response.reason}"
+
+def respond(user_input, chat_history):
+    # Add user message to history
+    chat_history.append({"role": "user", "content": user_input})
+    reply = query_hf_model(chat_history)
+    chat_history.append({"role": "assistant", "content": reply})
+    return "", chat_history
+
+with gr.Blocks() as demo:
+    gr.Markdown("### 🤖 Mistral Chatbot — No Auth Required")
+
+    chatbot = gr.Chatbot(label="Chat with AI", type="messages", avatar_images=("👤", "🤖"))
+    msg = gr.Textbox(label="Your message", placeholder="Ask me anything...", scale=1)
+
+    msg.submit(fn=respond, inputs=[msg, chatbot], outputs=[msg, chatbot])
+
+demo.launch(share=True)