Update app.py

app.py

@@ -1,52 +1,53 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline 
-"""
-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")
+from transformers import pipeline
+
 model_id = "thrishala/mental_health_chatbot"
 
+try:
+    pipe = pipeline("text-generation", model=model_id)  # Directly create pipeline
+
+except Exception as e:
+    print(f"Error loading model: {e}")
+    exit()
+
 def respond(
     message,
     history: list[tuple[str, str]],
-    system_message,
+    system_message,  # You can use this for initial instructions
     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})
+# 2. Construct the Prompt (Crucial!)
+prompt = f"{system_message}\n" 
+for user_msg, bot_msg in history:
+    prompt += f"User: {user_msg}\nAssistant: {bot_msg}\n"
+prompt += f"User: {message}\nAssistant:"
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+# 3. Generate with the Pipeline
+try:
+    response = pipe(
+        prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+    )[0]["generated_text"]
+    #Extract the bot's reply (adjust if your model format is different)
+    bot_response = response.split("Assistant:")[-1].strip()
+    yield bot_response
 
+except Exception as e:
+    print(f"Error during generation: {e}")
+    yield "An error occurred during generation." #Handle generation errors.
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# 4. Gradio Interface (No changes needed here)
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(
+            value="You are a friendly and helpful mental health 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(
@@ -59,6 +60,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()