Update space

app.py

@@ -1,64 +1,58 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import json
 
-"""
-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}]
+# Initialize the client with your model
+client = InferenceClient("pramodkoujalagi/SmolLM2-360M-Instruct-Text-2-JSON")
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def respond(message, history: list[tuple[str, str]]):
+    # Format the prompt according to your model's expected input format
+    formatted_prompt = f"""<|im_start|>user
+Extract the relevant event information from this text and organize it into a JSON structure with fields for action, date, time, attendees, location, duration, recurrence, and notes. If a field is not present, return null for that field.
 
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+Text: {message}
+<|im_end|>
+<|im_start|>assistant
+"""
+    
+    # Make the API call to your model
+    complete_response = ""
+    for chunk in client.text_generation(
+        formatted_prompt,
+        max_new_tokens=512,
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
+        temperature=0.1,
+        top_p=0.95,
+        stop_sequences=["<|im_end|>"]
     ):
-        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
-"""
+        complete_response += chunk
+    
+    # Clean up the response to get just the JSON and remove end tag
+    cleaned_response = complete_response.strip()
+    # Remove the <|im_end|> tag if present
+    cleaned_response = cleaned_response.replace("<|im_end|>", "").strip()
+    
+    try:
+        # Parse the JSON to validate it
+        json_obj = json.loads(cleaned_response)
+        # Return properly formatted JSON
+        return json.dumps(json_obj, indent=2)
+    except json.JSONDecodeError:
+        # If parsing fails, return the raw response with end tag removed
+        return cleaned_response
+
+# Create the chat interface with no additional inputs
 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)",
-        ),
+    examples=[
+        "Plan an exhibition walkthrough on 15th, April 2028 at 3 PM with Harper, Grace, and Alex in the art gallery for 1 hour.",
+        "Schedule a meeting with the marketing team tomorrow at 2 PM in the conference room.",
+        "Let's do a weekly team standup every Monday at 9 AM for 30 minutes starting next week.",
+        "Reminder to pick up groceries this Saturday afternoon."
     ],
+    title="Calendar Event Extraction",
+    description="Enter text containing event information, and I'll extract the details into a JSON format."
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()