Update app.py

app.py

@@ -1,29 +1,59 @@
-import streamlit as st
-from transformers import pipeline
-
-# Load the fill-mask pipeline with the specified model
-@st.cache_resource
-def load_pipeline():
-    """Load the ParlBERT model for the fill-mask task."""
-    pipe = pipeline("fill-mask", model="InfAI/parlbert-german-law")
-    return pipe
-
-# Load the pipeline
-pipe = load_pipeline()
-
-# Streamlit app UI
-st.title("ParlBERT German Law Fill-in-the-Blank Assistant")
-st.write("Enter a sentence with a `[MASK]` token, and the model will predict possible words.")
-
-# Input text area for the sentence with a default example
-user_input = st.text_input("Your sentence (use [MASK] as a placeholder):", "Das Gesetz [MASK] den Bürger.")
-
-# Generate predictions when the button is clicked
-if st.button("Generate Prediction"):
-    # Run the model on the input sentence
-    predictions = pipe(user_input)
-    
-    # Display predictions
-    st.write("Predicted Fill-ins:")
-    for i, pred in enumerate(predictions):
-        st.write(f"{i+1}. {pred['sequence']} (Score: {pred['score']:.4f})")
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+# Initialize the InferenceClient with the model 'InfAI/parlbert-german-law'
+client = InferenceClient("InfAI/parlbert-german-law")
+
+
+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
+
+
+# Create the Gradio interface for chatbot interaction
+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()