Update app.py

app.py

@@ -46,21 +46,30 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 import os
 
-token = os.getenv("HF_TOKEN")
-client = InferenceClient(api_key=token)
+hf_token = os.getenv("HF_TOKEN")
 
-messages = [
-	{ "role": "user", "content": "Tell me a story" }
-]
+def chat(messages):
+    client = InferenceClient(api_key=hf_token)
+    stream = client.chat.completions.create(
+        model="google/gemma-2-2b-it",
+        messages=messages,
+        #temperature=0.5,
+        #max_tokens=2048,
+        #top_p=0.7,
+        stream=True
+    )
+    story = ""
+    for chunk in stream:
+        story += chunk.choices[0].delta.content
+        return story
 
-stream = client.chat.completions.create(
-    model="google/gemma-2-2b-it", 
-	messages=messages, 
-	temperature=0.5,
-	max_tokens=2048,
-	top_p=0.7,
-	stream=True
+interface = gr.Interface(
+    fn=chat,
+    inputs="textbox",
+    outputs="textbox",
+    title="Storyteller with Gemma",
+    description="Tell me a story starter and I'll continue it using Gemma!",
+    label="Start your story..."
 )
 
-for chunk in stream:
-    print(chunk.choices[0].delta.content)
+interface.launch()