Update app.py

app.py

@@ -1,4 +1,32 @@
+# import gradio as gr
+# import os
+
+# gr.load("models/google/gemma-1.1-7b-it", hf_token=os.environ.get("YOUR_API_TOKEN"), streaming=True).launch()
+
+from openai import OpenAI
 import gradio as gr
-import os
 
-gr.load("models/google/gemma-1.1-7b-it", hf_token=os.environ.get("YOUR_API_TOKEN"), streaming=True).launch()
+client = OpenAI(
+  base_url="https://api-inference.huggingface.co/v1",
+  api_key=os.environ.get('YOUR_API_TOKEN')
+) 
+
+def predict(message, history):
+    history_openai_format = []
+    for human, assistant in history:
+        history_openai_format.append({"role": "user", "content": human })
+        history_openai_format.append({"role": "assistant", "content":assistant})
+    history_openai_format.append({"role": "user", "content": message})
+  
+    response = client.chat.completions.create(model='google/gemma-1.1-7b-it',
+    messages= history_openai_format,
+    temperature=0.7,
+    stream=True)
+
+    partial_message = ""
+    for chunk in response:
+        if chunk.choices[0].delta.content is not None:
+              partial_message = partial_message + chunk.choices[0].delta.content
+              yield partial_message
+
+gr.ChatInterface(predict).launch()