Update app.py

app.py

@@ -1,27 +1,32 @@
-import os 
-from openai import OpenAI
+from huggingface_hub import InferenceClient
 import gradio as gr
+from dotenv import load_dotenv
+import os
 
-api_key=os.environ.get("OPEN_API_KEY")
-client = OpenAI(api_key=api_key)
+load_dotenv()
 
-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='gpt-3.5-turbo',
-    messages= history_openai_format,
-    temperature=1.0,
-    stream=True)
+client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta", token=os.getenv("HF_TOKEN"))
 
-    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
+#built a chat interface on gradio
 
-gr.ChatInterface(predict).launch()
+def chatbot(input, history):
+    message = [{"role": "user", "content": input}]
+    #print(message)
+    history = [{"role" : "system", "content": "You are a helpful assistant."}]
+    #print(history)
+    messages = history + message
+    #print(messages)
+    output = client.chat_completion(
+        messages=messages,
+        max_tokens=256,
+        temperature=0.7
+    )
+    #print(output)
+    history = history + [{"role": "assistant", "content": output.choices[0].message.content}]
+    #print(history)
+    #print(history[0])
+    return output.choices[0].message.content
 
+demo = gr.ChatInterface(chatbot, title="Chatbot",fill_height=True)
+
+demo.launch()