Update app.py

app.py

@@ -1,63 +1,78 @@
-import gradio as gr
 from huggingface_hub import InferenceClient
+import os
+import openai
+import gradio as gr
+import time
 
-"""
-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")
+openai.api_key = os.getenv('openai_api_key')
+api_key = openai.api_key
+
+client = openai.Client(api_key=api_key)
 
+# Assuming you've already set up your OpenAI client and assistant
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+assistant_id = os.getenv('assistant_id')
+assistant_id = assistant_id
+assistant = client.beta.assistants.retrieve(assistant_id)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+thread = client.beta.threads.create()
 
-    messages.append({"role": "user", "content": message})
+def chat_with_assistant(message, history):
+    # Add the user's message to the thread
+    client.beta.threads.messages.create(
+        thread_id=thread.id,
+        role="user",
+        content=message
+    )
+    
+    # Run the assistant
+    run = client.beta.threads.runs.create(
+        thread_id=thread.id,
+        assistant_id=assistant_id
+    )
+    
+    # Wait for the assistant's response
+    while True:
+        run_status = client.beta.threads.runs.retrieve(thread_id=thread.id, run_id=run.id)
+        if run_status.status == 'completed':
+            # Retrieve the assistant's response
+            messages = client.beta.threads.messages.list(thread_id=thread.id)
+            assistant_response = messages.data[0].content[0].text.value
+            break
+        time.sleep(1)
+    
+    return assistant_response
 
-    response = ""
+# Custom CSS for chat bubbles and colors
+custom_css = """
+.user-message { background-color: #DCF8C6; }
+.assistant-message { background-color: #E2E2E2; }
+"""
 
-    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
+# Create the Gradio interface
+with gr.Blocks(css=custom_css) as demo:
+    chatbot = gr.Chatbot(
+        [],
+        elem_id="chatbot",
+        bubble_full_width=False,
+        avatar_images=(None, "path/to/assistant_avatar.png")
+    )
+    msg = gr.Textbox(
+        show_label=False,
+        placeholder="Enter text and press enter",
+    )
 
-        response += token
-        yield response
+    def user(user_message, history):
+        return "", history + [[user_message, None]]
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-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()
+    def bot(history):
+        user_message = history[-1][0]
+        bot_message = chat_with_assistant(user_message, history)
+        history[-1][1] = bot_message
+        return history
+
+    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
+        bot, chatbot, chatbot
+    )
+
+demo.launch(share=True)