Update app.py

app.py

@@ -1,63 +1,56 @@
+import os
+import openai
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
-
-
-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
-
-"""
-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)",
-        ),
-    ],
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+# Set your OpenAI API key from environment variable
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+# Retrieve the existing Assistant
+assistant_id = "asst_Fps5fdccFdhxF95G6iOAwIdQ"
+assistant = openai.beta.assistants.retrieve(assistant_id)
+
+# Initialize the Thread
+thread = openai.beta.threads.create()
+
+def chat(message, history):
+    # Add the user's message to the thread
+    openai.beta.threads.messages.create(
+        thread_id=thread.id,
+        role="user",
+        content=message
+    )
+
+    # Run the Assistant
+    run = openai.beta.threads.runs.create(
+        thread_id=thread.id,
+        assistant_id=assistant.id
+    )
+
+    # Wait for the run to complete
+    while run.status != "completed":
+        run = openai.beta.threads.runs.retrieve(
+            thread_id=thread.id,
+            run_id=run.id
+        )
+
+    # Retrieve the assistant's messages
+    messages = openai.beta.threads.messages.list(thread_id=thread.id)
+
+    # Get the last message from the assistant
+    last_message = next(msg for msg in messages if msg.role == "assistant")
+
+    return last_message.content[0].text.value
+
+# Create the Gradio interface
+iface = gr.ChatInterface(
+    fn=chat,
+    title="Colossal Cave",
+    description="Ask me anything about Colossal Cave Adventure!"
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the interface
+iface.launch()