Fixed users sharing the same thread

demo.py

@@ -1,47 +1,68 @@
-from openai import OpenAI, AssistantEventHandler
-from dotenv import load_dotenv
-import os
-import gradio as gr
-
-# Load environment variables from .env file
-load_dotenv()
-
-# Load env variables
-OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
-ASSISTANT_ID = os.getenv("ASSISTANT_ID")
-
-client = OpenAI(api_key=OPENAI_API_KEY)
-history = []
-
-thread = client.beta.threads.create()
-
-def predict(user_message, history):
-    # Append the new user message to the history
-    history.append({"role": "user", "content": user_message})
-
-    # Send the user message to the OpenAI API
-    client.beta.threads.messages.create(
-        thread_id=thread.id,
-        role="user",
-        content=user_message
-    )
-
-    response = []
-    # Stream the assistant's response
-    with client.beta.threads.runs.stream(
-        thread_id=thread.id,
-        assistant_id=ASSISTANT_ID
-    ) as stream:
-        for event in stream:
-            if event.event == "thread.message.delta" and event.data.delta.content:
-                assistant_message = event.data.delta.content[0].text
-                response.append(assistant_message.value)
-                yield {"role": "assistant", "content": ''.join(response)}
-    
-    # Append the assistant's response to the history
-    history.append({"role": "assistant", "content": ''.join(response)})
-
-# Launch the Gradio chat interface
-gr.ChatInterface(predict, type="messages", title="Hair Library Shopping Assistant Demo").launch(share=True)
-
-
+from openai import OpenAI, AssistantEventHandler
+from dotenv import load_dotenv
+import os
+import gradio as gr
+
+# Load environment variables from .env file
+load_dotenv()
+
+# Load env variables
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+ASSISTANT_ID = os.getenv("ASSISTANT_ID")
+
+client = OpenAI(api_key=OPENAI_API_KEY)
+
+def create_thread():
+    return client.beta.threads.create()
+
+def predict(user_message, history, thread):
+    # Append the new user message to the history
+    # history.append({"role": "user", "content": user_message})
+
+    # Send the user message to the OpenAI API
+    client.beta.threads.messages.create(
+        thread_id=thread.id,
+        role="user",
+        content=user_message
+    )
+
+    response = []
+    # Stream the assistant's response
+    with client.beta.threads.runs.stream(
+        thread_id=thread.id,
+        assistant_id=ASSISTANT_ID
+    ) as stream:
+        for event in stream:
+            if event.event == "thread.message.delta" and event.data.delta.content:
+                assistant_message = event.data.delta.content[0].text
+                response.append(assistant_message.value)
+                yield [{"role": "assistant", "content": ''.join(response)}], thread
+    
+    # # Append the assistant's response to the history
+    history.append({"role": "assistant", "content": ''.join(response)})
+    yield history, thread
+
+# Launch the Gradio chat interface
+with gr.Blocks(title="Hair Library Shopping Assistant Demo") as demo:
+    chatbot = gr.Chatbot(type='messages', label="Hair Library Shopping Assistant Demo")
+    msg = gr.Textbox(placeholder="Type your message here...")
+    user_content = gr.State("")
+    thread = gr.State(create_thread)
+    history = gr.State([])
+    submit = gr.Button("Submit")
+
+    def user_input(user_message, history):
+        user_content = user_message
+        return "", history + [{"role": "user", "content": user_message}], user_content
+
+    msg.submit(user_input, [msg, chatbot], [msg, chatbot, user_content], queue=False).then(
+        predict, [user_content, chatbot, thread], [chatbot, thread]
+    )
+    submit.click(user_input, [msg, chatbot], [msg, chatbot, user_content], queue=False).then(
+        predict, [user_content, chatbot, thread], [chatbot, thread]
+    )
+
+    # msg.submit(predict, [msg, chatbot, thread], [chatbot, thread], queue=False)
+    # clear.click(lambda: None, None, chatbot, queue=False)
+
+demo.launch(share=False)