Update app.py

app.py

@@ -1,63 +1,45 @@
 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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import requests
+import time
+import os
+
+api_key = os.getenv("apichatbotacess")
+
+# Define the API calling function
+def api_call(prompt, thread_id):
+    url = "https://multimodalcompany-dev--talent-chatbot-beta-dev-dev.modal.run"
+    headers = {
+        "key": api_key,
+        "Content-Type": "application/json"
+    }
+    data = {
+        "prompt": prompt,
+        "thread_id": thread_id,
+        "max_new_tokens": 4096,
+        "top_p": 0.95,
+        "temperature": 0.7,
+        "repetition_penalty": 1.15,
+        "do_sample": False,
+        "stream": False,
+        "user_id": "talent-demo-user",
+        "topic_id": "talent-chatbot",
+        "persist_data": True,
+        "max_chat_history_tokens": 2000,
+        "max_chat_history_days": 10
+    }
+    response = requests.post(url, headers=headers, json=data)
+    return response.json()["message"]
+
+with gr.Blocks() as demo:
+    thread_id_input = gr.Textbox(label="Enter Thread ID", placeholder="Thread ID", lines=1)
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(label="Your Message")
+
+    def respond(message, thread_id, chat_history):
+        bot_message = api_call(message, thread_id)
+        chat_history.append((message, bot_message))
+        return "", chat_history
+
+    msg.submit(respond, [msg, thread_id_input, chatbot], [msg, chatbot])
+
+demo.launch(share=True)