Update app.py

app.py

@@ -1,64 +1,43 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from fastapi import FastAPI
+from pydantic import BaseModel
+import uvicorn
 
-"""
-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})
+# Create FastAPI app
+app = FastAPI()
 
-    response = ""
+# Hugging Face model
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
+# Request format
+class Request(BaseModel):
+    message: str
+    history: list[tuple[str, str]] = []
+    system_message: str = "You are a friendly chatbot."
+    max_tokens: int = 512
+    temperature: float = 0.7
+    top_p: float = 0.95
+
+@app.post("/chat")
+def chat(req: Request):
+    messages = [{"role": "system", "content": req.system_message}]
+    
+    for user_msg, bot_reply in req.history:
+        if user_msg:
+            messages.append({"role": "user", "content": user_msg})
+        if bot_reply:
+            messages.append({"role": "assistant", "content": bot_reply})
+    
+    messages.append({"role": "user", "content": req.message})
+
+    response_text = ""
+    for message in client.chat_completion(messages, max_tokens=req.max_tokens, stream=True, temperature=req.temperature, top_p=req.top_p):
         token = message.choices[0].delta.content
+        response_text += token
 
-        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)",
-        ),
-    ],
-)
-
+    return {"response": response_text}
 
+# Launch API
 if __name__ == "__main__":
-    demo.launch()
+    uvicorn.run(app, host="0.0.0.0", port=7860)