Update app.py

app.py

@@ -1,63 +1,40 @@
-import gradio as gr
+from fastapi import FastAPI, Request
 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(
+import uvicorn
+
+app = FastAPI()
+
+client = InferenceClient("scb10x/llama-3-typhoon-v1.5-8b-instruct")
+
+@app.post("/webhook")
+async def webhook(request: Request):
+    # รับข้อมูลจาก Dialogflow
+    data = await request.json()
+    query_text = data['queryResult']['queryText']
+    
+    # สร้าง messages สำหรับ Huggingface API
+    messages = [
+        {"role": "system", "content": "You are a friendly Chatbot."},
+        {"role": "user", "content": query_text}
+    ]
+    
+    # เรียกใช้ Huggingface API
+    response = 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)",
-        ),
-    ],
-)
-
+        max_tokens=512,
+        temperature=0.7,
+        top_p=0.95,
+    )
+    
+    # ดึงข้อความตอบกลับ
+    answer = response.choices[0].message.content
+    
+    # สร้างการตอบกลับสำหรับ Dialogflow
+    dialogflow_response = {
+        "fulfillmentText": answer,
+    }
+    
+    return dialogflow_response
 
 if __name__ == "__main__":
-    demo.launch()
+    uvicorn.run(app, host="0.0.0.0", port=7860)