Update app.py

app.py

@@ -4,7 +4,18 @@ 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")
+
+
+from openai import OpenAI
+# 设置 OpenAI 的 API 密钥和 API 基础 URL 以使用 vLLM 的 API 服务器。
+openai_api_key = "EMPTY"
+openai_api_base = "http://47.117.17.202:12345/v1"
+
+
+client = OpenAI(
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
 
 
 def respond(
@@ -25,19 +36,19 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    response = openai.chat.completions.create(
+        model="Qwen2_5VL",
+        messages=messages,
+        extra_body={},
+        extra_headers={
+            "apikey": "empty"
+        },
         stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+        temperature=0.7,
+        top_p=1.0,
+    )
+    for chunk in response:
+        yield chunk.choices[0].delta.content
 
 
 """