Update app.py

app.py

@@ -1,46 +1,25 @@
-import os, gradio as gr
-from openai import OpenAI
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-# 初始化 DeepSeek 客户端
-client = OpenAI(
-    api_key=os.getenv("DEEPSEEK_API_KEY"),
-    base_url="https://api.deepseek.com/v1"
-)
+model_id = "your-username/lora-plant-deepseek"
+
+# 加载模型
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
 
-def analyze_stream(temperature, light, soil_humidity):
-    """
-    接收三个环境数据指标，调用 DeepSeek chat 模型进行流式分析。
-    将生成的 token 实时 yield 回前端。
-    """
-    messages = [
-        {"role": "system", "content": "You are a plant care assistant."},
-        {"role": "user", "content": 
-            f"Temperature: {temperature}°C, Light: {light} lux, Soil Humidity: {soil_humidity}%."}
-    ]
-    stream = client.chat.completions.create(
-        model="deepseek-chat",
-        messages=messages,
-        temperature=0.7,
-        stream=True
-    )
-    partial = ""
-    for chunk in stream:
-        delta = chunk.choices[0].delta.content or ""
-        partial += delta
-        yield partial  # 持续输出拼接中的内容
+def plant_ask(user_input):
+    prompt = f"用户提问：{user_input}\n请用人性化语言回答，并建议一些可查阅的植物文献资料。\n回答："
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs, max_new_tokens=300)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-# 定义 Gradio 界面
-demo = gr.Interface(
-    fn=analyze_stream,
-    inputs=[
-        gr.Number(label="Temperature (°C)"),
-        gr.Number(label="Light (lux)"),
-        gr.Number(label="Soil Humidity (%)")
-    ],
-    outputs=gr.Textbox(label="DeepSeek 分析结果"),
-    title="🌱 实时植物环境分析",
-    description="输入当前环境参数后，系统将流式返回 DeepSeek 的分析建议。",
+iface = gr.Interface(
+    fn=plant_ask,
+    inputs="text",
+    outputs="text",
+    title="🌱 植物助手问答系统",
+    description="欢迎提问关于植物养护、生长环境、病虫害防治等问题，我会尽力给出人性化建议和文献推荐。",
 )
 
-# 启用 Gradio 的队列和流式输出
-demo.queue(default_concurrency_limit=2).launch(server_name="0.0.0.0")
+iface.launch()