bot / app.py
pigrun2025's picture
Create app.py
c2b5368 verified
Raw History Blame Contribute Delete
10.3 kB
import gradio as gr
import os
import tempfile
from typing import List, Tuple, Optional
import dashscope
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import Chroma
from langchain_community.document_loaders import PyPDFLoader, Docx2txtLoader, TextLoader
import shutil
# ============== 配置 ==============
DASHSCOPE_API_KEY = os.getenv("DASHSCOPE_API_KEY", "")
if DASHSCOPE_API_KEY:
dashscope.api_key = DASHSCOPE_API_KEY
QWEN_MODEL = "qwen-turbo"
# 全局变量
vector_store = None
docs_loaded = False
# ============== 工具函数 ==============
def load_documents(file_paths: List[str]) -> List:
"""加载各种格式的文档"""
documents = []
for file_path in file_paths:
try:
if file_path.endswith('.pdf'):
loader = PyPDFLoader(file_path)
elif file_path.endswith('.docx'):
loader = Docx2txtLoader(file_path)
elif file_path.endswith('.txt'):
loader = TextLoader(file_path, encoding='utf-8')
else:
continue
documents.extend(loader.load())
except Exception as e:
print(f"加载文件失败 {file_path}: {e}")
return documents
def create_vector_store(documents: List):
"""创建向量数据库"""
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=500,
chunk_overlap=50,
length_function=len,
)
chunks = text_splitter.split_documents(documents)
embeddings = HuggingFaceEmbeddings(
model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
model_kwargs={'device': 'cpu'},
encode_kwargs={'normalize_embeddings': True}
)
vector_store = Chroma.from_documents(
documents=chunks,
embedding=embeddings,
persist_directory=None
)
return vector_store
def chat_with_qwen(messages: List[dict]) -> str:
"""调用通义千问 API"""
try:
response = dashscope.Generation.call(
model=QWEN_MODEL,
messages=messages,
result_format='message'
)
if response.status_code == 200:
return response.output.choices[0].message.content
else:
return f"API 错误:{response.code} - {response.message}"
except Exception as e:
return f"调用失败:{str(e)}"
def retrieve_context(query: str, top_k: int = 3) -> str:
"""从向量数据库检索相关内容"""
global vector_store
if vector_store is None:
return ""
try:
results = vector_store.similarity_search(query, k=top_k)
context = "\n\n".join([doc.page_content for doc in results])
return context
except Exception as e:
return f"检索失败:{str(e)}"
# ============== Gradio 界面 ==============
with gr.Blocks(title="通义千问混合机器人", theme=gr.themes.Soft()) as demo:
gr.Markdown("""
# 🤖 通义千问混合机器人
支持两种模式:
- **💬 聊天模式**:自由对话,什么问题都可以问
- **📄 文档问答**:上传文档后,基于文档内容回答问题
**使用前请确保已在 Space 设置中配置 `DASHSCOPE_API_KEY` 环境变量**
""")
# 状态存储
chat_state = gr.State([])
doc_store = gr.State(None)
with gr.Row():
with gr.Column(scale=1):
gr.Markdown("### 📁 文档管理")
file_upload = gr.File(
label="上传文档 (PDF/Word/TXT)",
file_types=[".pdf", ".docx", ".txt"],
file_count="multiple"
)
load_doc_btn = gr.Button("📥 加载文档", variant="secondary")
mode_toggle = gr.Checkbox(
label="📄 启用文档问答模式",
value=False,
info="开启后基于上传的文档回答问题"
)
status_box = gr.Textbox(
label="状态",
value="就绪",
interactive=False,
lines=1
)
clear_btn = gr.Button("🗑️ 清除状态", variant="secondary")
with gr.Column(scale=3):
gr.Markdown("### 💬 对话")
chatbot = gr.Chatbot(
label="对话记录",
height=450,
placeholder="输入问题开始对话...",
show_copy_button=True
)
msg_input = gr.Textbox(
label="输入消息",
placeholder="输入您的问题,按 Enter 发送...",
lines=2
)
with gr.Row():
submit_btn = gr.Button("🚀 发送", variant="primary", scale=2)
clear_chat_btn = gr.Button("🧹 清空对话", variant="secondary", scale=1)
gr.Markdown("""
---
**提示:**
- 首次使用请在 Space 设置中配置 `DASHSCOPE_API_KEY` 环境变量
- 文档问答模式需要先上传文档并点击"加载文档"
- 通义千问模型:qwen-turbo(快速)/ qwen-plus(平衡)/ qwen-max(最强)
""")
# ============== 事件处理 ==============
def load_docs(files):
"""加载文档到向量数据库"""
global vector_store, docs_loaded
if not files:
return "⚠️ 请先选择文件", None
try:
file_paths = [f.name for f in files]
documents = load_documents(file_paths)
if not documents:
return "❌ 未找到可加载的文档", None
vector_store = create_vector_store(documents)
docs_loaded = True
return f"✅ 已加载 {len(documents)} 个文档片段", vector_store
except Exception as e:
return f"❌ 加载失败:{str(e)}", None
def respond(message, chat_history, files, use_doc_mode, current_store):
"""处理用户消息"""
global vector_store, docs_loaded
if not message:
return "", chat_history, "⚠️ 请输入内容"
# 检查 API 密钥
if not DASHSCOPE_API_KEY:
error_msg = "⚠️ 请在 Space 设置中配置 DASHSCOPE_API_KEY 环境变量\n\n配置方法:\n1. 进入 Space Settings\n2. 找到 Repository secrets\n3. 添加 DASHSCOPE_API_KEY"
if chat_history is None:
chat_history = []
chat_history.append((message, error_msg))
return "", chat_history, "❌ 缺少 API 密钥"
# 如果是文档模式但没有加载文档
if use_doc_mode and not docs_loaded:
hint_msg = "📄 检测到您启用了文档问答模式,但尚未加载文档。\n\n请先上传文档并点击「加载文档」按钮,或者关闭文档问答模式进行普通聊天。"
if chat_history is None:
chat_history = []
chat_history.append((message, hint_msg))
return "", chat_history, "⚠️ 请先加载文档"
# 文档问答模式
if use_doc_mode and docs_loaded and vector_store:
context = retrieve_context(message)
if context:
prompt = f"""请根据以下文档内容回答问题。如果文档中没有相关信息,请说明。
文档内容:
{context}
用户问题:{message}
请基于文档内容给出准确回答:"""
messages = [
{"role": "system", "content": "你是一个专业的文档问答助手,请基于提供的文档内容准确回答问题。"},
{"role": "user", "content": prompt}
]
response = chat_with_qwen(messages)
if chat_history is None:
chat_history = []
chat_history.append((message, response))
return "", chat_history, "✅ 基于文档回答"
else:
hint_msg = "🤔 文档中没有找到相关信息。\n\n您可以:\n1. 尝试换一种问法\n2. 关闭文档问答模式进行普通聊天"
if chat_history is None:
chat_history = []
chat_history.append((message, hint_msg))
return "", chat_history, "⚠️ 未找到相关信息"
# 普通聊天模式
messages = [{"role": "system", "content": "你是一个友好、专业的 AI 助手,由通义千问驱动。"}]
if chat_history:
for user_msg, assistant_msg in chat_history[-5:]:
messages.append({"role": "user", "content": user_msg})
messages.append({"role": "assistant", "content": assistant_msg})
messages.append({"role": "user", "content": message})
response = chat_with_qwen(messages)
if chat_history is None:
chat_history = []
chat_history.append((message, response))
return "", chat_history, "✅ 已回复"
def clear_state():
"""清除状态"""
global vector_store, docs_loaded
vector_store = None
docs_loaded = False
return "状态已清除", None, []
def clear_chat_only():
"""只清空对话"""
return "", []
# 绑定事件
load_doc_btn.click(
fn=load_docs,
inputs=[file_upload],
outputs=[status_box, doc_store]
)
submit_btn.click(
fn=respond,
inputs=[msg_input, chatbot, file_upload, mode_toggle, doc_store],
outputs=[msg_input, chatbot, status_box]
)
msg_input.submit(
fn=respond,
inputs=[msg_input, chatbot, file_upload, mode_toggle, doc_store],
outputs=[msg_input, chatbot, status_box]
)
clear_btn.click(
fn=clear_state,
outputs=[status_box, doc_store, chatbot]
)
clear_chat_btn.click(
fn=clear_chat_only,
outputs=[msg_input, chatbot]
)
if __name__ == "__main__":
demo.launch()