锦中人工智能助手

import nltk

from transformers import pipeline

from flask import Flask, request, jsonify

# 下载必要的nltk数据

nltk.download('punkt')

# 初始化问答模型

qa_pipeline = pipeline("question-answering")

app = Flask(__name__)

@app.route('/ask', methods=['POST'])

def ask():

data = request.json

question = data['question']

context = data['context']

result = qa_pipeline(question=question, context=context)

return jsonify({

'answer': result['answer'],

'score': result['score']

})

if __name__ == '__main__':

app.run(debug=True)

from transformers import AutoTokenizer, AutoModelForSequenceClassification

import torch

# 加载预训练的BERT模型和分词器

model_name = "bert-base-uncased"

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForSequenceClassification.from_pretrained(model_name)

# 示例数据

texts = [

"下周的考试安排是什么时候？",

"我想预约导师。",

"今天的课程有哪些？"

]

# 分词并编码

inputs = tokenizer(texts, padding=True, truncation=True, return_tensors="pt")

# 进行预测

with torch.no_grad():

outputs = model(**inputs)

logits = outputs.logits

# 获取预测结果

predictions = torch.softmax(logits, dim=1).argmax(dim=1)

print(predictions)

from sqlalchemy import create_engine, Column, Integer, String

from sqlalchemy.ext.declarative import declarative_base

from sqlalchemy.orm import sessionmaker

Base = declarative_base()

class Course(Base):

__tablename__ = 'courses'

id = Column(Integer, primary_key=True)

name = Column(String(50))

time = Column(String(50))

# 创建数据库连接

engine = create_engine('sqlite:///school.db')

Base.metadata.create_all(engine)

Session = sessionmaker(bind=engine)

session = Session()

# 添加一条课程信息

new_course = Course(name='人工智能导论', time='周一上午10点')

session.add(new_course)

session.commit()

# 查询所有课程

courses = session.query(Course).all()

for course in courses:

print(course.name, course.time)