47 lines
1.5 KiB
Python
47 lines
1.5 KiB
Python
|
import re
|
|||
|
|
import sys
|
|||
|
|
import os
|
|||
|
|
sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
|
|||
|
|
from Util.LlmUtil import get_llm_response
|
|||
|
|
|
|||
|
|
def stream_and_split_text(prompt):
|
|||
|
|
"""
|
|||
|
|
流式获取LLM输出并按句子分割
|
|||
|
|
@param prompt: 提示文本
|
|||
|
|
@return: 生成器，每次产生一个完整句子
|
|||
|
|
"""
|
|||
|
|
buffer = ""
|
|||
|
|
|
|||
|
|
# 使用LlmUtil中的get_llm_response函数获取流式响应
|
|||
|
|
for content in get_llm_response(prompt, stream=True):
|
|||
|
|
buffer += content
|
|||
|
|
|
|||
|
|
# 使用正则表达式检测句子结束
|
|||
|
|
sentences = re.split(r'([。！？.!?])', buffer)
|
|||
|
|
if len(sentences) > 1:
|
|||
|
|
# 提取完整句子
|
|||
|
|
for i in range(0, len(sentences)-1, 2):
|
|||
|
|
if i+1 < len(sentences):
|
|||
|
|
sentence = sentences[i] + sentences[i+1]
|
|||
|
|
yield sentence
|
|||
|
|
|
|||
|
|
# 保留不完整的部分
|
|||
|
|
buffer = sentences[-1]
|
|||
|
|
|
|||
|
|
# 处理最后剩余的部分
|
|||
|
|
if buffer:
|
|||
|
|
yield buffer
|
|||
|
|
|
|||
|
|
def main():
|
|||
|
|
"""
|
|||
|
|
测试stream_and_split_text函数
|
|||
|
|
"""
|
|||
|
|
test_prompt = "请简单介绍一下人工智能的发展历史。包括从图灵测试到深度学习的演进过程。"
|
|||
|
|
print("测试文本：", test_prompt)
|
|||
|
|
print("\n分割后的句子：")
|
|||
|
|
|
|||
|
|
for i, sentence in enumerate(stream_and_split_text(test_prompt), 1):
|
|||
|
|
print(f"句子 {i}: {sentence}")
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
main()
|