主页 / coding / 问题 / 79573908
Accepted
Tiago Peres
Asked: 2025-04-15 03:42:52 +0800 CST

OpenAI Assistants 的引用类似于【4:2†source】和citeturnXfileY

  • 772

使用 OpenAI Assistant 进行流式传输时

openai.beta.threads.messages.create(
    thread_id=thread_id,
    role="user",
    content=payload.question
)

run = openai.beta.threads.runs.create(
    thread_id=thread_id,
    assistant_id=assistant_id,
    stream=True,
    tool_choice={"type": "file_search"},
)

streamed_text = ""
for event in run:
  if event.event == "thread.message.delta":
    delta_content = event.data.delta.content
    if delta_content and delta_content[0].type == "text":
      text_fragment = delta_content[0].text.value
      streamed_text += text_fragment
      yield {"data": text_fragment}
  if event.event == "thread.run.completed":
    break

引用的格式如下【4:2†source】或citeturnXfileY

OpenAI 奇怪的引用 1 OpenAI 奇怪的引用 2

如何修复？

python

1 个回答

  1. Best Answer

    我使用的方法是在流式传输后获取最终消息

    messages = openai.beta.threads.messages.list(thread_id=thread_id)

    然后应用以下正则表达式

    def replace_placeholder(match):
  nonlocal citation_index
  citation_index += 1
  return f"[{citation_index}]"

pattern = r"(citeturn\d+file\d+|【\d+:\d+†.*?】)"
citation_index = 0
assistant_reply_cleaned = re.sub(pattern, replace_placeholder, raw_text)

    将占位符（如【4:2†source】或citeturnXfileY）替换为[1]、[2]等

    • 0

相关问题