aws-samples / bedrock-claude-chat

AWS-native chatbot using Bedrock + Claude (+Mistral)
MIT No Attribution
828 stars 304 forks source link

[BUG] playwright でアクセスしたサイトがHTTP Status200以外の場合にエラーページが学習される #264

Closed kyosuke-kobayashi-lvgs closed 5 months ago

kyosuke-kobayashi-lvgs commented 5 months ago

Describe the bug

https://github.com/aws-samples/bedrock-claude-chat/blob/02473ad46fc6fc0804d72dc44e75cc0a21cbb39c/backend/embedding/loaders/playwright.py#L156

もし、アクセスしたサイトから400系あるいは500系のHTTPStatusが返却された場合にエラーハンドリングする

if response.status != 200:
    raise ValueError(f"page.goto() returned Not HTTP Status 200 for url {url}")

Filling out this field will help us investigate the issue efficiently. Providing detailed information allows us to set the appropriate priority. We appreciate your cooperation.
A clear and concise description of what the bug is.

To Reproduce

Filling out this field will help us investigate the issue efficiently. Providing detailed information allows us to set the appropriate priority. We appreciate your cooperation.
Steps to reproduce the behavior:

  1. Go to '...'
  2. Click on '....'
  3. Scroll down to '....'
  4. See error

Screenshots

If applicable, add screenshots to help explain your problem.

Additional context

Add any other context about the problem here.