Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixed issue in Prompt Pagination, Update to OpenAI API, and various formatting fixes #6

Open
wants to merge 7 commits into
base: main
Choose a base branch
from

Conversation

gatuno1
Copy link

@gatuno1 gatuno1 commented Jan 20, 2025

  • Bugfix: duplicated text in pagination prompt.
    Removed error of adding twice the main pagination prompt text when scraping for pagination links with a LLM call.

  • Bugfix: migrated to v1.0 call
    When using generic openai-compatible model, the chat completation call is using client object as recommended in v1.0 API.

  • Prompt improvement:
    Modifications on scaper and pagination Prompts, to be clearer for the LLM.

  • Formatting & linting on all files:
    Includes removal of unused imports, removal of old comments, added header with she-bang for python, formatted python code for better readability, corrected problems with f-strings and logging options, etc.

  • Created .gitignore file with exclusions for output dir, and common cases for python, virtual environment, windows, vscode and pycharm.
    Hint from amgrbi96/AI-scraper fork.

  • Added changes.md file: to maintain changes log.

  • Added streamlit app debug configuration for VSCode.

  • Streamlit opt-out configuration added.

  • Ordered contents of requirements.txt files.

  • Removed empty test.py file.

  • Added links to Youtube videos for this project in README.md, as silasneo/scrape-master fork did.

Add configuration files and update README for Streamlit configuration
When using generic openai-compatible model, the chat completation call is using client as recommended in v1.0 API.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant