Render a template for a specific section. Args: section_name (str): Name of the section (basics, work, education, etc.)

Helper function to extract profile information for a given network.

Send a chat request to the LLM provider.

Check if middle of rect is contained in a rect of the list.

Optionally render the rect part of a page. We will ignore images that are empty or that have an edge smaller than x% of the correspon

Extract JSON content from markdown code blocks. Args: response_text: Text that may contain JSON wrapped in markdown code blocks

Initialize the appropriate LLM provider based on the model name. Args: model_name: The name of the model to use Returns:

Accept a span and return a markdown link string. Args: links: a list as returned by page.get_links() span: a span dic

Output the text found inside the given clip. This is an alternative for plain text in that it outputs text enriched with markdown sty

Match parts of text to specific links based on content and position.

Check if the resume data has at least some extracted core content.

Output images and graphics above text rectangle.

Output tables above given text rectangle.

Parse date range and return both start and end dates. For format like "Jan-Mar 2021", returns ("Jan 2021", "Mar 2021")

Evaluate the resume using AI and display results.

Initialize the appropriate LLM provider based on the model.

Initialize the appropriate LLM provider based on the model.

Load all available templates.

Match individual words to links based on position and content.

Resolve multiple links within a single span text. Args: span_text: The text content of the span links: List of overla

Get list of available section names. Returns: list: List of available section names

Determine the background color of the page. The function returns a PDF RGB color triple or None. We check the color of 10 x 10 pixel

Process one page. Args: doc: pymupdf.Document pno: 0-based page number textflags: text extraction flag bi

Check if rect is contained in a rect of the list.

Check whether the rectangle "box" contains 'signifiant' drawings. This means that some path is contained in the "interior" of box. To this en

Check if page exclusivley contains OCR text. For this to be true, all text must be written as "ignore-text".

Print evaluation results in a readable format.

Join any rectangles with a pairwise non-empty overlap. Accepts and returns a list of Rect items. Note that rectangles that only "touch" each

Reorder words in lines. The argument list must be presorted by bottom, then left coordinates. Words with similar top / bottom coordi

Process the document and return the text of the selected pages. Args: doc: pymupdf.Document or string. pages: list of page number

Transform the three inputs (resume_data, github_data, evaluation) into the most important columns as a CSV row. Args: resume_data: J

Read all text and make a dictionary of fontsizes. Args: doc: PDF document or filename pages: consider these page numb

Read and store the TOC of the document.

Initialize the template manager. Args: template_dir (str): Directory containing Jinja templates

Send a chat request to Ollama.

Send a chat request to Google Gemini API.

Return appropriate markdown header prefix. Given a text span from a "dict"/"rawdict" extraction, determine the markdown header prefix

Return appropriate markdown header prefix. Given a text span from a "dict"/"rawdict" extraction, determine the markdown header prefix