👤  lecture style summary

Content

- type: ask
  param: p1
  message: 'Please provide content:'
  default: '{{page}} {{youtube.transcript}}'
- type: gpt
  prompt: >-
    You are an adept college professor, skilled in crafting insightful notes. 


    Your task is to condense given text into a cheatsheet-style lecture note
    with markdown syntax. This summary should be detailed, including key steps,
    codes, figures (as markdown images),  equations, and additional notes
    necessary for understanding and utilizing the information without referring
    back to the original text. When formatting display equations, use only
    "$$...$$" as delimiters, never use "\(...\)" or "\[...\]".  Pay special
    effort to preserve coding examples and images.  Include the given chunk
    number in the H1 title '# <TITLE> (part X/<total>, REF Y)' where part is the
    trunk # given, and REF is section or timestamp in the text.  Use H2,H3,H4
    for sections, put original section if available in brackets like "## summary
    title (REF #original)'.  Indented lists can't contain indented lists, but
    don't omit details. Study questions and exercises can be omitted.


    [CONTENT TO SUMMARIZE]: 

    ```

    --begin text chunk {{chunk.index}} of {{chunk.total}} chunks--

    {{chunk}}

    --end text chunk {{chunk.index}} of {{chunk.total}} chunks --

    ```

    lecture note:

    # [title] ({{chunk.index}} of {{chunk.total}} )
  chunkify:
    text: '{{p1}}'
    maxTokens: 4500
    empty: ''
  isolated: false
  param: gpt
- type: js
  code: |2-

              const patterns = [
                  { regex: /^\s*\$\s*\n/g, replacement: "\$\$\n" },
     { regex: /\\Perp/g, replacement: "\\perp" },
                  { regex: /\\\(|\\\)/g, replacement: "\$" },
                  { regex: /\$\$\$/g, replacement: "\$\$" },
                  { regex: /^\s+!/gm, replacement: "!" },
                  { regex: /^\s+\$\$\s*\n/g, replacement: "\$\$\n" },
                  { regex: /-\s+!\[/gm, replacement: "!\[" },
    { regex: /boldbold/g, replacement: "boldsymbol" },
    { regex: /boldboldbold/g, replacement: "boldsymbol" },
    { regex: /-\s+!\[/g, replacement: "!\[" },
    { regex: /^\s\s\s\s/g, replacement: "  "}, 

              ];
              
              let result = gpt;
              for (const pattern of patterns) {
                  result = result.replace(pattern.regex, pattern.replacement);
              }
              return result;
          
  param: result
  timeout: 15000
  args: gpt
- message: '{{result}}'
  type: say