#document-conversion

• Sat, Aug 23, 2025. Codex and Codex CLI now support image attachments. #document-conversion

• Wed, Aug 20, 2025. ⭐ Policy-as-code is an emerging theme. Allow users to create their own guardrails policy. Or, take existing policy documents and convert them into an LLM-based evaluator. Krishnakumar Menon #ai-coding #code-agents #document-conversion #future #llm-ops

• Sat, Aug 16, 2025. ⭐ LLMs can hyper-personalize demos. E.g. an LLM document generator demo accepts a role, document type, and prompt. The demo-er says "Bank, LinkedIn marketing" and the LLM auto-populates the fields aptly, re-purposing the demo. #document-conversion #future #llm-ops #markdown

• Tue, Aug 12, 2025. Increasing the size of an image improves OCR accuracy for LLM models (or at least Claude 4 Sonnet). Anecdotally, resizing 2x did not work on a number of examples but 2.5x - 3x did. This increases the cost to 6.25x or 9x, however. #document-conversion #image-generation

• Tue, Aug 5, 2025. defuddle can be used in the browser to get the main content from web pages. A replacement for Mozilla Readability. # #document-conversion #html #markdown #web-dev #faq

• Fri, Aug 1, 2025. Teaching vibe coding is satisfying, too. I guided a developer to write a Python workflow by providing 2 prompts. Both of these were one-shotted by Claude 4 Sonnet. The entire process took 20 min with me guiding them over the phone. #ai-coding #code-agents #document-conversion #prompt-engineering #write
  • "Write a Python script to extract a page from a PDF file and save it." Followed by "Write minimal code. Drop error handling."
  • "Write a Python script to pass a PDF file to an LLM for OCR and print the result. Use this code sample... [PASTED CODE]." Followed by "Write minimal code. Drop error handling."

• Mon, Jun 30, 2025. ⭐ When bringing in humans-in-the-loop, applications must make it easier to review and to edit the work. #automation #best-practices #document-conversion #future #optimization #prompt-engineering #write

• Mon, Jun 23, 2025. XConvert is a convenient online app to compress .webm videos. Not great design but fairly good compression. #document-conversion #web-dev

• Sun, Jun 15, 2025. Documentation can become technical debt. If LLMs can read code and understand it well enough, maybe docs become a build artifact rather than a version controlled source of truth. Refactoring Podcast: The Future of Dev Tools 🔧 — with Dennis Pilarinos 35:56 #document-conversion #github #markdown #ai-coding

• Fri, Jun 13, 2025. PDF plumber seems a good way to extract PDF structure and internals. #document-conversion

• Tue, May 27, 2025. When processing presentations for RAG via OCR: #document-conversion
  • How to parse PDF docs for RAG is a useful OpenAI cookbook with a GPT 4o prompt

• Sun, May 11, 2025. Pandoc has several options useful when converting Markdown to HTML (cat file.md | pandoc -f markdown -t html). My favorites: #document-conversion #html #markdown
  • --no-highlight skips code-highlighting. --highlight=pygments adds Pygments styling
  • --wrap=none doesn't wrap the content in a single block
  • --number-sections adds section numbering (<h2>1. Introduction</h2>)
  • --shift-heading-level-by=NUM – shift all headings by NUM levels (e.g., start at <h2> instead of <h1>)
  • pandoc -f markdown-auto_identifiers drops the auto-identifiers extension that generates id=... for each heading
  • pandoc -f gfm uses GitHub flavored Markdown. Run pandoc --list-extensions=gfm to identify the extensions it uses.
  • Pandoc's Markdown extension examples are quite extensive.
  • Auto-enabled GFM extensions:
    • alerts: GitHub-style callouts (info, tip, warning) via > [!TYPE] blocks.
    • autolink_bare_uris: Turns bare URLs into links, without needing <...>.
    • emoji: Parses :smile:-style codes into Unicode emoji characters.
    • footnotes: Enables footnote syntax with [^id] and definitions at the bottom.
    • gfm_auto_identifiers: Uses GitHub’s heading-ID algorithm: spaces → dashes, lowercase, removes punctuation.
    • pipe_tables: Enables table.
    • raw_html: Raw HTML is unchanged.
    • strikeout: Enables strikethrough with ~~text~~.
    • task_lists: Parses - [ ] and - [x] items as checkboxes.
    • yaml_metadata_block: YAML front matter for document metadata, e.g. <title>
  • GFM extensions worth enabling:
    • ascii_identifiers: Strips accents/non-Latin letters in automatically generated IDs.
    • bracketed_spans: [Warning]{.alert} becomes <span class="alert">
    • definition_lists: Term\n: Definition text becomes a definition list
    • fenced_divs: ::: {.note} block creates a <div class="note">...</div>
    • implicit_figures: Standalone images become <figure> with <figcaption>.
    • implicit_header_references: [Section] is treated as [Section][#section]
    • raw_attribute: <b>bold</b>{=html} is inserted as HTML
    • smart: Converts straight quotes to curly, -- to en-dash, --- to em-dash, ... to ellipsis.
    • subscript & superscript: E.g. H~2~O and E = mc^2^

• Sat, May 10, 2025. snapdom is a fast, light, element capture alternative to html2canvas but doesn't work well with non-CORS images or iframes. #document-conversion #html

• Tue, Apr 22, 2025. You can run xclip -sel clip -o | pandoc -f markdown -t html --no-highlight | xclip -sel clip -t text/html -i to convert Markdown in the clipboard to rich text. But xclip doesn't support multiple selections, so the text is lost. ChatGPT #document-conversion #markdown

• Thu, Apr 10, 2025. Claude 3.7 Sonnet with extended thinking has a token limit of over 64,000 tokens. Given a strong instruction following capability, that makes it one of the most powerful models for transforming text. For example, transcription restyling, translations, XML to json conversions, PDF to XML, etc. #document-conversion #markdown #speech-to-text

• Tue, Apr 8, 2025. Claude 3.7 Sonnet with extended thinking has a token limit of over 64,000 tokens. Given a strong instruction following capability, that makes it one of the most powerful models for transforming text. For example, transcription restyling, translations, XML to json conversions, PDF to XML, etc. #document-conversion #markdown #speech-to-text

• Tue, Apr 8, 2025. One way to copy as Markdown: copy page contents, paste in text-html.com, copy HTML, paste in Turndown, copy Markdown. #document-conversion #html #markdown #write

• Thu, Apr 3, 2025. Clipboard2Markdown is a utility that lets you paste rich text and convert it to Markdown. #document-conversion #html #markdown

• Wed, Mar 19, 2025. OpenAI now supports PDFs natively in the API. (Gemini has done so for a while) #document-conversion

• Sun, Mar 16, 2025. Monolith downloads web pages as a single HTML file by embedding content. #document-conversion #html #web-dev

• Sat, Mar 15, 2025. There's a PDF UA2 standard for accessibility but there aren't enough tools to generate it. #document-conversion

• Sat, Mar 15, 2025. LibreOffice is now on WASM. ZetaJS provides office in the browser. Has a CDN (that was down from our IP). 35M packaged binary. 100M of in-memory file-system loaded. #document-conversion #html #markdown #web-dev
  • Useful for: Document conversion, Thumbnail generation, Text extraction, Merging / splitting documents

• Sat, Mar 8, 2025. "Export to prompt" can be a useful feature in apps (or even as a bookmarklet). It would let you export content in an LLM-friendly Markdown format. You can paste it into an LLM and ask questions. Here are things I would find useful: #document-conversion #github #markdown #prompt-engineering
  • Copy an entire issue (with history) from GitHub, Gitlab, or JIRA
  • Copy an entire PR (with code changes) from GitHub, Gitlab, or Bitbucket
  • Copy CI/CD logs from GitHub Actions, Gitlab CI, Azure DevOps, etc.
  • Copy entire conversation thread in Gmail or Discourse, Service now etc.
  • Copy product reviews from Amazon, Shopify, etc.
  • Copy page(s) from wikis and content sites like Wikipedia, StackOverflow, etc.
  • Copy survey responses from Google Forms, Typeform, etc.
  • Copy all interactions with a contact (including interactions, proposal history) from HubSpot or Salesforce
  • Copy transcripts from Zoom, Teams, Google Meet, etc.
  • Copy as Markdown from Word, GDocs, PDF or HTML
  • Copy the summary of an analysis as well as all key metrics from any dashboard
  • Copy SAP invoices
  • Copy JDs, CVs, and reviews from Workday, BambooHR, DarwinBox, etc.
  • Copy design specs, component libraries, and style guides from Figma, Miro, etc.
  • Generated with the help of ChatGPT -- link not working

• Fri, Mar 7, 2025. Mistral released an impressive OCR model. #document-conversion #github #gpu #markdown
  • Marker from DataLab seems comparable but is CC-BY-NC-SA.
  • MinerU convert medical textbooks to Markdown well.
  • Gemini Flash may be more cost effective and better

• Sat, Feb 1, 2025. You can add any content at the end of a PDF file. It's ignored. It's an interesting way to send additional information (or just blow up the file size if you don't like them.) #document-conversion

• Thu, Jan 2, 2025. Tools that convert files to prompt / Markdown suitable for LLMs: #document-conversion #github #markdown
  • uvx files-to-prompt
  • npx git-ingest
  • ingest - written in Go, only Mac/Linux binaries

• Thu, Jan 2, 2025. uvx doc2docx converts Word .doc files to the new .docx format. I had several old .doc files that I converted. #document-conversion

• Mon, Dec 23, 2024. Document to Markdown Converters: #document-conversion #markdown
  • PyMuPDF4LLM uses MuPDF. Requires PyTorch.
    • PYTHONUTF8=1 uv run --with pymupdf4llm python -c 'import pymupdf4llm; h = open("pymupdf4llm.md", "w"); h.write(pymupdf4llm.to_markdown("$FILE.pdf"))'
  • markitdown from Microsoft. PDF via PDFMiner, DOCX via Mammoth, XLSX via Pandas, PPTX via Python-PPTD, ZIP, etc.
    • PYTHONUTF8=1 uvx markitdown $FILE.pdf > markitdown.md
  • Docling by IBM. Unable to install via pip on Windows AND on Linux.
  • MegaParse uses libreoffice, pandoc, tesseract-ocr, etc. Requires OpenAI API key.

• Sun, Dec 22, 2024. aspose-words is a Python library that converts documents with many formats (Word, RTF, PDF, HTML, Markdown, EPUB, etc.) #document-conversion

• Tue, Nov 26, 2024. CloudFlare workers can bundle any kind of files, including text, data, and WASM. Docs #cloud #document-conversion #markdown

• Mon, Nov 25, 2024. Crawl4AI and Firecrawl are tools / libraries to convert websites into LLM Friendly Markdown and extract structured data using LLMs. #ai-coding #code-agents #document-conversion #html #llm-ops

• Sat, Nov 23, 2024. A list of Markdown to Website converters on this thread: #document-conversion #github #html #markdown
  • Jekyll - Ruby - 2008
  • MkDocs - Python - 2014
  • GitBook - JavaScript (Node.js) - 2014
  • MkDocs Material - Python (MkDocs-based) - 2016
  • Docsify - JavaScript - 2016
  • MdBook - Rust - 2017
  • Antora - JavaScript (Node.js) - 2017
  • Docusaurus - JavaScript (React) - 2017
  • JupyterBook - Python - 2019
  • Keenwrite - Java - ~2019
  • Honkit - JavaScript (GitBook fork) - 2019
  • Nextra - JavaScript (Next.js) - 2020
  • Astro - JavaScript/TypeScript - 2021
  • Hugo Book - Go (Hugo-based) - ~2020
  • Clowncar - JavaScript/Node.js - ~2021
  • Quarto - R and Python - 2022
  • Starlight - JavaScript/TypeScript - 2023

• Wed, Nov 6, 2024. Docling by IBM converts PDF, DOCX, etc. to Markdown. Like PyMuPDF4LLM but better. #document-conversion #markdown

• Sat, Sep 28, 2024. PyMuPDF4LLM can convert PDFs to Markdown. It handles tables, too. #document-conversion #llm-ops #markdown
  • 04 Oct 2024. PDF-Extract-Kit does PDF layout, formula, table, and OCR extraction using various models.
  • 04 Oct 2024. llmsherpa extracts PDF layout, tables, not OCR

• Thu, Sep 12, 2024. Pixtral seems quite good at OCR #document-conversion #future #speech-to-text

• Tue, Aug 20, 2024. Lumentis creates docs from transcripts and text #document-conversion #future #github #speech-to-text

• Sun, Aug 11, 2024. DocxTemplater is SlideSense but open-core and handles DOCX as well! #document-conversion #html #markdown

• Sun, Apr 14, 2024. llmsherpa extracts PDFs using LLMs. It has errors but it preserves hierarchy, extracts tables well, and retains image coordinates. Via +91 90031 35354 ~Vetrivel PS #document-conversion #llm-ops

• Tue, Feb 20, 2024. Adobe express has a forever free video to GIF converter #document-conversion

• Wed, Jan 3, 2024. Adobe Firefly offers a "generative fill" that lets you remove or paint new objects into an image. I'm awaiting text to vector images. #document-conversion #future #image-generation

• Wed, Dec 27, 2023. Lica has a fascinating demo of how a document can be converted into a video story. #document-conversion

• Sun, Dec 3, 2023. Microsoft released table-transformer to extract tables from PDFs. Sample usage #document-conversion

• Sun, Dec 3, 2023. Convert PDF to markdown with marker - an improvement over nougat. #document-conversion #markdown

• Thu, Nov 30, 2023. CoVA scrapes web pages via OCR #ai-coding #code-agents #document-conversion

• Sat, Nov 4, 2023. 04 Nov 2023: Seamless4MT does language and speech inter-conversion. CC-NC-BY license #document-conversion #speech-to-text #tts #voice-cloning #faq