Markdown: An effective tool for LLM interaction
Introducing 'Mark', a Markdown CLI tool for seamless interaction with GPT-4o models. It enables in-document threaded conversations, image tags, link references, and extensibility through standard input. Mark enhances user experience by optimizing interactions with LLMs. Installation requires an OpenAI API key and Python 3.10+.
Read original article
Introducing 'Mark', a Markdown CLI tool designed to interact with GPT4o models seamlessly. Mark allows users to create in-document threaded conversations with GPT, incorporating responses back into the document. It supports image tags for visual context and link references for effective RAG retrieval. The tool is extensible, enabling users to pipe content through standard input for GPT responses. Markdown's compatibility with version control systems and modern IDEs enhances the user experience. By leveraging Markdown's simplicity and structure, Mark optimizes interactions with LLMs, emphasizing key parts and providing context for better responses. The tool's key features include in-document thread building, GPT Vision with image tags, RAG using links, and custom system prompts. Mark's installation requires an OpenAI API key and Python 3.10+. With use cases ranging from extracting data from screenshots to getting personalized coding help, Mark streamlines interactions with GPT-4, offering a robust and efficient solution for developers and writers.
Related
The Death of the Junior Developer – Steve Yegge
The blog discusses AI models like ChatGPT impacting junior developers in law, writing, editing, and programming. Senior professionals benefit from AI assistants like GPT-4o, Gemini, and Claude 3 Opus, enhancing efficiency and productivity in Chat Oriented Programming (CHOP).
The Eternal Truth of Markdown
Markdown, a simplified code alternative to HTML, enables diverse document formats from plain text. Despite lacking standardization, it thrives for its adaptability and simplicity, appealing to writers and programmers alike.
OpenAI releases ChatGPT on your desktop for macOS
OpenAI released ChatGPT for macOS, enabling desktop users to chat about various topics, access features like screenshots and file sharing, and enhance productivity. The app plans to expand to Windows.
Our guidance on using LLMs (for technical writing)
The Ritza Handbook advises on using GPT and GenAI models for writing, highlighting benefits like code samples and overcoming writer's block. However, caution is urged against using GPT-generated text in published articles.
GraphRAG (from Microsoft) is now open-source!
GraphRAG, a GitHub tool, enhances question-answering over private datasets with structured retrieval and response generation. It outperforms naive RAG methods, offering semantic analysis and diverse, comprehensive data summaries efficiently.
7 commentsecho "Please explain this code: $(cat some_class.py)" | mark
needs a dash at the end to work correctly. Also, it doesn't output pandoc-flavored markdown (blank lines before headings and code chunks) unless I specifically ask it to, as in:
echo "Please explain this code, using pandoc-flavored markdown, leaving a blank line before headings and code chunks: $(cat some_class.py)" | mark -
I mostly use local models. I might modify 'mark' myself, or wait a while and see if anyone does a pull request.
A little off topic, but I run ollama at the command line using:
echo "what is 1 + 3?" | ollama run llama3:latest
danielmiessler.com/p/fabric-origin-story
together with obsidian is my setup I am trying to build now. I'm using obsidian to plan the vector and meta data to pull and reference with the assistants and building function tools to query.
I think Ryan Elston's blog post is more effective in explaining the advantages of markdown for LLM interaction.
Related
The Death of the Junior Developer – Steve Yegge
The blog discusses AI models like ChatGPT impacting junior developers in law, writing, editing, and programming. Senior professionals benefit from AI assistants like GPT-4o, Gemini, and Claude 3 Opus, enhancing efficiency and productivity in Chat Oriented Programming (CHOP).
The Eternal Truth of Markdown
Markdown, a simplified code alternative to HTML, enables diverse document formats from plain text. Despite lacking standardization, it thrives for its adaptability and simplicity, appealing to writers and programmers alike.
OpenAI releases ChatGPT on your desktop for macOS
OpenAI released ChatGPT for macOS, enabling desktop users to chat about various topics, access features like screenshots and file sharing, and enhance productivity. The app plans to expand to Windows.
Our guidance on using LLMs (for technical writing)
The Ritza Handbook advises on using GPT and GenAI models for writing, highlighting benefits like code samples and overcoming writer's block. However, caution is urged against using GPT-generated text in published articles.
GraphRAG (from Microsoft) is now open-source!
GraphRAG, a GitHub tool, enhances question-answering over private datasets with structured retrieval and response generation. It outperforms naive RAG methods, offering semantic analysis and diverse, comprehensive data summaries efficiently.