Retrieval augmented generation in R using the ragnar package. Demonstration: scraping text from relevant links on a website and using RAG to ask about a university's grant funding.
Intent context defines what the user wants to get out of the model. For example, a system prompt usually serves as high-level instructions for how the user wants the model to behave. Most of the “prompting” done in Cursor is intent context. “Turn that button from blue to green” is an example of stated intent; it is prescriptive.
State context describes the state of the current world. Providing Cursor with error messages, console logs, images, and chunks of code are examples of context related to state. It is descriptive, not prescriptive.
Together, these two types of context work in harmony by describing the current state and desired future state, enabling Cursor to make useful coding suggestions.
Building a webapp for data collection & visualization using R Shiny
This is a tutorial post about building a webapp with user form and leaflet map visualization using R Shiny. The webapp I built aims to collect crowdsourced data of how sustainable are the eateries …
Paths contain responses. When 200 responses are available, use those to define a parser function. Specs might (probably will) be repeated, so refine to just one copy of each. Names will have to be ...
Tests via examples · Issue #70 · jonthegeek/beekeeper
Use response examples to build "mocked" responses for use in tests. While implementing this I'll have to figure out what to do about args. Some set of standard args (by type) that I encourage users...
So far I've had to do manual work to cleanly parse responses. Document that process. It's POSSIBLE the result of this ticket will actually be functionality to implement this automatically, but righ...
LightBox Zoning API | Developer Portal | SmartFabric | CRE
Enhance your CRE and development business with a lightweight Zoning API. Access robust Zoning information in our comprehensive developer portal to maximize ROI
Upload, download, and edit internet maps with the Felt API (). Allows users to create new maps, edit existing maps, and extract data. Provides tools for working with layers, which represent geographic data, and elements, which are interactive annotations. Spatial data accessed from the API is transformed to work with sf.