Outer Web | Explore

Explore >> Select a destination

You are here		blog.pamelafox.org RAG techniques: Function calling for more structured retrieval
\|	\|	isthisit.nz Prompting GPT Models to Return JSON	2.6 parsecs away Travel
\|	\|	August 2024 Update: Now a solved problem. Use Structured Outputs. Large language models (LLMs) return unstructured output. When we prompt them they respond with one large string. This is fine for applications such as ChatGPT, but in others where we want the LLM to return structured data such as lists or key value pairs, a parseable response is needed. In Building A ChatGPT-enhanced Python REPL I used a technique to prompt the LLM to return output in a text format I could parse.	2.6 parsecs away Travel
\|	\|	newvick.com Evolution of RAG: Addressing the common problems of a simple RAG system ? Newvick's blog	2.5 parsecs away Travel
\|	\|	RAG is not all you need. This post will cover some of the common problems that are encountered in a simple RAG system, and potential solutions for them.	2.5 parsecs away Travel
\|	\|	simonwillison.net Building search-based RAG using Claude, Datasette and Val Town	2.5 parsecs away Travel
\|	\|	Retrieval Augmented Generation (RAG) is a technique for adding extra "knowledge" to systems built on LLMs, allowing them to answer questions against custom information not included in their training data. ...	2.5 parsecs away Travel
\|	\|	www.onlandscape.co.uk Winter Forest \| On Landscape	7.6 parsecs away Travel
\|		[AI summary] The article discusses privacy and cookie policies for the online magazine 'On Landscape' focusing on user data collection and website functionality.	7.6 parsecs away Travel