Outer Web | Explore

/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.

You are here		til.simonwillison.net Using the ChatGPT streaming API from Python \| Simon Willison's TILs
\|	\|	isthisit.nz Prompting GPT Models to Return JSON 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.	2.3 parsecs Travel
\|	\|
\|	\|	blog.pamelafox.org Fetching JSON over streaming HTTP Recently, as part of my work on Azure OpenAI code samples, I've been experimenting with different ways of streaming data from a server i...	2.3 parsecs Travel
\|	\|
\|	\|	blog.miguelgrinberg.com Eliza-GPT: The Classic ELIZA Chatbot Running On OpenAI's Chat Completions API - miguelgrinberg.com miguelgrinberg.com	2.5 parsecs Travel
\|	\|
\|	\|	jsloop.net JAX-RS 3 API Server with Jetty 11 \| jsloop Here is a basic server setup with JAX-RS 3 using Jersey and Jetty 11 for the server. JAX-RS is Java API specification for RESTful web services using annotations. The project structure is as follows.	18.0 parsecs Travel
\|