/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

 softwaredoug.com
General purpose agentic loop in 40 lines of Python
| | ollama.com
Streaming responses with tool calling ยท Ollama Blog
3.1 parsecs away

Travel
| | Ollama now supports streaming responses with tool calling. This enables all chat applications to stream content and also call tools in real time.
| | isthisit.nz
Prompting GPT Models to Return JSON
4.0 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.
| | strathweb.com
Tool Calling with Azure OpenAI - Part 1: The Basics | Strathweb. A free flowing tech monologue.
4.8 parsecs away

Travel
| | [AI summary] This blog post introduces the fundamentals of tool calling in Azure OpenAI, explaining how large language models select and invoke application tools to orchestrate workflows.
| | til.simonwillison.net
A simple Python wrapper for the ChatGPT API | Simon Willison's TILs
8.0 parsecs away

Travel
| OpenAI released an API for ChatGPT yesterday. It's 1/10th of the price of the text-davinci-003 model!