/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

 josephm.dev
Return JSON from GPT
| | ollama.com
Tool support · Ollama Blog
1.5 parsecs away

Travel
| | Ollama now supports tool calling with popular models such as Llama 3.1. This enables a model to answer a given prompt using tool(s) it knows about, making it possible for models to perform more complex tasks or interact with the outside world.
| | blog.miguelgrinberg.com
Eliza-GPT: The Classic ELIZA Chatbot Running On OpenAI's Chat Completions API - miguelgrinberg.com
1.2 parsecs away

Travel
| | miguelgrinberg.com
| | isthisit.nz
Prompting GPT Models to Return JSON
1.2 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.
| | msfjarvis.dev
Support multiple authentication methods by fmeum · Pull Request #825 · android-password-store/Android-Password-Store · GitHub
6.4 parsecs away

Travel
| Type of change Bugfix New feature Enhancement Refactoring Description Add support for multiple authentication methods by offering password authentication after public key authentication. Along the way, refactor GitOperation to use a (somewhat) proper builder pattern. This uncovered that we were previously not using SSHJ for the case of no authentication, which is now rectified. Motivation and Context Fixes #333, fixes #548 and fixes #782 if it works. How did you test it? I lack the setup to test ...