Explore >> Select a destination
|
You are here 
|
www.promptingguide.ai | ||
| | | | |
neptune.ai
|
|
| | | | | LLMs can be used to extract insightful information from structured data, help users perform queries, and generate new datasets. | |
| | | | |
ollama.com
|
|
| | | | | 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. | |
| | | | |
isthisit.nz
|
|
| | | | | 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. | |
| | | | |
chrisdaleoxford.com
|
|
| | | I have found out how to make things happen in eDiscovery / eDisclosure. You publish an article opening with a sentence like this: We are a bit short of useful or interesting judgments about disclosure in England and Wales at the moment. ...just before you take a few days off. That brings all the interesting... | ||
