Introduction to LMQL
SQL offers a widely used way to talk to your data in a database. So, says Mariya Mansurova, it’s not surprising to see a similar approach for large language models (LLMs).
“LMQL (Language Model Query Language) is an open-source programming language for language models. LMQL is released under Apache 2.0 license, which allows you to use it commercially,” Mansurova says.
This article provides an introduction to LMQL with a look at both benefits and limitations.
Read more at Towards Data Science.
Related content
-
Chatbots put to the scripting test
The AI skillset is currently limited, so you don't yet have to worry about AI replacing programmers. We look at the capabilities of AI scripting with free large language models and where it works best. -
Selecting compilers for a supercomputer
If you compile software on an expensive supercomputer, it's a good idea to select the languages and compilers with particular care. We report on the tried-and-proved tools used on SuperMUC, a supercomputer at the Leibniz Supercomputing Center in Germany. -
Selecting Compilers for a Supercomputer
If you compile software on an expensive supercomputer, its a good idea to select the languages and compilers with particular care. We report on tried-and-proved tools used on SuperMUC, a supercomputer at the Leibniz Supercomputing Center in Germany.
-
The basics of domain-driven design
Domain-driven design addresses many aspects of software development, from the design of entire software landscapes and the relationships between (sub)systems to the design of domain models, patterns, and code. -
Operating large language models in-house
An internal AI server is an interesting way to retain data sovereignty. We show you how to set up an in-house AI server on your hardware and use it in parallel with AI services such as ChatGPT in the cloud.