Intro
Let's discover Blaze in less than 5 minutes.
BLAZE - Building Language Applications Easily 🔥
tl;dr - Cisco Research proudly presents BLAZE, a flexible, standardized, no-code, open-source platform to easily assemble, modify, and deploy various NLP models, datasets, and components
Check out our TechBlog and Homepage for more information and exciting applications!
Further technical documentation can also be found at our Cisco Research GitHub Pages.
Section-specific documentation can be found at the following smaller
README.md's:
- Drag-and-Drop YAML Builder -
drag/README.md- Generated YAML Files Folder -
yaml/README.md- Models Usage Instructions -
backend/models/README.md
What is BLAZE?
BLAZE is designed to streamline the integration of Natural Language Pipelines into software solutions1. We offer an open, extensible framework to benchmark existing solutions and compare them with novel ones.
The building blocks of BLAZE are flexible blocks of the NLP pipeline. The functionality of different stages in the pipeline are abstracted out to create blocks that can be combined in various ways. Users can arrange these Lego-like blocks to create new recipes of varying NLP pipelines.
In such, BLAZE will help democratize NLP applications, providing a no-code solution to experiment with SOTA research and serving as a framework to implement NLP pipeline recipes into usable solutions.