Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Add text2sql blog post #1558

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 8 commits into
base: main
Choose a base branch
from
Draft

Add text2sql blog post #1558

Changes from 1 commit
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
c664f26
add blog post
perlitz Jan 27, 2025
7821516
update blog post
perlitz Jan 27, 2025
586119f
add citation
perlitz Jan 27, 2025
8e26fc6
add citation
perlitz Jan 27, 2025
049a24d
add citation
perlitz Jan 27, 2025
6c97019
Merge branch 'main' into add-text2sql-blog-post
perlitz Jan 30, 2025
d93217b
update blog
perlitz Jan 30, 2025
6e8467a
exit metric when gt is returning None
perlitz Feb 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
add citation 
Signed-off-by: Yotam-Perlitz <[email protected]>
  • Loading branch information
@perlitz
perlitz committed Jan 27, 2025
commit 049a24ddd52903725dd52e4e2a01d61c32a9ee1e
7 changes: 2 additions & 5 deletions docs/blog/text2sql_blog.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@ Let’s break down this code step-by-step to understand the magic happening behi

1. **Loading the Dataset: Setting the Stage**

We kick things off by loading the [BIRD validation dataset]_ using the ``load_dataset`` function. Here, we specify the dataset card (``cards.text2sql.bird``) and the template (``templates.text2sql.you_are_given_with_hint_with_sql_prefix``). This template acts as a guide, instructing Unitxt on how to format natural language queries into well-structured SQL prompts for the model. **Note** that this is where much of the magic happens—when the template is rendered, the database is accessed, and the schema is fetched.
We kick things off by loading the [BIRD validation dataset](https://bird-bench.github.io/) using the ``load_dataset`` function. Here, we specify the dataset card (``cards.text2sql.bird``) and the template (``templates.text2sql.you_are_given_with_hint_with_sql_prefix``). This template acts as a guide, instructing Unitxt on how to format natural language queries into well-structured SQL prompts for the model. **Note** that this is where much of the magic happens—when the template is rendered, the database is accessed, and the schema is fetched.

2. **Setting Up Inference: Choosing Your Powerhouse**

Expand Down Expand Up @@ -126,7 +126,4 @@ Conclusion: Shaping the Future of Data Interaction – Empowering Everyone with

Unitxt’s groundbreaking Text-to-SQL evaluation feature is a game-changer for developers working on models that aim to translate natural language into SQL queries. By providing an automated, standardized, and rigorous evaluation framework, Unitxt dramatically accelerates the development of more accurate, reliable, and user-friendly Text-to-SQL systems.

We invite you to dive into this exciting new feature and join us on this journey to shape the future of data interaction. With Unitxt, you can unlock the true potential of your data, making it more accessible than ever before. Empower everyone—regardless of their SQL expertise—to effortlessly query, explore, and understand the wealth of information hidden


[BIRD validation dataset]_ https://bird-bench.github.io/
We invite you to dive into this exciting new feature and join us on this journey to shape the future of data interaction. With Unitxt, you can unlock the true potential of your data, making it more accessible than ever before. Empower everyone—regardless of their SQL expertise—to effortlessly query, explore, and understand the wealth of information hidden
Loading