DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use Quail: what you can do with it

Quail is an open-source inference engine that runs LLM-powered AI functions over large datasets from SQL on your own GPUs.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Filter table rows with an LLM question in SQL

    Keep only the rows where a language model answers yes to a question about the text.

    View prompt
    Use the Python package quail-engine (import quail) in the repo fsdatalab/quail to filter the table <table_name> with a BigQuery-style AI.IF question about column <text_column>. Return the matching id values as a table. Verify that the number of returned rows is less than or equal to the input row count.

  • Extract answers from a text column with AI.EXTRACT

    Pull a short answer to a question out of each row's text in one SQL query.

    View prompt
    Use the Python package quail-engine (import quail) from the repo fsdatalab/quail to run AI.EXTRACT over the text column <text_column> of the table <table_name> with the question <question>. Output a table of id and extracted answer. Verify that every id in the input appears in the output.

  • Run a long LLM query on a GPU server and reconnect later

    Submit a query to a Quail Server on your GPU machine, disconnect, and fetch results later.

    View prompt
    Use the repo fsdatalab/quail to submit the SQL query in <sql_file> to a Quail Server at <server_address>, save the query id, and later call get_run to fetch the result table. Output the final table as CSV. Verify that the server returned a completed status before collecting results.

  • Run Snowflake AI_FILTER style queries on your own GPU

    Reuse Snowflake-style AI_FILTER SQL with Quail's dialect support on local GPUs.

    View prompt
    Use the Python package quail-engine (import quail) from the repo fsdatalab/quail to run the Snowflake-style AI_FILTER query in <query_file> against the table <table_name>. Output the filtered rows. Verify that the output matches the Snowflake result for a sample of 10 rows.

Quick start with Quail

  1. Check you have what it needs: Python 3.12; An NVIDIA CUDA GPU from the supported list (for example H100 SXM); uv installed to run the pip install command.
  2. Open fsdatalab/quail on GitHub and read the README and license.
  3. Run uv pip install quail-engine to install the package (the import name is Quail).
  4. Build a table with an id column and a text column, then register it with Quail.DocumentProvider.from_table(table, id_col="id").
  5. Create Quail.EngineConfig with a supported model and device, for example model="qwen3-4b-fp8" and device="h100-sxm".
  6. Open a Quail.Session, then run session.sql with a WHERE AI.IF(PROMPT('Your question\n\n{0}', r.body)) clause and dialect="bq".

These steps come from our top use case, Filter table rows with an LLM question in SQL, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for fsdatalab/quail

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Quail alternatives · Best AI repos for Data and analytics

About this repo

  • Who it is forData engineers and analysts with a CUDA GPU who want to run LLM filters, extraction, scoring, or classification over tables from SQL or Python.
  • Why it is hot168 stars, launched 84 days ago
  • LanguagePython
  • Sourcegithub.com/fsdatalab/quail · Back to Hot repos

Requirements

  • Python 3.12
  • An NVIDIA CUDA GPU from the supported list (for example H100 SXM)
  • uv installed to run the pip install command
  • A table of text rows (for example reviews with an id and a body column)

Add this badge to your README

Maintain Quail? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/fsdatalab/quail.svg)](https://dedupedai.com/use-cases/fsdatalab-quail/?utm_source=github&utm_medium=badge&utm_campaign=fsdatalab-quail)

HTML 

<a href="https://dedupedai.com/use-cases/fsdatalab-quail/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=fsdatalab-quail"><img src="https://dedupedai.com/badge/fsdatalab/quail.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Quail

What is Quail?

Quail is an open-source inference engine that runs LLM-powered AI functions over large datasets from SQL on your own GPUs. It is an open-source project on GitHub: https://github.com/fsdatalab/quail.

Who is Quail for?

Data engineers and analysts with a CUDA GPU who want to run LLM filters, extraction, scoring, or classification over tables from SQL or Python.

What can I do with Quail?

4 use cases so far, for example: Filter table rows with an LLM question in SQL; Extract answers from a text column with AI.EXTRACT; Run a long LLM query on a GPU server and reconnect later. Each has steps and a copy-paste agent prompt.

What do I need to run Quail?

Python 3.12; An NVIDIA CUDA GPU from the supported list (for example H100 SXM); uv installed to run the pip install command; A table of text rows (for example reviews with an id and a body column).

What are alternatives to Quail?

Other hot AI repos in Data and analytics: DSH Usage, Schemagate, Asobeast, Coreclaw API Directory, Nexus Pilot.

Is Quail safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.