Datasette Agent の初版リリース発表
Simon Willison が、Datasette のデータに自然言語で質問し、SQL クエリを自動生成して可視化も行う拡張可能な AI アシスタント「Datasette Agent」の初版リリースを発表した。
キーポイント
Datasette と LLM の統合実現
3 年以上開発してきた Python ライブラリ「LLM」と Datasette がついに統合され、データ分析における自然言語インターフェースが提供されるようになった。
チャート生成機能の追加
「datasette-agent-charts」プラグインを導入することで、単なるテキスト回答だけでなく、データの可視化チャートを自動生成する機能が強化された。
Gemini 3.1 Flash-Lite の採用
デモ環境ではコスト効率が高く高速な Gemini 3.1 Flash-Lite を使用しており、SQLite クエリの生成において高い精度を示している。
影響分析・編集コメントを表示
影響分析
この発表は、データ分析ツールと生成 AI の融合を具体化した重要な一歩であり、特に SQLite ベースの軽量なデータベース環境において、AI を活用した直感的なデータ探索を一般化する可能性があります。技術者以外でも自然言語でデータを問い合わせて可視化できるため、データ民主化の促進に寄与すると考えられます。
編集コメント
既存のデータ分析ツールに AI を組み込むことで、SQL の知識がなくても高度な分析が可能になる点は実用性が極めて高いと言えます。特に軽量な環境での適用事例は参考になります。
Datasette Agent の最初のリリースを発表しました。これは Datasette 向けの新しい拡張可能な AI アシスタントです。私は約 3 年ほど LLM という Python ライブラリの開発に取り組んできましたが、Datasette Agent は LLM と Datasette がついに融合した瞬間を表しています。これには本当に興奮しています!
Datasette Agent は、Datasette に保存されたデータに対して質問できる対話型インターフェースを提供します。datasette-agent-charts プラグインを追加すれば、データのチャート生成も可能です。
デモ
発表記事(新しい Datasette プロジェクトのブログ)には、この デモ動画 が含まれています:
*
私は、agent.datasette.io の新しいライブデモインスタンスに対して動画を撮影しました。ここでは Datasette Agent が、クラシックな global-power-plants(WRI による)や、私のブログの Datasette バックアップ のコピーなどを含む例題データベースに対して動作しています。
ライブデモは Gemini 3.1 Flash-Lite で実行されており、安価で高速であり、SQLite クエリの作成にも問題ありません。
デモで行った質問の一つは次の通りです:
**
Simon が最後にペリカンを見たのはいつですか?
この SQL クエリを実行しました こちら:
SELECT
title, commentary, created
FROM
blog_beat
WHERE
beat_type = 'sighting'
AND (title LIKE '%pelican%' OR commentary LIKE '%pelican%')
ORDER BY
created DESC
LIMIT
5
そして、以下のように回答しました:
Simon によるペリカンの最も最近の目撃情報は、2026 年 5 月 20 日に記録されています。**
その観察には、カリフォルニアブラウンペリカンに加え、オナガガモ、カナダガン、シマエビザメ(Striped Shore Crab)、およびカリフォルニアアシカが含まれていました。
こちらが 私のブログ上のその目撃情報 です。また、会話の完全なトランスクリプトの Markdown エクスポート も用意されています。
プラグイン
Datasette Agent のお気に入りの機能は、Datasette の他の部分と同様に、プラグインを使用して拡張可能である点です。
これまでに 3 つのプラグインをリリースしています:
- datasette-agent-charts は、動画で示されている通り、Observable Plot を活用して Datasette Agent にチャート機能を追加します。
- datasette-agent-openai-imagegen は、ChatGPT Images 2.0 を使用して Datasette Agent に画像生成ツールを追加します。
- datasette-agent-sprites は、Fly Sprites の永続サンドボックス内でコードを実行するためのツールを提供します。
プラグインの開発は本当に楽しいものです*。まだアルファ版の品質には達していないが、さらに多くのプロトタイプを持っています。
Claude Code と OpenAI Codex はどちらもプラグイン作成において非常に優秀です。datasette-agent リポジトリ のチェックアウトを参照先として指定し、何を構築したいかを伝えるだけで十分です!
ローカルモデルでの実行
新しいプラグインをローカルモデルで動かすのも楽しいものです。Mac 上の LM Studio で gemma-4-26b-a4b を対象にこのプラグインを実行するための uv のワンライナーは以下の通りです:
uvx --prerelease=allow \
--with datasette-agent --with llm-lmstudio \
datasette --internal internal.db --root \
-s plugins.datasette-llm.default_model lmstudio/google/gemma-4-26b-a4b \
data.db
Datasette Agent は、信頼性の高いツール呼び出しと、SQLite に対して実行可能な SQL クエリをモデルが生成できる能力を必要とします。過去 6 ヶ月間に公開されたオープンウェイトモデルは、この要件に対応する能力をますます高めています。
次のステップ
Datasette Agent は、LLM と Datasette エコシステム全体において*非常に多くの*機会を開きます。
すでに、安定版リリースに向けてほぼ準備ができている主要な LLM 0.32a0 リファクタリング the major LLM 0.32a0 refactor には通知済みです。もしかすると、Datasette Agent そのものから抽出された追加の「LLM エージェント」抽象化機能も含まれるかもしれません。
Claude Artifacts に対する独自の取り組みを模索しており、これがプラグインとして順調に形になってきています。
私は Datasette Agent を活用して、自分自身の Claw を構築することに興奮しています。これは、デジタルライフの異なる部分からインポートされたデータを基盤としたパーソナル AI アシスタントです。これは、古くからの Dogsheep ツールファミリーを見直すための素晴らしい言い訳でもあります。
また、Datasette Cloud のユーザー向けにも Datasette Agent を展開していく予定です。
プロジェクトについて議論したい場合は、#datasette-agent Discord channel にご参加ください。
Tags: projects, sqlite, ai, datasette, generative-ai, llms, llm, uv, datasette-agent
原文を表示
We just announced the first release of Datasette Agent, a new extensible AI assistant for Datasette. I've been working on my LLM Python library for just over three years now, and Datasette Agent represents the moment that LLM and Datasette finally come together. I'm really excited about it!
Datasette Agent provides a conversational interface for asking questions of the data you have stored in Datasette. Add the datasette-agent-charts plugin and it can generate charts of your data as well.
The demo
The announcement post (on the new Datasette project blog) includes this demo video:
*
I recorded the video against the new agent.datasette.io live demo instance, which runs Datasette Agent against example databases including the classic global-power-plants by WRI, and a copy of the Datasette backup of my blog.
The live demo runs on Gemini 3.1 Flash-Lite - it's cheap, fast and has no trouble writing SQLite queries.
A question I asked in the demo was:
when did Simon most recently see a pelican?
Which ran this SQL query:
SELECT
title, commentary, created
FROM
blog_beat
WHERE
beat_type = 'sighting'
AND (title LIKE '%pelican%' OR commentary LIKE '%pelican%')
ORDER BY
created DESC
LIMIT
5And replied:
The most recent sighting of a pelican by Simon was recorded on May 20, 2026.
The observation included a California Brown Pelican, along with a Common Loon, Canada Goose, Striped Shore Crab, and a California Sea Lion.
Here's that sighting on my blog, and the Markdown export of the full conversation transcript.
The plugins
My favorite feature of Datasette Agent is that, like the rest of Datasette, it's extensible using plugins.
We've shipped three plugins so far:
- datasette-agent-charts, shown in the video, adds charts to Datasette Agent, powered by Observable Plot.
- datasette-agent-openai-imagegen adds an image generation tool to Datasette Agent using ChatGPT Images 2.0.
- datasette-agent-sprites provides tools for executing code in a Fly Sprites persistent sandbox.
Building plugins is really fun*. I have a bunch more prototypes that aren't quite alpha-quality yet.
Claude Code and OpenAI Codex are both proving excellent at writing plugins - just point them at a checkout of the datasette-agent repo for reference and tell them what you want to build!
Running it against local models
I've also been having fun running the new plugin against local models. Here's a uv one-liner to run the plugin against gemma-4-26b-a4b in LM Studio on a Mac:
uvx --prerelease=allow \
--with datasette-agent --with llm-lmstudio \
datasette --internal internal.db --root \
-s plugins.datasette-llm.default_model lmstudio/google/gemma-4-26b-a4b \
data.dbDatasette Agent needs reliable tool calls and the ability for a model to produce SQL queries that run against SQLite. The open weight models released in the past six months are increasingly able to handle that.
What's next
Datasette Agent opens up *so many* opportunities for the LLM and Datasette ecosystem in general.
It's already informed the major LLM 0.32a0 refactor which I'm nearly ready to roll into a stable release, maybe with some additional "LLM agent" abstractions extracte from Datasette Agent itself.
I've been exploring my own take on the Claude Artifacts, which is shaping up nicely as a plugin.
I'm excited to use Datasette Agent to build my own Claw - a personal AI assistant built around data imported from different parts of my digital life, which is a neat excuse to revisit my older Dogsheep family of tools.
We'll also be rolling out Datasette Agent for users of Datasette Cloud.
Join our #datasette-agent Discord channel if you'd like to talk about the project.
Tags: projects, sqlite, ai, datasette, generative-ai, llms, llm, uv, datasette-agent
関連記事
今日のまとめ
AI日報で今日の重要ニュースをまとめ読み