Skip to main content

datasette-enrichments-gpt

PyPI Changelog Tests License

Datasette enrichment for analyzing row data using OpenAI's GPT models

Installation

Install this plugin in the same environment as Datasette.

datasette install datasette-enrichments-gpt

Configuration

This plugin can optionally be configured with an OpenAI API key. You can set this as an environment variable:

export DATASETTE_SECRETS_OPENAPI_API_KEY=sk-..

Or you can configure it using the datasette-secrets plugin.

If you do not configure an OpenAI API key users will be asked to enter one any time they execute the enrichment. The key they provide will not be stored anywhere other than in-memory during the enrichment run.

Usage

Once installed, this plugin will allow users to select rows to enrich and run them through prompts using gpt-3.5-turbo or gpt-4o, saving the result of the prompt in the specified column.

The plugin also provides gpt-4o vision, which can run prompts against an image identified by a URL.

Development

To set up this plugin locally, first checkout the code. Then create a new virtual environment:

cd datasette-enrichments-gpt
python3 -m venv venv
source venv/bin/activate

Now install the dependencies and test dependencies:

pip install -e '.[test]'

To run the tests:

pytest

Release files for datasette-enrichments-gpt 0.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for datasette-enrichments-gpt 0.5
File Size Uploaded
datasette_enrichments_gpt-0.5.tar.gz 9.7 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for datasette-enrichments-gpt 0.5
File Interpreter ABI Platform
datasette_enrichments_gpt-0.5-py3-none-any.whl Python 3 none any Details

Total release size: 19.5 kB

Release files / datasette_enrichments_gpt-0.5.tar.gz

Download URL datasette_enrichments_gpt-0.5.tar.gz
Size 9.7 kB
Tags Source
SHA-256 checksum
How to use checksums
d4aa7992ce85ee18a74592c02387b216f40c027553e2ec5e80f140d01b08011f
BLAKE2b-256 checksum
How to use checksums
ac339921ab268a1f31dc40c7a8e8cd2d56e3db9c89096071345ab50d33853f01
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.0.0 CPython/3.12.3

Release files / datasette_enrichments_gpt-0.5-py3-none-any.whl

Download URL datasette_enrichments_gpt-0.5-py3-none-any.whl
Size 9.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
aef56b3b3cad6c81c4cd067e3c09e4a24f0d7f4ab346421da1e5f7742922db1e
BLAKE2b-256 checksum
How to use checksums
ea215b8fc281ed6fc5809524fb442ad23a39738da31e1295d2fb3228bc6e1488
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.0.0 CPython/3.12.3

Release history Release notifications | RSS feed

This release

0.5 This release

2 release files

0.4

2 release files

0.3

2 release files

0.2

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page