Skip to main content

freetext_jupyter

This is a IPyWidget that interfaces with the Kording Lab freetext server. The freetext server is an automatic text feedback system that can be used to provide feedback to students on their written responses to questions.

Overview

This widget takes the form of a simple text box. The student is presented with the prompt text and a place to answer the question. Upon submitting, the freetext server engages a large language model with general knowledge as well as fine-grained knowledge about the question (provided by the instructor) to generate feedback for the student. The feedback is then displayed to the student under the text area, in near-real time, without waiting for a human instructor.

As in all LLM-based tools, caveat emptor: the feedback is not always correct, and it is not always useful. But it is often correct, and it is often useful. The feedback is not meant to replace human instructors, but rather to augment them. The feedback is meant to be used as a starting point to engage meaningful discussion between the students and the instructor.

Installation

pip install freetext_jupyter

Usage

from freetext_jupyter import FreetextWidget

FreetextWidget(
    # This ID is generated by the instructor by creating a new assignment in
    # the freetext server. For more information, see the freetext documentation
    # for your community's server.
    "07b2c3ef-0f97-46bc-a11e-fc5c06c381c2"
)

https://github.com/KordingLab/fretext-jupyter/assets/693511/090a2445-7867-4428-a28a-d5f3a2c96f68

Metadata

Release files for freetext-jupyter 0.1.0

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

Source distribution (sdist)

Source distribution for freetext-jupyter 0.1.0
File Size Uploaded
freetext_jupyter-0.1.0.tar.gz 2.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for freetext-jupyter 0.1.0
File Interpreter ABI Platform
freetext_jupyter-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 6.1 kB

Release files / freetext_jupyter-0.1.0.tar.gz

Download URL freetext_jupyter-0.1.0.tar.gz
Size 2.8 kB
Tags Source
SHA-256 checksum
How to use checksums
79af875f3b0118b03a7226850c6e29efd8d8a1a4ae9231cfca4c0b1ae5951723
BLAKE2b-256 checksum
How to use checksums
9c317f68659cd5f3f4ab4f42accaf13c88bef141cd4b74dcb720d27fe94d0d6e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/3.7.1 importlib_metadata/4.8.2 pkginfo/1.8.2 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.16

Release files / freetext_jupyter-0.1.0-py3-none-any.whl

Download URL freetext_jupyter-0.1.0-py3-none-any.whl
Size 3.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c70c3dda15773dde92ca48a628a6a9b56af128e258b7a3bc0f621a65e92c0c28
BLAKE2b-256 checksum
How to use checksums
4bc6dcccf1c51bd926eca9695da4d37dc869424b1834cd6f1dfa303db6a75b05
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/3.7.1 importlib_metadata/4.8.2 pkginfo/1.8.2 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.16

Release history Release notifications | RSS feed

This release

0.1.0 This release

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