salesforce/TaiChi

Open source library for few shot NLP

37
/ 100
Emerging

This tool helps machine learning practitioners classify customer intent from short text inputs, like chatbot messages, even when very little training data is available. You provide a small set of example utterances and their corresponding intents, and the system outputs a trained model that can accurately categorize new user requests. It's designed for data scientists or ML engineers building conversational AI systems or other NLP applications where data labeling is a bottleneck.

No commits in the last 6 months.

Use this if you need to build an intent classification model but only have a handful of labeled examples for each intent.

Not ideal if you have extensive labeled datasets for your text classification task, as it's specifically optimized for low-data scenarios.

intent-classification conversational-ai chatbot-development natural-language-processing low-resource-nlp
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

79

Forks

8

Language

Python

License

BSD-3-Clause

Last pushed

Jun 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/salesforce/TaiChi"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.