keras-nlp

library0.29.1pypypi✓ verified 84d ago

KerasNLP provides pretrained NLP models (e.g., BERT, GPT-2, T5) and preprocessing utilities for Keras. Current version 0.28.0 supports Python >=3.10. Released approximately monthly.

ai-ml llm-agents

pip install keras-nlp

github ↗package ↗homepage ↗

INSTALL

IMPORT

SIG · KERAS-NLP

keras-nlp

ai-mlpythonv0.29.1

Install

39.4s avg

Import

19564ms

Disk

2417MB

Pass rate

5/ 10

Env Coverage5 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.25.1 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

py 3.10–3.95 runs

build_error

glibc

py 3.10–3.95 runs

installs and imports cleanly · install 39.4s · import 19.564s · 2355.2MB

2417MB installed

● package 2417MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

KerasNLP

✓ import keras_nlp

Module imports as keras_nlp, not keras_nlp.models.

BertTokenizer

✓ from keras_nlp.tokenizers import BertTokenizer

✗ from keras_nlp.models import BertTokenizer

BERTTokenizer is in the tokenizers submodule, not models.

bert_base_preprocessor

✓ from keras_nlp.models import bert_base_preprocessor

✗ import bert_base_preprocessor

Preprocessors are in the models submodule with model name prefix.

Load a pretrained BERT classifier and make a prediction.

import keras_nlp import keras # Load a pretrained BERT model model = keras_nlp.models.BertClassifier.from_preset( "bert_tiny_en_uncased", num_classes=2, ) # Encode sample text using the built-in preprocessor preprocessor = keras_nlp.models.bert_base_preprocessor() inputs = preprocessor(["Hello, world!"]) # Predict outputs = model(inputs) print(outputs)

Debug

Known issues

breakingKerasNLP models require Keras 3 and TensorFlow/JAX/PyTorch backend. Using with Keras 2 will fail.

fix

Install Keras 3: pip install 'keras>=3.0' and set backend via KERAS_BACKEND env var.

affects: >=0.6.0

deprecatedPresets like 'bert_tiny_en_uncased' may be removed or renamed in future versions. Always refer to the official preset list.

fix

Use keras_nlp.presets.list_presets() to see current presets.

affects: all

gotchaTokenizers and preprocessors must be built with a vocabulary before use. Calling .fit() on a raw tokenizer will raise an error.

fix

Use a preset tokenizer: tokenizer = keras_nlp.tokenizers.BertTokenizer.from_preset('bert_tiny_en_uncased')

affects: >=0.10.0

breakingFrom version 0.13.0, 'import keras_nlp' no longer imports TensorFlow. You must explicitly import the backend.

fix

Add import os; os.environ['KERAS_BACKEND'] = 'tensorflow' before importing keras_nlp.

affects: >=0.13.0

Errors

Common errors & fixes

AttributeError: module 'keras_nlp' has no attribute 'BertClassifier'

Wrong import path. BertClassifier is in keras_nlp.models.

fix

Use: from keras_nlp.models import BertClassifier

RuntimeError: You must call `build()` on the tokenizer before using it.

Tokenizers from presets need to be built or used via from_preset which builds automatically.

fix

Use: tokenizer = keras_nlp.tokenizers.BertTokenizer.from_preset('bert_tiny_en_uncased')

ValueError: Unknown preset: 'bert_tiny_uncased'

Typo or outdated preset name.

fix

Run: print(keras_nlp.presets.list_presets()) to see valid names.

ImportError: cannot import name 'bert_base_preprocessor' from 'keras_nlp.models'

The preprocessor name may vary by preset; not all presets have this symbol.

fix

Use: from keras_nlp.models import BertPreprocessor (or check preset-specific exports).

Upgrade

Version history

0.29.1latest on PyPI · released Jun 2, 2026

Audit

Dependencies

No dependency data recorded yet.

Agent activity

13 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/keras-team/keras ↗

packagehttps://pypi.org/project/keras-nlp/ ↗

homepagehttps://keras.io/keras_hub/ ↗