An open API service providing package, version and dependency metadata of many open source software ecosystems and registries.

pypi.org "NLP" keyword

Top 8.2% on pypi.org
khoj-assistant 1.21.1 💰
khoj-assistant is now khoj
784 versions - Latest release: about 2 years ago - 1 dependent repositories - 1.14 thousand downloads last month - 38,112 stars on GitHub - 2 maintainers
Top 0.3% on pypi.org
sentence-transformers 6.3.0
Embeddings, Retrieval, and Reranking
86 versions - Latest release: 2 days ago - 710 dependent packages - 5,182 dependent repositories - 22.6 million downloads last month - 19,282 stars on GitHub - 2 maintainers
openmed 3.3.0
Local-first SDK for clinical extraction and de-identification workflows on hardware you control.
54 versions - Latest release: about 2 hours ago - 2.29 million downloads last month - 5,797 stars on GitHub - 1 maintainer
Top 0.7% on pypi.org
llama-index 0.14.25
Interface between LLMs and your data
505 versions - Latest release: about 2 months ago - 153 dependent packages - 1,464 dependent repositories - 1.98 million downloads last month - 52,835 stars on GitHub - 2 maintainers
khoj 1.42.10 💰
Your Second Brain
603 versions - Latest release: over 1 year ago - 2 dependent repositories - 5.92 thousand downloads last month - 37,971 stars on GitHub - 2 maintainers
tokenizers-gt 0.15.2.post0
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
3 versions - Latest release: over 2 years ago - 832 downloads last month - 11,239 stars on GitHub - 1 maintainer
Top 0.6% on pypi.org
tokenizers 0.23.3
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
129 versions - Latest release: about 1 month ago - 380 dependent packages - 14,571 dependent repositories - 211 million downloads last month - 11,239 stars on GitHub - 4 maintainers
divyanx-tokenizers 0.20.0.dev0
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
1 version - Latest release: about 2 years ago - 55 downloads last month - 11,239 stars on GitHub - 1 maintainer
unstructured-cpu 0.15.1
A library that prepares raw documents for downstream ML tasks.
13 versions - Latest release: over 2 years ago - 94 downloads last month - 15,697 stars on GitHub - 1 maintainer
Top 3.0% on pypi.org
stanfordcorenlp 3.9.1.1
Python wrapper for Stanford CoreNLP.
4 versions - Latest release: over 8 years ago - 1 dependent package - 135 dependent repositories - 1.84 thousand downloads last month - 914 stars on GitHub - 1 maintainer
sentencex 1.0.35
Sentence segmenter that supports ~300 languages
39 versions - Latest release: about 6 hours ago - 1.17 million downloads last month - 145 stars on GitHub - 1 maintainer
presidio-haystack 3.0.0
Haystack integration for Microsoft Presidio — PII detection and anonymization
4 versions - Latest release: 26 days ago - 492 downloads last month - 212 stars on GitHub - 1 maintainer
Top 1.5% on pypi.org
unstructured 0.27.37
A library that prepares raw documents for downstream ML tasks.
249 versions - Latest release: 7 days ago - 113 dependent packages - 3,374 dependent repositories - 2.68 million downloads last month - 15,697 stars on GitHub - 1 maintainer
Top 0.2% on pypi.org
nltk 3.10.4
Natural Language Toolkit
71 versions - Latest release: 23 days ago - 1,440 dependent packages - 57,572 dependent repositories - 46.1 million downloads last month - 14,766 stars on GitHub - 5 maintainers
summa-visualization 0.1.0b0
A visualization for the graphs generated by summa.
1 version - Latest release: almost 9 years ago - 1 dependent repositories - 30 downloads last month - 2 stars on GitHub - 1 maintainer
transformers4576 4.57.6.4
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
5 versions - Latest release: 4 months ago - 2.63 thousand downloads last month - 168,923 stars on GitHub - 1 maintainer
mcwtimesformer 4.52.0
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
1 version - Latest release: over 1 year ago - 168,923 stars on GitHub - 1 maintainer
transformers-mcw 4.52.0.dev0
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
1 version - Latest release: over 1 year ago - 11 downloads last month - 168,923 stars on GitHub - 1 maintainer
t-draft-123 4.48.0.dev4
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
5 versions - Latest release: almost 2 years ago - 9 downloads last month - 168,923 stars on GitHub - 1 maintainer
transformers-machinify 4.27.0.dev0
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
1 version - Latest release: over 3 years ago - 1 dependent package - 14 downloads last month - 168,923 stars on GitHub - 2 maintainers
transformers-phobert 3.1.2
State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch. Note that the tokeni...
2 versions - Latest release: about 6 years ago - 1 dependent repositories - 9 downloads last month - 168,923 stars on GitHub - 1 maintainer
divyanx-transformers 4.45.0.dev0
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
1 version - Latest release: about 2 years ago - 15 downloads last month - 168,923 stars on GitHub - 1 maintainer
xmersawitransformers 4.52.0.dev0
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
1 version - Latest release: over 1 year ago - 5 downloads last month - 168,923 stars on GitHub - 1 maintainer
transformers-v4.55.0-glm-4.5v-preview 4.56.0.dev0
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
1 version - Latest release: over 1 year ago - 27 downloads last month - 168,923 stars on GitHub - 1 maintainer
mcwtransformers 4.52.1
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
2 versions - Latest release: over 1 year ago - 8 downloads last month - 168,923 stars on GitHub - 1 maintainer
my-transformers 4.5.1
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
2 versions - Latest release: over 1 year ago - 16 downloads last month - 168,923 stars on GitHub - 1 maintainer
rlinf-transformer-openpi 4.53.2
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
1 version - Latest release: 4 months ago - 1.63 thousand downloads last month - 168,923 stars on GitHub
in-transformers 1.0.0
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
1 version - Latest release: almost 4 years ago - 18 downloads last month - 168,923 stars on GitHub - 1 maintainer
transformers-openpi 4.53.3
State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
1 version - Latest release: about 1 year ago - 16 downloads last month - 168,923 stars on GitHub - 1 maintainer
transformers-qwenomni 4.52.0.3
Transformers: With code for Qwen 2.5 Omni
2 versions - Latest release: over 1 year ago - 20 downloads last month - 168,923 stars on GitHub - 1 maintainer
Top 0.6% on pypi.org
pytorch-pretrained-bert 0.6.2
PyTorch version of Google AI BERT model with script to load Google pre-trained models
10 versions - Latest release: over 7 years ago - 11 dependent packages - 940 dependent repositories - 37.2 thousand downloads last month - 168,923 stars on GitHub - 1 maintainer
Top 2.4% on pypi.org
tf-sentencepiece 0.1.90
SentencePiece Encode/Decode ops for TensorFlow
15 versions - Latest release: over 6 years ago - 1 dependent package - 30 dependent repositories - 913 downloads last month - 12,170 stars on GitHub - 1 maintainer
Top 6.3% on pypi.org
unstructured-inference 1.6.17
A library for performing inference using trained models.
130 versions - Latest release: 16 days ago - 8 dependent packages - 16 dependent repositories - 685 thousand downloads last month - 210 stars on GitHub - 1 maintainer
Top 2.5% on pypi.org
beir 2.2.0
A Heterogeneous Benchmark for Information Retrieval
31 versions - Latest release: over 1 year ago - 9 dependent packages - 30 dependent repositories - 41.3 thousand downloads last month - 2,333 stars on GitHub - 1 maintainer
Top 9.3% on pypi.org
huaweicloudsdknlp 3.1.222
NLP
262 versions - Latest release: about 17 hours ago - 1 dependent package - 1 dependent repositories - 1.12 thousand downloads last month - 164 stars on GitHub - 1 maintainer
ruts-mcp 0.1.5
MCP server for ruTS: statistics of Russian texts as tools for LLM agents
6 versions - Latest release: about 18 hours ago - 701 downloads last month - 0 stars on GitHub - 1 maintainer
textdescriptives 2.8.4
A library for calculating a variety of features from text using spaCy
38 versions - Latest release: almost 2 years ago - 4 dependent packages - 1 dependent repositories - 5.98 thousand downloads last month - 369 stars on GitHub - 2 maintainers
esmorph 0.3.0
Fast Spanish morphological analyzer written in Rust with a Python API
3 versions - Latest release: about 19 hours ago - 0 downloads last month - 0 stars on GitHub - 1 maintainer
uralicnlp 2.1.3 💰
An NLP library for Uralic languages such as Finnish and Sami. Also supports Spanish, Arabic, Russ...
31 versions - Latest release: 23 days ago - 1 dependent repositories - 918 downloads last month - 101 stars on GitHub - 1 maintainer
opencompass 0.5.5
A comprehensive toolkit for large model evaluation
32 versions - Latest release: 7 days ago - 3.03 thousand downloads last month - 7,564 stars on GitHub - 1 maintainer
trunajod 0.1.1
A python lib for readability analyses.
3 versions - Latest release: over 5 years ago - 1 dependent repositories - 81 downloads last month - 31 stars on GitHub - 1 maintainer
Top 7.9% on pypi.org
jury 2.3.1
Evaluation toolkit for neural language generation.
23 versions - Latest release: over 2 years ago - 1 dependent package - 2 dependent repositories - 884 downloads last month - 187 stars on GitHub - 1 maintainer
Top 9.5% on pypi.org
augmenty 1.4.4
An augmentation library based on SpaCy for joint augmentation of text and labels.
33 versions - Latest release: over 2 years ago - 4 dependent packages - 1 dependent repositories - 143 downloads last month - 155 stars on GitHub - 2 maintainers
llama-trainer 0.2.1
Llama trainer utility
3 versions - Latest release: about 3 years ago - 19 downloads last month - 9 stars on GitHub - 1 maintainer
xfinder 0.2.6
An Robust and Pinpoint Answer Extractor for LLM Evaluation
9 versions - Latest release: almost 2 years ago - 8 downloads last month - 179 stars on GitHub - 1 maintainer
easyinstruct 0.1.2
An Easy-to-use Instruction Processing Framework for Large Language Models.
8 versions - Latest release: almost 3 years ago - 1 dependent repositories - 38 downloads last month - 407 stars on GitHub - 3 maintainers
Top 1.4% on pypi.org
spark-nlp 7.0.0
John Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML...
197 versions - Latest release: about 2 months ago - 35 dependent packages - 35 dependent repositories - 692 thousand downloads last month - 4,163 stars on GitHub - 4 maintainers
Top 10.0% on pypi.org
ckls-test-lib 4.2.7
John Snow Labs Spark NLP is a natural language processing library built on top of Apache Spark ML...
1 version - Latest release: almost 4 years ago - 85 downloads last month - 4,163 stars on GitHub - 1 maintainer
healthsageai 0.1.7
HealthSage AI LLMs, Healthcare genAI platform
5 versions - Latest release: over 2 years ago - 9 downloads last month - 1 maintainer
healthsageai-note-to-fhir 0.1
HealthSage AI LLM - from clinical note to FHIR
1 version - Latest release: almost 3 years ago - 9 downloads last month - 1 maintainer
rst2dep 1.4.1.0
RST (Rhetorical Structure Theory) constituent and dependency converter for discourse parses
11 versions - Latest release: 1 day ago - 18 downloads last month - 17 stars on GitHub - 1 maintainer
Top 5.0% on pypi.org
text2num 3.1.0
Parse and convert numbers written in French, Spanish, English, Portuguese, German, Dutch, Danish,...
20 versions - Latest release: 3 months ago - 1 dependent package - 20 dependent repositories - 1.24 million downloads last month - 119 stars on GitHub - 1 maintainer
sacrebleu-macrof 2.0.1
Hassle-free computation of shareable, comparable, and reproducible BLEU, chrF, and TER scores
1 version - Latest release: about 5 years ago - 1 dependent package - 1 dependent repositories - 71 downloads last month - 1,265 stars on GitHub - 1 maintainer
Top 1.3% on pypi.org
sacrebleu 2.6.0
Hassle-free computation of shareable, comparable, and reproducible BLEU, chrF, and TER scores
73 versions - Latest release: 10 months ago - 96 dependent packages - 4,263 dependent repositories - 3.12 million downloads last month - 1,265 stars on GitHub - 3 maintainers
labton 0.2.5
Clean minimal text-annotation tool - with buildt in control of Inter-Annotator Agreement
26 versions - Latest release: almost 4 years ago - 87 downloads last month - 2 stars on GitHub - 1 maintainer
spark-nlp-jsl-tmp 5.0.0 removed
NLP Text processing library built on top of Apache Spark
2 versions - Latest release: over 4 years ago
xtest-bert-score 0.3.13.1
PyTorch implementation of BERT score for xtest
2 versions - Latest release: over 1 year ago - 11 downloads last month - 1,923 stars on GitHub - 1 maintainer
Top 1.8% on pypi.org
bert-score 0.3.13
PyTorch implementation of BERT score
21 versions - Latest release: over 3 years ago - 51 dependent packages - 220 dependent repositories - 422 thousand downloads last month - 1,923 stars on GitHub - 2 maintainers
zuel-test 0.1
Chinese Words Segmentation Utilities
1 version - Latest release: almost 5 years ago - 1 dependent repositories - 4 downloads last month - 35,224 stars on GitHub - 1 maintainer
jieba-migang 0.0.1
Chinese Words Segmentation Utilities
1 version - Latest release: over 2 years ago - 17 downloads last month - 35,224 stars on GitHub - 1 maintainer
wbjieba 0.42.1
Chinese Words Segmentation Utilities
1 version - Latest release: about 5 years ago - 1 dependent repositories - 6 downloads last month - 35,224 stars on GitHub - 1 maintainer
Top 0.2% on pypi.org
jieba 0.42.1
Chinese Words Segmentation Utilities
32 versions - Latest release: almost 7 years ago - 238 dependent packages - 4,190 dependent repositories - 4.79 million downloads last month - 35,224 stars on GitHub - 1 maintainer
tensorzero 2026.6.0
The Python client for TensorZero
126 versions - Latest release: 5 months ago - 32.8 thousand downloads last month - 11,709 stars on GitHub - 1 maintainer
mindsql 0.2.1
Text-2-SQL made easy in just a few lines of python.
6 versions - Latest release: over 2 years ago - 37 downloads last month - 447 stars on GitHub - 1 maintainer
dcr-core 0.9.7
Document Content Recognition API
49 versions - Latest release: about 4 years ago - 1 dependent repositories - 52 downloads last month - 0 stars on GitHub - 1 maintainer
llama-index-core 0.14.25
Interface between LLMs and your data
258 versions - Latest release: about 2 months ago - 518 dependent packages - 6.57 million downloads last month - 52,835 stars on GitHub - 1 maintainer
Top 1.6% on pypi.org
nemo-toolkit 3.0.0
NeMo - a toolkit for Conversational AI
109 versions - Latest release: 3 months ago - 4 dependent packages - 27 dependent repositories - 446 thousand downloads last month - 18,544 stars on GitHub - 3 maintainers
relex 1.2
An easy to use PyTorch-based library for state-of-the-art semantic relations extraction.
15 versions - Latest release: over 4 years ago - 1 dependent repositories - 30 downloads last month - 5 stars on GitHub - 1 maintainer
modelgauge 0.6.3
Automatically and uniformly measure the behavior of many AI Systems.
7 versions - Latest release: about 2 years ago - 55 downloads last month - 26 stars on GitHub - 6 maintainers
ais-bench-benchmark 3.1.20260630
A comprehensive toolkit for large model evaluation, commit id: 1e7cb37e3d5d2101db47fe3fe2272c9653...
2 versions - Latest release: 5 months ago - 180 downloads last month - 863 stars on GitHub - 1 maintainer
Top 6.2% on pypi.org
fastt5 0.1.4
boost inference speed of T5 models by 5x & reduce the model size by 3x using fastT5.
13 versions - Latest release: over 4 years ago - 6 dependent repositories - 30.2 thousand downloads last month - 587 stars on GitHub - 1 maintainer
keyphrasetransformer 0.0.2
Quickly extract key-phrases/topics from you text data with T5 transformer.
2 versions - Latest release: over 4 years ago - 1 dependent repositories - 847 downloads last month - 107 stars on GitHub - 1 maintainer
reading-poetry 0.1.9
Tool for the computational analysis of poetry
6 versions - Latest release: over 4 years ago - 11 downloads last month - 0 stars on GitHub - 1 maintainer
rectvision 3.0.73
A low-code tool to help create your own AI
62 versions - Latest release: about 3 years ago - 76 downloads last month - 4 stars on GitHub - 1 maintainer
fastgpt 0.0.8 💰
boost inference speed of GPT models in transformers by onnxruntime
8 versions - Latest release: over 3 years ago - 2 dependent repositories - 105 downloads last month - 51 stars on GitHub - 1 maintainer
greekroom 0.1.5
The Greek Room will be a suite of tools supporting Biblical natural language processing.
6 versions - Latest release: 2 months ago - 1 dependent repositories - 288 downloads last month - 9 stars on GitHub - 1 maintainer
jsl-tmp 4.4.7 removed
The John Snow Labs Library gives you access to all of John Snow Labs Enterprise And Open Source p...
118 versions - Latest release: about 4 years ago - 505 downloads last month
income 0.0.2
Domain Adaptation for Memory-Efficient Dense Retrieval
2 versions - Latest release: over 4 years ago - 2 dependent repositories - 89 downloads last month - 24 stars on GitHub - 1 maintainer
hf-endpoints-emulator 0.1.1
Emulator for Custom Handlers for Inference Endpoints
2 versions - Latest release: about 4 years ago - 27 downloads last month - 1 maintainer
nlptest 1.5.0
John Snow Labs provides a library for delivering safe & effective NLP models.
41 versions - Latest release: over 3 years ago - 1 dependent repositories - 441 downloads last month - 561 stars on GitHub - 2 maintainers
Top 0.7% on pypi.org
pytorch-transformers 1.2.0
Repository of pre-trained NLP Transformer models: BERT & RoBERTa, GPT & GPT-2, Transformer-XL, XL...
4 versions - Latest release: about 7 years ago - 16 dependent packages - 772 dependent repositories - 13.1 thousand downloads last month - 167,055 stars on GitHub - 1 maintainer
lavague-llms-huggingface 0.1.0
HuggingFaceLLM integration for lavague
1 version - Latest release: over 2 years ago - 15 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague 1.1.19
automation code generation from text instructions
52 versions - Latest release: over 2 years ago - 152 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-server 0.0.4
Server for Lavague agents
4 versions - Latest release: over 2 years ago - 8 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-contexts-gemini 0.2.1
gemini integration for lavague
6 versions - Latest release: over 2 years ago - 48 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-drivers-playwright 0.2.11
Playwright integration for lavague
17 versions - Latest release: over 2 years ago - 78 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-contexts-openai 0.2.4
Openai integration for lavague
7 versions - Latest release: over 2 years ago - 115 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-sdk 0.1.0
automation code generation from text instructions
1 version - Latest release: about 2 years ago - 7 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-contexts-cache 0.0.1
Context for lavague able to cache and proxy to LLM and MM LLM designed to save up tokens and make...
1 version - Latest release: about 2 years ago - 9 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-retriever-cohere 0.2.0
Cohere retriever for lavague
3 versions - Latest release: over 2 years ago - 22 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-drivers-selenium 0.2.15
Selenium integration for lavague
25 versions - Latest release: about 2 years ago - 120 downloads last month - 6,396 stars on GitHub - 1 maintainer
Top 4.5% on pypi.org
synonyms 3.25.1
中文近义词:聊天机器人,智能问答工具包;Chinese Synonyms for Natural Language Processing and Understanding
25 versions - Latest release: 10 months ago - 48 dependent repositories - 496 downloads last month - 5,108 stars on GitHub - 1 maintainer
lavague-gradio 0.2.8
Gradio demo for lavague
10 versions - Latest release: over 2 years ago - 93 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-contexts-groq 0.1.0
Groq integration for lavague
1 version - Latest release: over 2 years ago - 19 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-core 0.2.35
automation code generation from text instructions
51 versions - Latest release: about 2 years ago - 169 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-tests 0.0.4
Test runner for Lavague
4 versions - Latest release: over 2 years ago - 41 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-contexts-anthropic 0.1.3
anthropic integration for lavague
7 versions - Latest release: over 2 years ago - 25 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-cli 0.1.0
CLI for lavague
1 version - Latest release: over 2 years ago - 7 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-drivers-remote 0.2.5
Remote driver execution for Lavague
6 versions - Latest release: over 2 years ago - 7 downloads last month - 6,396 stars on GitHub - 1 maintainer
lavague-contexts-huggingface 0.1.0
HuggingFaceLLM integration for lavague
1 version - Latest release: over 2 years ago - 11 downloads last month - 6,396 stars on GitHub - 1 maintainer