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

pypi.org "nlp" keyword

textstat-rs 2.0.0
Rust port of the textstat textual analysis library, with Python bindings.
3 versions - Latest release: 16 days ago - 917 downloads last month - 0 stars on GitHub - 1 maintainer
Top 1.9% on pypi.org
bertviz 1.4.1
Attention visualization tool for NLP Transformer models.
6 versions - Latest release: over 1 year ago - 3 dependent packages - 95 dependent repositories - 4.17 thousand downloads last month - 8,170 stars on GitHub - 1 maintainer
Top 0.6% on pypi.org
rasa 3.6.21
Open source machine learning framework to automate text- and voice-based conversations: NLU, dial...
374 versions - Latest release: over 1 year ago - 7 dependent packages - 584 dependent repositories - 242 thousand downloads last month - 21,315 stars on GitHub - 3 maintainers
rasa-pro 3.19.2
State-of-the-art open-core Conversational AI framework for Enterprises that natively leverages ge...
494 versions - Latest release: 1 day ago - 12.4 thousand downloads last month - 21,309 stars on GitHub - 2 maintainers
Top 0.1% on pypi.org
transformers 5.16.1
Transformers: the model-definition framework for state-of-the-art machine learning models in text...
241 versions - Latest release: 14 days ago - 2,589 dependent packages - 31,800 dependent repositories - 148 million downloads last month - 164,705 stars on GitHub - 6 maintainers
Top 4.4% on pypi.org
unidic 1.1.0 💰
UniDic packaged for Python
13 versions - Latest release: almost 5 years ago - 14 dependent packages - 142 dependent repositories - 427 thousand downloads last month - 102 stars on GitHub - 1 maintainer
Top 1.5% on pypi.org
chatterbot 1.2.15
ChatterBot is a machine learning, conversational dialog engine
96 versions - Latest release: 15 days ago - 2 dependent packages - 235 dependent repositories - 6.06 thousand downloads last month - 13,884 stars on GitHub - 2 maintainers
llamafactory 0.9.5
Unified Efficient Fine-Tuning of 100+ LLMs
11 versions - Latest release: 3 months ago - 22.5 thousand downloads last month - 74,633 stars on GitHub - 1 maintainer
langflow-base 1.12.0
A Python package with a built-in web application
296 versions - Latest release: 8 days ago - 2 dependent packages - 64.1 thousand downloads last month - 153,991 stars on GitHub - 2 maintainers
Top 2.1% on pypi.org
langflow 1.12.0
A Python package with a built-in web application
445 versions - Latest release: 8 days ago - 1 dependent package - 11 dependent repositories - 48.1 thousand downloads last month - 153,991 stars on GitHub - 2 maintainers
Top 3.1% on pypi.org
langsmith 0.12.2
Client library to connect to the LangSmith Observability and Evaluation Platform.
527 versions - Latest release: 4 days ago - 86 dependent packages - 2,234 dependent repositories - 102 million downloads last month - 1,047 stars on GitHub - 3 maintainers
Top 0.2% on pypi.org
nltk 3.10.3
Natural Language Toolkit
70 versions - Latest release: 28 days ago - 1,440 dependent packages - 57,572 dependent repositories - 57.1 million downloads last month - 14,706 stars on GitHub - 5 maintainers
wicky-vllm 0.1.6
a lightweight vLLM implementation built from scratch
7 versions - Latest release: 8 months ago - 22 downloads last month - 11,674 stars on GitHub - 1 maintainer
nano-vllm-fork 20260210
a lightweight vLLM implementation built from scratch
1 version - Latest release: 7 months ago - 63 downloads last month - 7,822 stars on GitHub - 1 maintainer
Top 3.8% on pypi.org
krwordrank 1.0.3
KR-WordRank: Korean Unsupervised Word/Keyword Extractor
8 versions - Latest release: about 6 years ago - 3 dependent packages - 28 dependent repositories - 525 downloads last month - 353 stars on GitHub - 1 maintainer
sygra 2.0.0
Graph-oriented Synthetic data generation Pipeline library
4 versions - Latest release: 9 months ago - 23 downloads last month - 91 stars on GitHub - 2 maintainers
ballerina-codebleu 0.7.1
Unofficial CodeBLEU implementation that supports Linux, MacOS and Windows available on PyPI.
1 version - Latest release: about 1 year ago - 15 downloads last month - 140 stars on GitHub - 1 maintainer
Top 5.5% on pypi.org
simplemma 2.0.0
Fast and zero-dependency lemmatization, tokenization and sentence splitting for 54 languages.
20 versions - Latest release: 28 days ago - 6 dependent packages - 25 dependent repositories - 154 thousand downloads last month - 215 stars on GitHub - 1 maintainer
Top 1.7% on pypi.org
keybert 0.9.0
KeyBERT performs keyword extraction with state-of-the-art transformer models.
19 versions - Latest release: over 1 year ago - 20 dependent packages - 105 dependent repositories - 451 thousand downloads last month - 4,215 stars on GitHub - 1 maintainer
radgraph-it 1.0.1
RadGraph graph inference for Italian radiology reports, with output in the canonical RadGraph-XL ...
2 versions - Latest release: 30 days ago - 3 stars on GitHub - 1 maintainer
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 - 1.2 thousand downloads last month - 11,015 stars on GitHub - 1 maintainer
Top 0.6% on pypi.org
tokenizers 0.23.2
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
124 versions - Latest release: 6 days ago - 380 dependent packages - 14,571 dependent repositories - 212 million downloads last month - 9,012 stars on GitHub - 5 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 - 12 downloads last month - 10,983 stars on GitHub - 1 maintainer
quranic-phonemizer 2.15.3
A riwayah-aware grapheme-to-phoneme converter for Quranic recitation.
23 versions - Latest release: 16 days ago - 2.01 thousand downloads last month - 33 stars on GitHub - 1 maintainer
landa-chatterbot-corpus 1.2.0 💰
A machine readable multilingual dialog corpus
1 version - Latest release: over 7 years ago - 1 dependent repositories - 13 downloads last month - 1,416 stars on GitHub - 1 maintainer
nlqueries-core 0.2.0
Natural-language query engine — open-source core (CLI, connectors, MCP server)
3 versions - Latest release: 2 months ago - 29 downloads last month - 2 stars on GitHub - 1 maintainer
nlqueries 0.0.1
Natural language queries for any database or document. Coming soon.
1 version - Latest release: 3 months ago - 9 downloads last month - 2 stars on GitHub - 1 maintainer
guidellm 0.7.3 💰
Guidance platform for deploying and managing large language models.
91 versions - Latest release: about 1 month ago - 22.4 thousand downloads last month - 1,572 stars on GitHub - 1 maintainer
Top 1.6% on pypi.org
sacremoses 0.2.0
SacreMoses
53 versions - Latest release: 26 days ago - 120 dependent packages - 5,564 dependent repositories - 2.97 million downloads last month - 497 stars on GitHub - 3 maintainers
rustling 0.9.0 💰
A high-performance library for computational linguistics
8 versions - Latest release: about 2 months ago - 42.2 thousand downloads last month - 3 stars on GitHub - 1 maintainer
Top 0.5% on pypi.org
textblob 0.20.1
Simple, Pythonic text processing. Sentiment analysis, part-of-speech tagging, noun phrase parsing...
62 versions - Latest release: about 2 months ago - 93 dependent packages - 6,514 dependent repositories - 3.74 million downloads last month - 9,545 stars on GitHub - 1 maintainer
Top 1.6% on pypi.org
bert-serving-client 1.10.0
Mapping a variable-length sentence to a fixed-length vector using BERT model (Client)
56 versions - Latest release: over 6 years ago - 2 dependent packages - 169 dependent repositories - 3.45 thousand downloads last month - 12,835 stars on GitHub - 1 maintainer
Top 1.5% on pypi.org
unstructured 0.27.5
A library that prepares raw documents for downstream ML tasks.
232 versions - Latest release: 12 days ago - 113 dependent packages - 3,374 dependent repositories - 4.31 million downloads last month - 15,391 stars on GitHub - 1 maintainer
llm-demo-2-production 0.0.1
The set of tools and examples for creating LLM-based solutions from demo to production
1 version - Latest release: about 3 years ago - 68 downloads last month - 1 stars on GitHub - 1 maintainer
mseep-langflow 1.6.3
A Python package with a built-in web application
3 versions - Latest release: about 1 year ago - 9 downloads last month - 154,441 stars on GitHub - 1 maintainer
tringlang 2.2.2
A Python package with a built-in web application
1 version - Latest release: about 2 years ago - 9 downloads last month - 154,441 stars on GitHub - 1 maintainer
Top 6.2% on pypi.org
tokenizer 3.6.4
A fast, compact pure-Python tokenizer for Icelandic text with sentence segmentation
65 versions - Latest release: 2 months ago - 6 dependent packages - 75 dependent repositories - 31.3 thousand downloads last month - 32 stars on GitHub - 3 maintainers
ibm-db-haystack 0.3.0
Haystack integration for IBM Db2
4 versions - Latest release: 8 days ago - 55 downloads last month - 202 stars on GitHub - 1 maintainer
snowflake-haystack 3.0.0
A Snowflake integration for the Haystack framework.
11 versions - Latest release: 8 months ago - 4.31 thousand downloads last month - 202 stars on GitHub - 1 maintainer
amazon-bedrock-haystack 8.1.0
An integration of AWS S3 and Bedrock as a Downloader and Generator components.
90 versions - Latest release: 5 days ago - 18 thousand downloads last month - 202 stars on GitHub - 1 maintainer
opendataloader-pdf-haystack 0.1.1
Haystack integration for opendataloader_pdf
2 versions - Latest release: 16 days ago - 171 downloads last month - 202 stars on GitHub - 1 maintainer
ragas-haystack 4.2.0
An integration of Ragas LLM evaluation framework with Haystack
17 versions - Latest release: 16 days ago - 5.65 thousand downloads last month - 202 stars on GitHub - 1 maintainer
acronymkit 0.3.0
Enterprise-grade text-to-acronym generation, extraction, and disambiguation engine.
1 version - Latest release: 29 days ago - 113 downloads last month - 0 stars on GitHub - 1 maintainer
spacy-partial-tagger 0.15.6
Sequence Tagger for Partially Annotated Dataset in spaCy
17 versions - Latest release: almost 3 years ago - 1 dependent package - 4 dependent repositories - 175 downloads last month - 24 stars on GitHub - 1 maintainer
Top 6.7% on pypi.org
small-text 1.4.1
Active Learning for Text Classification in Python.
26 versions - Latest release: about 2 years ago - 6 dependent repositories - 515 downloads last month - 646 stars on GitHub - 1 maintainer
fastrag 3.1.2
An Efficient Retrieval Augmentation and Generation Framework for Intel Hardware.
6 versions - Latest release: almost 2 years ago - 52 downloads last month - 945 stars on GitHub - 2 maintainers
Top 5.9% on pypi.org
ltp-extension 0.1.13
Rust Extension For Language Technology Platform(Python).
12 versions - Latest release: over 2 years ago - 2 dependent packages - 1 dependent repositories - 2.99 thousand downloads last month - 5,259 stars on GitHub - 2 maintainers
cogie 0.1.6
CogIE: An Information Extraction Toolkit for Bridging Text and CogNet
7 versions - Latest release: about 4 years ago - 1 dependent repositories - 75 downloads last month - 71 stars on GitHub - 1 maintainer
Top 5.4% on pypi.org
gridx-egret 0.6.2
EGRET: Electrical Grid Research and Engineering Tools.
9 versions - Latest release: 3 months ago - 1 dependent package - 4 dependent repositories - 30.9 thousand downloads last month - 168 stars on GitHub - 1 maintainer
qcnlp 1.1.0
A Preprocessing & Parsing tool for Chinese Natural Language Processing
2 versions - Latest release: over 4 years ago - 1 dependent repositories - 47 downloads last month - 4 stars on GitHub - 1 maintainer
alignment-handbook 0.3.0
The Alignment Handbook
3 versions - Latest release: almost 2 years ago - 83 downloads last month - 5,664 stars on GitHub - 1 maintainer
banks 2.5.0
A prompt programming language
37 versions - Latest release: about 1 month ago - 1 dependent repositories - 7.23 million downloads last month - 128 stars on GitHub - 1 maintainer
semantic-router 0.1.16
Super fast semantic router for AI decision making
99 versions - Latest release: about 1 month ago - 5 dependent packages - 295 thousand downloads last month - 3,831 stars on GitHub - 1 maintainer
unstructured-cpu 0.15.1
A library that prepares raw documents for downstream ML tasks.
13 versions - Latest release: about 2 years ago - 25 downloads last month - 15,391 stars on GitHub - 1 maintainer
pinferencia 0.2.1
Aims to be the Simplest Machine Learning Model Inference Server
15 versions - Latest release: about 4 years ago - 1 dependent repositories - 91 downloads last month - 543 stars on GitHub - 1 maintainer
Top 2.3% on pypi.org
txtai 9.13.0
All-in-one open-source AI framework for semantic search, LLM orchestration and language model wor...
67 versions - Latest release: 13 days ago - 13 dependent packages - 14 dependent repositories - 24.8 thousand downloads last month - 12,922 stars on GitHub - 1 maintainer
bio-epidemiology-ner 0.1.3
Recognize bio-medical entities from a text corpus
13 versions - Latest release: about 4 years ago - 155 downloads last month - 134 stars on GitHub - 3 maintainers
xturing 0.1.8
Fine-tuning, evaluation and data generation for LLMs
19 versions - Latest release: about 3 years ago - 64 downloads last month - 2,674 stars on GitHub - 1 maintainer
zarnitsa 0.0.19
zarnitsa package for data augmentation
16 versions - Latest release: almost 5 years ago - 1 dependent repositories - 21 downloads last month - 7 stars on GitHub - 1 maintainer
chronologia 0.2.9
General-purpose calendrical and chronological core: unbounded datetime-compatible dates, half-ope...
83 versions - Latest release: 23 days ago - 3.26 thousand downloads last month - 1 stars on GitHub - 1 maintainer
Top 0.2% on pypi.org
datasets 5.0.1
HuggingFace community-driven open-source library of datasets
119 versions - Latest release: about 1 month ago - 931 dependent packages - 14,962 dependent repositories - 122 million downloads last month - 21,889 stars on GitHub - 4 maintainers
zhtw 4.5.0
Simplified/HK Traditional to Taiwan Traditional Chinese Converter
39 versions - Latest release: 10 days ago - 806 downloads last month - 14 stars on GitHub - 1 maintainer
fundus 0.5.7
A very simple news crawler
21 versions - Latest release: about 1 month ago - 1.68 thousand downloads last month - 473 stars on GitHub - 1 maintainer
fdatasets 1.12.1
HuggingFace/Datasets is an open library of NLP datasets.
1 version - Latest release: over 4 years ago - 21,868 stars on GitHub
insuant 1.0.0a20
A Python package with a built-in web application
4 versions - Latest release: about 2 years ago - 63 downloads last month - 154,441 stars on GitHub - 1 maintainer
mehen 1.10.0 💰
Tool to compute and export code metrics
25 versions - Latest release: 21 days ago - 1.05 thousand downloads last month - 5 stars on GitHub - 1 maintainer
prompt-amplifier 0.2.2
Transform short prompts into detailed, structured instructions using context-aware retrieval
6 versions - Latest release: 9 months ago - 43 downloads last month - 0 stars on GitHub - 1 maintainer
newspaper4k 0.9.6
Simplified python article discovery & extraction.
9 versions - Latest release: about 2 months ago - 171 thousand downloads last month - 1,141 stars on GitHub - 1 maintainer
sequifier 3.0.0
Train a transformer model with the command line
106 versions - Latest release: about 2 years ago - 201 downloads last month - 21 stars on GitHub - 1 maintainer
pai-easynlp 0.0.3
PAI EasyNLP Toolkit
1 version - Latest release: over 4 years ago - 1 dependent package - 1 dependent repositories - 15 downloads last month - 2,184 stars on GitHub - 2 maintainers
grammared-language 0.1.4
Grammar error correction backend with Triton and GRPC integration
5 versions - Latest release: 7 months ago - 75 downloads last month - 1 maintainer
Top 1.2% on pypi.org
tika 3.3.2 💰
Apache Tika Python library
37 versions - Latest release: about 1 month ago - 33 dependent packages - 528 dependent repositories - 521 thousand downloads last month - 1,666 stars on GitHub - 1 maintainer
Top 3.2% on pypi.org
thinc-gpu-ops 0.0.4
CUDA kernels for Thinc
4 versions - Latest release: over 7 years ago - 2 dependent packages - 10 dependent repositories - 1.14 thousand downloads last month - 2,889 stars on GitHub - 3 maintainers
Top 0.9% on pypi.org
thinc 9.1.1
A refreshing functional take on deep learning, compatible with your favorite libraries
250 versions - Latest release: almost 2 years ago - 40 dependent packages - 8,632 dependent repositories - 23.9 million downloads last month - 2,889 stars on GitHub - 3 maintainers
manas-ai 0.2.1 💰
A framework for building LLM-powered applications with intelligent agents, task decomposition, an...
5 versions - Latest release: over 1 year ago - 70 downloads last month - 11 stars on GitHub - 1 maintainer
denckring 0.1.1
A library of experimental writing procedures, where the validator is the eval
2 versions - Latest release: about 15 hours ago - 1 maintainer
edenai-haystack 0.1.0
Use Eden AI with Haystack to build AI applications with 500+ AI models through one unified, OpenA...
1 version - Latest release: about 2 months ago - 3.01 thousand downloads last month - 202 stars on GitHub - 1 maintainer
scandeval 18.0.0
The robust European language model benchmark.
201 versions - Latest release: 26 days ago - 1 dependent repositories - 2.22 thousand downloads last month - 193 stars on GitHub - 1 maintainer
euroeval 18.0.0
The robust European language model benchmark.
60 versions - Latest release: 26 days ago - 758 downloads last month - 193 stars on GitHub - 1 maintainer
Top 9.0% on pypi.org
spacy-wheel 3.5.0 💰
Reupload of SpaCy 3.4.4 with Global Wheel
1 version - Latest release: over 3 years ago - 33,876 stars on GitHub - 1 maintainer
udar 0.1.10
Detailed part-of-speech tagger for (accented) Russian.
4 versions - Latest release: over 5 years ago - 1 dependent repositories - 25 downloads last month - 30 stars on GitHub - 1 maintainer
vngrs-nlp 0.2.4
Turkish NLP Tools developed by VNGRS.
17 versions - Latest release: almost 2 years ago - 1 dependent repositories - 81 downloads last month - 290 stars on GitHub - 1 maintainer
Top 1.5% on pypi.org
usaddress 0.5.16
Parse US addresses using conditional random fields
39 versions - Latest release: about 1 year ago - 11 dependent packages - 149 dependent repositories - 5.51 million downloads last month - 1,636 stars on GitHub - 2 maintainers
cats-scoring 1.6.0
Contextual Ambiguity & Trust Scoring — trust intelligence for OSINT sources
5 versions - Latest release: about 2 months ago - 53 downloads last month - 1 stars on GitHub - 1 maintainer
Top 3.8% on pypi.org
htmldate 1.10.0 💰
Fast and robust extraction of original and updated publication dates from URLs and web pages.
60 versions - Latest release: 3 months ago - 5 dependent packages - 50 dependent repositories - 13.6 million downloads last month - 156 stars on GitHub - 1 maintainer
causalif 0.1.10
Large Language Models (LLMs) with Bayesian causal inference to discover causal relationships and ...
15 versions - Latest release: 3 months ago - 242 downloads last month - 17 stars on GitHub - 1 maintainer
Top 4.4% on pypi.org
whatlies 0.7.0
Tools to help uncover `whatlies` in word embeddings.
44 versions - Latest release: over 4 years ago - 76 dependent packages - 22 dependent repositories - 725 downloads last month - 477 stars on GitHub - 1 maintainer
reasongraph 0.7.19
A graph-based reasoning library with embedding search and multi-hop traversal
34 versions - Latest release: about 12 hours ago - 2.35 thousand downloads last month - 1 stars on GitHub - 1 maintainer
txtai-minimal 9.13.0
All-in-one open-source AI framework for semantic search, LLM orchestration and language model wor...
6 versions - Latest release: 13 days ago - 361 downloads last month - 12,922 stars on GitHub - 1 maintainer
litellm-haystack 1.2.0
An integration of LiteLLM AI gateway into the Haystack framework, routing to 100+ LLM providers.
5 versions - Latest release: about 1 month ago - 1.2 thousand downloads last month - 202 stars on GitHub - 1 maintainer
google-ai-haystack 5.4.0
Use models like Gemini via Google AI Studio
22 versions - Latest release: about 1 year ago - 3.14 thousand downloads last month - 202 stars on GitHub - 1 maintainer
amazon-textract-haystack 1.1.0
Haystack integration for AWS Textract document text extraction and analysis
2 versions - Latest release: 2 days ago - 311 downloads last month - 202 stars on GitHub - 1 maintainer
chonkie-haystack 1.1.0
Haystack integration for chonkie
2 versions - Latest release: 5 days ago - 443 downloads last month - 202 stars on GitHub - 1 maintainer
weblinx 0.3.2
The official weblinx library
12 versions - Latest release: almost 2 years ago - 13 thousand downloads last month - 160 stars on GitHub - 1 maintainer
Top 6.6% on pypi.org
bilm 0.1.post5
Tensorflow implementation of contextualized word representations from bi-directional language models
2 versions - Latest release: almost 8 years ago - 6 dependent repositories - 61 downloads last month - 1,612 stars on GitHub - 2 maintainers
plane 0.2.1 💰
A lib for text preprocessing
20 versions - Latest release: over 5 years ago - 3 dependent repositories - 447 downloads last month - 11 stars on GitHub - 1 maintainer
deepl-haystack 0.4.1
Haystack integration with DeepL translation services provider.
9 versions - Latest release: about 2 months ago - 3.35 thousand downloads last month - 7 stars on GitHub - 1 maintainer
hezar 1.0.0
Hezar: The all-in-one AI library for Persian, supporting a wide variety of tasks and modalities!
89 versions - Latest release: 6 months ago - 1.84 thousand downloads last month - 1,013 stars on GitHub - 1 maintainer
Top 1.8% on pypi.org
scispacy 0.6.2
A full SpaCy pipeline and models for scientific/biomedical documents.
17 versions - Latest release: 11 months ago - 17 dependent packages - 178 dependent repositories - 49.6 thousand downloads last month - 1,702 stars on GitHub - 3 maintainers
scispacy-ops 0.5.4
A full SpaCy pipeline and models for scientific/biomedical documents.
3 versions - Latest release: over 2 years ago - 13 downloads last month - 1,601 stars on GitHub - 2 maintainers