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

pypi.org "information-retrieval" keyword

View the packages on the pypi.org package registry that are tagged with the "information-retrieval" keyword.

dataquest 0.1.1
A package to extract hystorical news sentiments
3 versions - Latest release: 23 days ago - 237 downloads last month - 1 stars on GitHub - 1 maintainer
nalcos 0.1.1 💰
Search Git commits in natural language
2 versions - Latest release: over 3 years ago - 1 dependent repositories - 100 downloads last month - 54 stars on GitHub - 1 maintainer
ir-metrics 0.1.6
The most common information retrieval (IR) metrics
15 versions - Latest release: about 4 years ago - 5 dependent repositories - 5.04 thousand downloads last month - 5 stars on GitHub - 1 maintainer
unstructured-cpu 0.15.1
A library that prepares raw documents for downstream ML tasks.
13 versions - Latest release: 8 months ago - 368 downloads last month - 10,877 stars on GitHub - 1 maintainer
Top 9.6% on pypi.org
tevatron 0.1.0
Tevatron: A toolkit for learning and running deep dense retrieval models.
1 version - Latest release: about 3 years ago - 1 dependent package - 1 dependent repositories - 281 downloads last month - 582 stars on GitHub - 1 maintainer
Top 6.9% on pypi.org
text2text 1.9.5
Text2Text Language Modeling Toolkit
192 versions - Latest release: 3 months ago - 4 dependent repositories - 7.11 thousand downloads last month - 300 stars on GitHub - 1 maintainer
Top 0.2% on pypi.org
gensim 4.3.3 💰
Python framework for fast Vector Space Modelling
91 versions - Latest release: 9 months ago - 426 dependent packages - 13,895 dependent repositories - 4.89 million downloads last month - 15,255 stars on GitHub - 2 maintainers
dynamic-prompting 0.2.6
Dynamic Few-Shot Prompting is a Python package that dynamically selects N samples that are contex...
4 versions - Latest release: 9 months ago - 88 downloads last month - 2 stars on GitHub - 1 maintainer
billm 0.1.6
Tool for converting LLMs from uni-directional to bi-directional for tasks like classification and...
7 versions - Latest release: 11 months ago - 1.09 thousand downloads last month - 441 stars on GitHub - 1 maintainer
langroid-examples 0.1.25 💰
Add your description here
19 versions - Latest release: 4 months ago - 658 downloads last month - 3,221 stars on GitHub - 1 maintainer
langroid 0.52.4 💰
Harness LLMs with Multi-Agent Programming
431 versions - Latest release: 2 days ago - 1 dependent repositories - 21.7 thousand downloads last month - 2,245 stars on GitHub - 1 maintainer
megabots 0.0.11
🤖 Megabots provides State-of-the-art, production ready bots made mega-easy, so you don't have to ...
5 versions - Latest release: almost 2 years ago - 1 dependent repositories - 274 downloads last month - 341 stars on GitHub - 1 maintainer
Top 1.9% on pypi.org
rank-bm25 0.2.2
Various BM25 algorithms for document ranking
4 versions - Latest release: about 3 years ago - 69 dependent packages - 345 dependent repositories - 1.19 million downloads last month - 1,133 stars on GitHub - 1 maintainer
pylate 1.1.7
A library for training and retrieval with ColBERT
9 versions - Latest release: about 1 month ago - 1.33 thousand downloads last month - 276 stars on GitHub - 1 maintainer
Top 0.7% on pypi.org
easyocr 1.7.2
End-to-End Multi-Lingual Optical Character Recognition (OCR) Solution
33 versions - Latest release: 7 months ago - 90 dependent packages - 671 dependent repositories - 821 thousand downloads last month - 26,321 stars on GitHub - 1 maintainer
promptcache 0.0.1a1
A tool for caching prompts and compleation based on embedding
1 version - Latest release: over 1 year ago - 56 downloads last month - 1,933 stars on GitHub - 1 maintainer
lm-cocktail 0.0.4
LM_Cocktail
5 versions - Latest release: about 1 year ago - 631 downloads last month - 9,278 stars on GitHub - 1 maintainer
Top 7.0% on pypi.org
flagembedding 1.3.4
FlagEmbedding
31 versions - Latest release: 2 months ago - 4 dependent packages - 1 dependent repositories - 119 thousand downloads last month - 9,278 stars on GitHub - 2 maintainers
c-mteb 1.1.1
Chinese Massive Text Embedding Benchmark
3 versions - Latest release: about 1 year ago - 171 downloads last month - 9,278 stars on GitHub - 1 maintainer
stringzilla 3.12.5
SIMD-accelerated string search, sort, hashes, fingerprints, & edit distances
69 versions - Latest release: about 18 hours ago - 1 dependent package - 1.36 million downloads last month - 1,749 stars on GitHub - 1 maintainer
tira-measure 0.0.11
Measuring what really matters.
4 versions - Latest release: 2 months ago - 610 downloads last month - 4 stars on GitHub - 1 maintainer
pyterrier-sentence-transformers 0.2.2
Create an pyterrier index using any sentence-transformers model
1 version - Latest release: over 2 years ago - 1 dependent repositories - 71 downloads last month - 5 stars on GitHub - 1 maintainer
Top 7.1% on pypi.org
cherche 2.2.1
Neural Search
23 versions - Latest release: 11 months ago - 3 dependent repositories - 682 downloads last month - 296 stars on GitHub - 1 maintainer
Top 1.5% on pypi.org
catalyst 22.2.1 💰
Catalyst. Accelerated deep learning R&D with PyTorch.
104 versions - Latest release: about 3 years ago - 13 dependent packages - 179 dependent repositories - 23.4 thousand downloads last month - 3,235 stars on GitHub - 1 maintainer
rakun2 0.30
RaKUn 2.0; Better faster stronger lighter
12 versions - Latest release: about 21 hours ago - 1 dependent repositories - 919 downloads last month - 66 stars on GitHub - 1 maintainer
colpali-engine 0.3.10
The code used to train and run inference with the ColPali architecture.
19 versions - Latest release: about 22 hours ago - 33.6 thousand downloads last month - 1,710 stars on GitHub - 2 maintainers
ducksearch 1.0.2
DuckSearch: A Python library for efficient search in large collections of text data.
3 versions - Latest release: 7 months ago - 74 downloads last month - 45 stars on GitHub - 1 maintainer
forte.health 0.1.0
NLP pipeline framework for biomedical and clinical domains
1 version - Latest release: almost 3 years ago - 54 downloads last month - 10 stars on GitHub - 3 maintainers
tirex-tracker 0.2.12
Automatic resource and metadata tracking for information retrieval experiments.
13 versions - Latest release: 15 days ago - 120 thousand downloads last month - 4 stars on GitHub - 2 maintainers
irtm 0.0.4
A toolbox for Information Retrieval & Text Mining.
4 versions - Latest release: over 3 years ago - 1 dependent repositories - 187 downloads last month - 1 stars on GitHub - 1 maintainer
sycamore-ai 0.1.31
Sycamore is an LLM-powered semantic data preparation system for building search applications.
31 versions - Latest release: 25 days ago - 1.39 thousand downloads last month - 506 stars on GitHub - 2 maintainers
Top 2.5% on pypi.org
instructorembedding 1.0.1
Text embedding tool
2 versions - Latest release: almost 2 years ago - 14 dependent packages - 34 dependent repositories - 88.7 thousand downloads last month - 1,930 stars on GitHub - 1 maintainer
pvoctopus 2.0.2
⚠️ DEPRECATED: This package is no longer maintained.
15 versions - Latest release: 3 days ago - 1 dependent package - 1 dependent repositories - 387 downloads last month - 36 stars on GitHub - 1 maintainer
bm25s 0.2.12
An ultra-fast implementation of BM25 based on sparse matrices.
39 versions - Latest release: 2 days ago - 194 thousand downloads last month - 1,097 stars on GitHub - 1 maintainer
ir_evaluation 1.1.0
Information retrieval evaluation metrics in pure python with zero dependencies
5 versions - Latest release: 3 months ago - 218 downloads last month - 8 stars on GitHub - 1 maintainer
Top 9.7% on pypi.org
nocv2easyocr 0.1.1
This is a fork of the EasyOCR library without the opencv requirement
2 versions - Latest release: about 2 years ago - 105 downloads last month - 20,452 stars on GitHub - 1 maintainer
needle-haystack-ai 0.1.0
Needle RAG tools for Haystack
1 version - Latest release: 8 months ago - 84 downloads last month - 2 stars on GitHub - 1 maintainer
weaviate-cli 3.2.0
Command line interface to interact with weaviate
31 versions - Latest release: 8 days ago - 1 dependent repositories - 5.51 thousand downloads last month - 9,772 stars on GitHub - 2 maintainers
pvoctopusdemo 2.0.2
⚠️ DEPRECATED: This package is no longer maintained.
15 versions - Latest release: 3 days ago - 1 dependent repositories - 387 downloads last month - 36 stars on GitHub - 1 maintainer
netizenship 0.2.3
Tool to check the username with popular websites for membership
13 versions - Latest release: about 5 years ago - 1 dependent repositories - 367 downloads last month - 48 stars on GitHub - 1 maintainer
metriks 0.0.2
metriks is a Python package of commonly used metrics for evaluating information retrieval models.
2 versions - Latest release: over 5 years ago - 1 dependent repositories - 107 downloads last month - 25 stars on GitHub - 2 maintainers
archive-query-log 1.2.26
Mining Millions of Search Result Pages of Hundreds of Search Engines from 25 Years of Web Archives.
44 versions - Latest release: over 1 year ago - 2.55 thousand downloads last month - 28 stars on GitHub - 4 maintainers
catalyst-pdm 22.4.1 💰
Catalyst fork compatible with PDM
1 version - Latest release: about 2 years ago - 74 downloads last month - 3,342 stars on GitHub - 1 maintainer
yabm25 0.1.1
Fast BM25 search engine for Python with RAG support
2 versions - Latest release: about 2 months ago - 91 downloads last month - 0 stars on GitHub - 1 maintainer
lightning-ir 0.0.3
Your one-stop shop for fine-tuning and running neural ranking models.
3 versions - Latest release: 15 days ago - 234 downloads last month - 52 stars on GitHub - 1 maintainer
tiledb-vector-search 0.12.0
TileDB Vector Search Python client
32 versions - Latest release: 15 days ago - 10.1 thousand downloads last month - 44 stars on GitHub - 4 maintainers
corec 1.1.5
A Context-Aware Recommendation Framework for Python
15 versions - Latest release: 7 days ago - 817 downloads last month - 537 stars on GitHub - 1 maintainer
txt2hpo 0.2.3
HPO concept recognition and phenotype extraction tool
6 versions - Latest release: about 4 years ago - 2 dependent repositories - 243 downloads last month - 29 stars on GitHub - 3 maintainers
Top 9.4% on pypi.org
axcelocr 1.6.3
End-to-End Multi-Lingual Optical Character Recognition (OCR) Solution
1 version - Latest release: about 2 years ago - 29 downloads last month - 26,321 stars on GitHub - 1 maintainer
easyocr-itgn 1.2.3
Modified Easyorc By IntoThatGoodNight
3 versions - Latest release: over 1 year ago - 176 downloads last month - 20,429 stars on GitHub - 1 maintainer
asoen-ocr 1.0.0
End-to-End Multi-Lingual Optical Character Recognition (OCR) Solution
1 version - Latest release: about 2 years ago - 29 downloads last month - 22,979 stars on GitHub - 1 maintainer
Top 7.4% on pypi.org
asone-ocr 1.6.2
End-to-End Multi-Lingual Optical Character Recognition (OCR) Solution
2 versions - Latest release: about 2 years ago - 2 dependent packages - 1 dependent repositories - 130 downloads last month - 20,452 stars on GitHub - 1 maintainer
myeasyocr 1.2.3
End-to-End Multi-Lingual Optical Character Recognition (OCR) Solution
1 version - Latest release: about 4 years ago - 1 dependent repositories - 76 downloads last month - 20,452 stars on GitHub - 1 maintainer
fabricator-ai 0.2.0
Conveniently generating datasets with large language models.
3 versions - Latest release: over 1 year ago - 107 downloads last month - 20,266 stars on GitHub - 1 maintainer
docling-haystack 0.1.1
Docling Haystack converter
1 version - Latest release: 4 months ago - 665 downloads last month - 20,266 stars on GitHub - 1 maintainer
open-retrievals 0.0.14
Text Embeddings for Retrieval and RAG based on transformers
16 versions - Latest release: 3 months ago - 596 downloads last month - 12 stars on GitHub - 1 maintainer
embed-anything-gpu 0.5.3
Embed anything at lightning speed
16 versions - Latest release: 2 months ago - 2.79 thousand downloads last month - 503 stars on GitHub - 1 maintainer
embed-anything 0.5.5
Embed anything at lightning speed
41 versions - Latest release: 24 days ago - 7.13 thousand downloads last month - 503 stars on GitHub - 1 maintainer
elasticsearch-ir-evaluator 0.4.4
A Python package for easily calculating information retrieval (IR) accuracy metrics using Elastic...
9 versions - Latest release: about 1 year ago - 355 downloads last month - 5 stars on GitHub - 1 maintainer
fastrag 3.1.2
An Efficient Retrieval Augmentation and Generation Framework for Intel Hardware.
6 versions - Latest release: 5 months ago - 321 downloads last month - 945 stars on GitHub - 1 maintainer
persianstemmer 1.0.0
Persian Stemmer for Python
1 version - Latest release: about 8 years ago - 2 dependent repositories - 55 downloads last month - 51 stars on GitHub - 1 maintainer
rurage 1.1.1
RURAGE (Robust Universal RAG Evaluation) is a Python library developed to speed-up evaluation of ...
5 versions - Latest release: 5 months ago - 200 downloads last month - 27 stars on GitHub - 2 maintainers
Top 2.3% on pypi.org
txtai 8.5.0
All-in-one open-source embeddings database for semantic search, LLM orchestration and language mo...
50 versions - Latest release: 5 days ago - 13 dependent packages - 14 dependent repositories - 24.9 thousand downloads last month - 10,705 stars on GitHub - 1 maintainer
Top 3.3% on pypi.org
haystack-ai 2.12.2
LLM framework to build customizable, production-ready LLM applications. Connect components (model...
254 versions - Latest release: 5 days ago - 51 dependent packages - 2 dependent repositories - 369 thousand downloads last month - 16,679 stars on GitHub - 1 maintainer
superlinked-server 1.23.0
Superlinked server enables fast and scalable vector search and storage
45 versions - Latest release: 9 days ago - 3.66 thousand downloads last month - 1,023 stars on GitHub - 1 maintainer
goldenretriever-core 1.0.0
Dense Retriever
7 versions - Latest release: 9 months ago - 313 downloads last month - 9 stars on GitHub - 1 maintainer
dlkp 0.0.1
A deep learning library for keyphrase extraction and generation
1 version - Latest release: about 3 years ago - 1 dependent repositories - 58 downloads last month - 25 stars on GitHub - 2 maintainers
cogexpke 1.8.1
Python Keyphrase Extraction module
1 version - Latest release: about 3 years ago - 1 dependent repositories - 27 downloads last month - 1,581 stars on GitHub - 1 maintainer
vke 1.8.1
Python Keyphrase Extraction module
1 version - Latest release: almost 4 years ago - 1 dependent repositories - 46 downloads last month - 1,581 stars on GitHub - 1 maintainer
Top 8.8% on pypi.org
pke-tool 1.8.1
Python Keyphrase Extraction module
1 version - Latest release: over 3 years ago - 1 dependent package - 1 dependent repositories - 97 downloads last month - 1,581 stars on GitHub - 1 maintainer
ccpke 2.0.0
Python Keyphrase Extraction module
1 version - Latest release: about 2 years ago - 1 dependent package - 31 downloads last month - 1,581 stars on GitHub - 1 maintainer
pkelambda 1.8.1
Python Keyphrase Extraction module
1 version - Latest release: about 3 years ago - 1 dependent repositories - 54 downloads last month - 1,581 stars on GitHub - 1 maintainer
cuvs-cu12 25.4.0
cuVS: Vector Search on the GPU
8 versions - Latest release: 9 days ago - 3.59 thousand downloads last month - 362 stars on GitHub - 1 maintainer
libcuvs-cu11 25.4.0
cuVS: Vector Search on the GPU (C++)
3 versions - Latest release: 9 days ago - 1.07 thousand downloads last month - 362 stars on GitHub - 1 maintainer
libcuvs-cu12 25.4.0
cuVS: Vector Search on the GPU (C++)
3 versions - Latest release: 9 days ago - 2.42 thousand downloads last month - 362 stars on GitHub - 1 maintainer
cuvs-cu11 25.4.0
cuVS: Vector Search on the GPU
8 versions - Latest release: 9 days ago - 1.33 thousand downloads last month - 72 stars on GitHub - 1 maintainer
Top 6.2% on pypi.org
lexicalrichness 0.5.1
A small module to compute textual lexical richness (aka lexical diversity).
15 versions - Latest release: over 1 year ago - 5 dependent packages - 7 dependent repositories - 8.86 thousand downloads last month - 105 stars on GitHub - 1 maintainer
litepali 0.0.5
Lightweight ColPali-based retrieval for cloud
6 versions - Latest release: 7 months ago - 314 downloads last month - 46 stars on GitHub - 1 maintainer
pynutshell 1.0.2
An unsupervised text summarization and information retrieval library under the hood using natural...
3 versions - Latest release: over 4 years ago - 1 dependent repositories - 145 downloads last month - 15 stars on GitHub - 1 maintainer
rmdl 1.0.8
RMDL: Random Multimodel Deep Learning for Classification
6 versions - Latest release: almost 5 years ago - 1 dependent repositories - 130 downloads last month - 430 stars on GitHub - 1 maintainer
rankify 0.1.3
A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation
7 versions - Latest release: about 1 month ago - 7.42 thousand downloads last month - 384 stars on GitHub - 1 maintainer
agent-search 0.1.0
AgentSearch: An open source framework and dataset for webscale local search.
9 versions - Latest release: over 1 year ago - 1 dependent package - 482 downloads last month - 482 stars on GitHub - 1 maintainer
pyranker 0.1.3
A Python based package consisiting of BM25 and Vector Space Rankers for Information Retri...
3 versions - Latest release: about 2 years ago - 65 downloads last month - 0 stars on GitHub - 1 maintainer
hinteval 0.0.3
A Python framework designed for both generating and evaluating hints.
3 versions - Latest release: 3 months ago - 7.57 thousand downloads last month - 32 stars on GitHub - 1 maintainer
autograph-obsidian 0.3
Automatic knowledge graph generation.
3 versions - Latest release: over 1 year ago - 1 dependent repositories - 80 downloads last month - 29 stars on GitHub - 1 maintainer
gensim-bz2-nsml 3.8.0 💰
Python framework for fast Vector Space Modelling
1 version - Latest release: over 5 years ago - 1 dependent repositories - 94 downloads last month - 15,949 stars on GitHub - 1 maintainer
wiki-passage-retriever 0.1.4
A small tool for retrieving relevant passages to a question from Wikipedia
8 versions - Latest release: over 4 years ago - 1 dependent repositories - 318 downloads last month - 2 stars on GitHub - 1 maintainer
Top 3.5% on pypi.org
mteb 2.0.0
Massive Text Embedding Benchmark
508 versions - Latest release: about 1 year ago - 6 dependent packages - 25 dependent repositories - 175 thousand downloads last month - 1,441 stars on GitHub - 4 maintainers
retriv 0.2.3
retriv: A Python Search Engine for Humans.
10 versions - Latest release: over 1 year ago - 1 dependent package - 1 dependent repositories - 713 downloads last month - 213 stars on GitHub - 1 maintainer
raft-dask-cu11 25.4.0
Reusable Accelerated Functions & Tools Dask Infrastructure
19 versions - Latest release: 9 days ago - 2 dependent packages - 1 dependent repositories - 1.43 thousand downloads last month - 866 stars on GitHub - 3 maintainers
pylibraft-cu11 25.4.0
RAFT: Reusable Algorithms Functions and other Tools
19 versions - Latest release: 9 days ago - 4 dependent packages - 1 dependent repositories - 1.59 thousand downloads last month - 866 stars on GitHub - 3 maintainers
pylibraft-cu12 25.4.0
RAFT: Reusable Algorithms Functions and other Tools
14 versions - Latest release: 9 days ago - 4 dependent packages - 1 dependent repositories - 4.47 thousand downloads last month - 602 stars on GitHub - 1 maintainer
raft-dask-cu12 25.4.0
Reusable Accelerated Functions & Tools Dask Infrastructure
14 versions - Latest release: 9 days ago - 2 dependent packages - 1 dependent repositories - 3.7 thousand downloads last month - 602 stars on GitHub - 1 maintainer
libraft-cu11 25.4.0
RAFT: Reusable Algorithms Functions and other Tools (C++)
2 versions - Latest release: 9 days ago - 1.02 thousand downloads last month - 866 stars on GitHub - 1 maintainer
libraft-cu12 25.4.0
RAFT: Reusable Algorithms Functions and other Tools (C++)
2 versions - Latest release: 9 days ago - 2.6 thousand downloads last month - 866 stars on GitHub - 1 maintainer
fast-forward-indexes 0.7.1
Efficient interpolation-based ranking on CPUs
13 versions - Latest release: about 1 month ago - 1 dependent repositories - 963 downloads last month - 10 stars on GitHub - 1 maintainer
Top 9.8% on pypi.org
allrank 1.4.3
allRank is a framework for training learning-to-rank neural models
8 versions - Latest release: almost 4 years ago - 1 dependent repositories - 466 downloads last month - 920 stars on GitHub - 1 maintainer
allrank-mod 1.3.0a0
allRank is a framework for training learning-to-rank neural models
1 version - Latest release: almost 5 years ago - 1 dependent repositories - 30 downloads last month - 920 stars on GitHub - 1 maintainer
Top 2.5% on pypi.org
beir 2.1.0
A Heterogeneous Benchmark for Information Retrieval
30 versions - Latest release: about 2 months ago - 9 dependent packages - 30 dependent repositories - 13.3 thousand downloads last month - 1,602 stars on GitHub - 1 maintainer
Top 3.3% on pypi.org
ir-datasets 0.5.10
provides a common interface to many IR ad-hoc ranking benchmarks, training datasets, etc.
21 versions - Latest release: about 1 month ago - 10 dependent packages - 21 dependent repositories - 135 thousand downloads last month - 296 stars on GitHub - 1 maintainer