Data

Tools

Indexes

Applications

Experiments

Packages

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

pypi.org "data" keyword

fileformats-vendor-xnat-extras 0.3.1
Extra methods for accessing and manipulating the underlying data referenced by fileformats-vendor...
3 versions - Latest release: 1 day ago - 0 downloads last month - 1 maintainer
fileformats-vendor-xnat 0.3.1
Classes for representing different file formats in Python classes for use in type hinting in data...
3 versions - Latest release: 1 day ago - 0 downloads last month - 1 maintainer
Top 2.6% on pypi.org
pandasai 3.0.0
Chat with your database (SQL, CSV, pandas, mongodb, noSQL, etc). PandasAI makes data analysis con...
226 versions - Latest release: about 1 year ago - 6 dependent packages - 44 dependent repositories - 31.4 thousand downloads last month - 23,873 stars on GitHub - 1 maintainer
ethyca-fides 2.86.2
Open-source ecosystem for data privacy as code.
1,060 versions - Latest release: 5 months ago - 9.33 thousand downloads last month - 482 stars on GitHub - 1 maintainer
Top 0.4% on pypi.org
prefect 3.9.0
Workflow orchestration and management.
911 versions - Latest release: 8 days ago - 123 dependent packages - 767 dependent repositories - 6.9 million downloads last month - 24,084 stars on GitHub - 3 maintainers
llama-index-core 0.14.25
Interface between LLMs and your data
258 versions - Latest release: about 1 month ago - 518 dependent packages - 6.57 million downloads last month - 52,537 stars on GitHub - 1 maintainer
Top 4.8% on pypi.org
mage-ai 0.9.80
Mage is a tool for building and deploying data pipelines.
343 versions - Latest release: 19 days ago - 2 dependent repositories - 10.1 thousand downloads last month - 8,834 stars on GitHub - 2 maintainers
Top 5.5% on pypi.org
invenio-rdm-records 36.0.0
InvenioRDM module for the communities feature.
576 versions - Latest release: 16 days ago - 11 dependent packages - 21 dependent repositories - 22.8 thousand downloads last month - 23 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 1 month ago - 153 dependent packages - 1,464 dependent repositories - 2.94 million downloads last month - 52,537 stars on GitHub - 2 maintainers
apache-airflow-core 3.3.2
Core packages for Apache Airflow, schedule and API server
85 versions - Latest release: about 1 month ago - 2.63 million downloads last month - 47,269 stars on GitHub
Top 0.2% on pypi.org
apache-airflow 3.3.2
Programmatically author, schedule and monitor data pipelines
304 versions - Latest release: about 1 month ago - 314 dependent packages - 1,554 dependent repositories - 7.2 million downloads last month - 47,269 stars on GitHub - 1 maintainer
Top 7.3% on pypi.org
prefect-dbt 0.7.25
Prefect integrations for working with dbt
58 versions - Latest release: 5 months ago - 5 dependent repositories - 268 thousand downloads last month - 24,084 stars on GitHub - 2 maintainers
Top 9.9% on pypi.org
prefect-databricks 0.4.2
Prefect integrations with Databricks
27 versions - Latest release: 4 months ago - 1 dependent repositories - 21.2 thousand downloads last month - 24,084 stars on GitHub - 1 maintainer
prefect-ob 3.7.3
Workflow orchestration and management (OceanBase/MySQL-compatible fork).
4 versions - Latest release: about 20 hours ago - 22 downloads last month - 24,084 stars on GitHub - 1 maintainer
Top 9.2% on pypi.org
prefect-docker 0.7.4
Prefect integrations for interacting with Docker.
37 versions - Latest release: about 2 months ago - 2 dependent packages - 2 dependent repositories - 760 thousand downloads last month - 24,084 stars on GitHub - 2 maintainers
prefect-oceanbase 3.7.1
Workflow orchestration and management (OceanBase/MySQL-compatible fork).
2 versions - Latest release: 6 months ago - 14 downloads last month - 24,084 stars on GitHub - 1 maintainer
Top 0.3% on pypi.org
pydeck 0.9.3
Widget for deck.gl maps
41 versions - Latest release: 4 months ago - 55 dependent packages - 9,646 dependent repositories - 18 million downloads last month - 14,700 stars on GitHub - 4 maintainers
mosaic-widget 0.34.3 💰
A Jupyter widget for Mosaic
56 versions - Latest release: about 4 hours ago - 1.82 thousand downloads last month - 1,390 stars on GitHub - 2 maintainers
duckdb-server 0.34.3 💰
A DuckDB server for Mosaic
40 versions - Latest release: about 4 hours ago - 351 downloads last month - 1,390 stars on GitHub - 2 maintainers
vgplot 0.34.3 💰
A Python API for authoring Mosaic vgplot visualizations
13 versions - Latest release: about 4 hours ago - 225 downloads last month - 1,390 stars on GitHub - 2 maintainers
uriel-pc-tests 1.0.1
Workflow orchestration and management.
2 versions - Latest release: about 3 years ago - 11 downloads last month - 24,084 stars on GitHub - 1 maintainer
Top 5.5% on pypi.org
prefect-shell 0.3.7
Prefect integrations for interacting with shell commands.
22 versions - Latest release: 29 days ago - 6 dependent packages - 6 dependent repositories - 368 thousand downloads last month - 24,084 stars on GitHub - 2 maintainers
Top 3.2% on pypi.org
daff 1.4.2 💰
Diff and patch tables
60 versions - Latest release: over 1 year ago - 3 dependent packages - 34 dependent repositories - 16.7 million downloads last month - 930 stars on GitHub - 1 maintainer
Top 8.4% on pypi.org
prefect-ray 0.6.0
Prefect integrations with the Ray execution framework.
31 versions - Latest release: 10 days ago - 2 dependent packages - 2 dependent repositories - 234 thousand downloads last month - 24,084 stars on GitHub - 2 maintainers
prefect-gitlab 0.3.5
A Prefect collection for working with GitLab repositories.
17 versions - Latest release: 5 months ago - 73.7 thousand downloads last month - 24,084 stars on GitHub - 1 maintainer
Top 4.6% on pypi.org
prefect-gcp 0.6.22
Prefect integrations for interacting with Google Cloud Platform.
69 versions - Latest release: about 2 months ago - 2 dependent packages - 39 dependent repositories - 1.17 million downloads last month - 24,084 stars on GitHub - 2 maintainers
Top 7.0% on pypi.org
prefect-sqlalchemy 0.6.1
Prefect integrations for working with databases
24 versions - Latest release: 9 months ago - 1 dependent package - 27 dependent repositories - 320 thousand downloads last month - 24,084 stars on GitHub - 2 maintainers
prefect-client 3.9.0
Workflow orchestration and management.
515 versions - Latest release: 8 days ago - 577 thousand downloads last month - 24,084 stars on GitHub - 1 maintainer
prefect-bitbucket 0.3.7
Prefect integrations for working with Bitbucket repositories.
19 versions - Latest release: 5 months ago - 25.8 thousand downloads last month - 24,084 stars on GitHub - 1 maintainer
Top 4.9% on pypi.org
prefect-dask 0.3.7
Prefect integrations with the Dask execution framework.
25 versions - Latest release: 5 months ago - 9 dependent packages - 6 dependent repositories - 148 thousand downloads last month - 24,084 stars on GitHub - 2 maintainers
prefect-slack 0.4.0
Prefect integrations with Slack
16 versions - Latest release: 3 months ago - 2 dependent repositories - 249 thousand downloads last month - 24,084 stars on GitHub - 3 maintainers
Top 9.6% on pypi.org
prefect-azure 0.4.13
Prefect integrations with Microsoft Azure services
42 versions - Latest release: about 2 months ago - 1 dependent package - 1 dependent repositories - 140 thousand downloads last month - 24,084 stars on GitHub - 2 maintainers
prefect-redis 0.3.0
Prefect integrations with Redis.
21 versions - Latest release: 21 days ago - 75.3 thousand downloads last month - 24,084 stars on GitHub - 1 maintainer
Top 7.4% on pypi.org
prefect-snowflake 0.28.9
Prefect integrations for interacting with Snowflake
31 versions - Latest release: about 2 months ago - 1 dependent package - 2 dependent repositories - 239 thousand downloads last month - 24,084 stars on GitHub - 2 maintainers
Top 9.8% on pypi.org
prefect-email 0.4.3
Prefect integrations for interacting with email.
16 versions - Latest release: about 2 months ago - 3 dependent repositories - 64.4 thousand downloads last month - 24,084 stars on GitHub - 2 maintainers
Top 9.0% on pypi.org
prefect-github 0.4.4
Prefect integrations interacting with GitHub
24 versions - Latest release: 5 months ago - 3 dependent repositories - 822 thousand downloads last month - 24,084 stars on GitHub - 2 maintainers
Top 3.9% on pypi.org
prefect-aws 0.7.12
Prefect integrations for interacting with Amazon Web Services.
80 versions - Latest release: about 2 months ago - 4 dependent packages - 82 dependent repositories - 2.03 million downloads last month - 24,084 stars on GitHub - 2 maintainers
Top 8.8% on pypi.org
prefect-kubernetes 0.8.0
Prefect integrations for interacting with Kubernetes.
76 versions - Latest release: 9 days ago - 1 dependent package - 1 dependent repositories - 455 thousand downloads last month - 24,084 stars on GitHub - 2 maintainers
climakitae 1.5.10
Climate data analysis toolkit
22 versions - Latest release: 29 days ago - 534 downloads last month - 41 stars on GitHub - 1 maintainer
Top 3.2% on pypi.org
ckan 2.12.1
CKAN Software
127 versions - Latest release: about 18 hours ago - 5 dependent packages - 24 dependent repositories - 3.93 thousand downloads last month - 5,141 stars on GitHub - 1 maintainer
Top 1.8% on pypi.org
pydap 3.5.11
A pure python implementation of the Data Access Protocol.
56 versions - Latest release: about 2 months ago - 18 dependent packages - 57 dependent repositories - 186 thousand downloads last month - 157 stars on GitHub - 5 maintainers
ifk-smhi 0.3.0
Inspect and get SMHI data.
5 versions - Latest release: over 1 year ago - 35 downloads last month - 10 stars on GitHub - 1 maintainer
Top 4.9% on pypi.org
pygbif 0.7.0
Python client for GBIF
16 versions - Latest release: 22 days ago - 3 dependent packages - 24 dependent repositories - 9.48 thousand downloads last month - 158 stars on GitHub - 2 maintainers
catalystcoop.pudl 2025.12.1 💰
An open data processing pipeline for US energy data
34 versions - Latest release: 11 months ago - 1 dependent package - 8 dependent repositories - 453 downloads last month - 611 stars on GitHub - 3 maintainers
Top 1.4% on pypi.org
netcdf4 1.7.5
Provides an object-oriented python interface to the netCDF version 4 library
91 versions - Latest release: 14 days ago - 422 dependent packages - 1,377 dependent repositories - 3.06 million downloads last month - 840 stars on GitHub - 2 maintainers
dataprof 0.13.1 💰
Fast, lightweight data profiling and quality assessment library
37 versions - Latest release: about 13 hours ago - 2.55 thousand downloads last month - 31 stars on GitHub - 1 maintainer
Top 5.7% on pypi.org
pandas-dq 1.29
Clean your data using a scikit-learn transformer in a single line of code
19 versions - Latest release: almost 3 years ago - 1 dependent package - 13 dependent repositories - 4.02 thousand downloads last month - 138 stars on GitHub - 1 maintainer
spinetoolbox 0.10.10
An application to define, manage, and execute various energy system simulation models
53 versions - Latest release: about 2 months ago - 1 dependent package - 1 dependent repositories - 771 downloads last month - 103 stars on GitHub - 3 maintainers
Top 9.6% on pypi.org
recoverpy 2.3.0
A TUI to recover overwritten or deleted data.
38 versions - Latest release: 9 months ago - 1 dependent repositories - 186 downloads last month - 1,795 stars on GitHub - 1 maintainer
kotori 0.29.1
Kotori is a data acquisition, processing and graphing toolkit for humans
34 versions - Latest release: 6 days ago - 1 dependent repositories - 455 downloads last month - 126 stars on GitHub - 1 maintainer
tcmb 0.5.0
A Python client for the Central Bank of the Republic of Türkiye (TCMB) EVDS-API.
6 versions - Latest release: 8 months ago - 92 downloads last month - 16 stars on GitHub - 1 maintainer
dataops-testgen 5.134.0
DataKitchen's Data Quality DataOps TestGen
40 versions - Latest release: 14 days ago - 263 downloads last month - 80 stars on GitHub - 1 maintainer
jk_datamatrix 0.2025.5.25
This python module provides a class that represents a data matrix. This is basically a table you ...
6 versions - Latest release: over 1 year ago - 43 downloads last month - 0 stars on GitHub - 1 maintainer
worldometer 2.0.0 💰
Get live, population, geography, projected, and historical data from around the world.
5 versions - Latest release: about 3 years ago - 1 dependent repositories - 104 downloads last month - 71 stars on GitHub - 1 maintainer
Top 3.8% on pypi.org
sdmx1 2.28.0
Statistical Data and Metadata eXchange (SDMX)
78 versions - Latest release: 11 days ago - 4 dependent packages - 8 dependent repositories - 205 thousand downloads last month - 50 stars on GitHub - 2 maintainers
cannlytics 1.0.5
Simple cannabis analytics — COA parsing, data tools, and Metrc API access.
16 versions - Latest release: 29 days ago - 3 dependent repositories - 238 downloads last month - 82 stars on GitHub - 1 maintainer
dghs-imgutils 0.19.0
A convenient and user-friendly anime-style image data processing library that integrates various ...
62 versions - Latest release: about 1 year ago - 3 dependent packages - 1 dependent repositories - 7.79 thousand downloads last month - 428 stars on GitHub - 1 maintainer
Top 3.6% on pypi.org
dlt 1.31.0
dlt is an open-source python-first scalable data loading library that does not require any backen...
186 versions - Latest release: 22 days ago - 5 dependent packages - 23 dependent repositories - 4.92 million downloads last month - 6,024 stars on GitHub - 2 maintainers
dlt-dataops 0.5.4a0
dlt is an open-source python-first scalable data loading library that does not require any backen...
1 version - Latest release: about 2 years ago - 8 downloads last month - 6,024 stars on GitHub - 1 maintainer
dlt-core 202606.30.0
dlt is an open-source python-first scalable data loading library that does not require any backen...
18 versions - Latest release: 4 months ago - 2.25 thousand downloads last month - 6,024 stars on GitHub - 1 maintainer
Top 3.4% on pypi.org
pykrx 1.2.9 💰
KRX data scraping
115 versions - Latest release: about 1 month ago - 1 dependent package - 26 dependent repositories - 242 thousand downloads last month - 1,106 stars on GitHub - 1 maintainer
puro 0.0.1
Highly configurable data streams
1 version - Latest release: over 8 years ago - 1 dependent repositories - 10 downloads last month - 3 stars on GitHub - 1 maintainer
trafaret_schema 0.2.1
Validation and parsing library
4 versions - Latest release: over 8 years ago - 15 downloads last month - 8 stars on GitHub - 1 maintainer
justobjects 0.3.0
Simple data object (de)serialization and validation
8 versions - Latest release: almost 5 years ago - 1 dependent repositories - 17 downloads last month - 0 stars on GitHub - 1 maintainer
datamind 1.1.0
Two-agent inference-time data system over RAG, Graph, DB, Skills, and Memory
3 versions - Latest release: about 1 month ago - 1.74 thousand downloads last month - 455 stars on GitHub - 1 maintainer
locopy 0.7.0
Loading/Unloading to Amazon Redshift using Python
33 versions - Latest release: about 1 month ago - 1 dependent repositories - 1.69 thousand downloads last month - 114 stars on GitHub - 3 maintainers
dataspyre 0.3.0
Spyre makes it easy to build interactive web applications,and requires no knowledge of HTML, CSS,...
30 versions - Latest release: 7 months ago - 1 dependent repositories - 183 downloads last month - 833 stars on GitHub - 1 maintainer
faculty-cli 0.15.0
The command line interface to Faculty
14 versions - Latest release: over 1 year ago - 1 dependent repositories - 35 downloads last month - 4 maintainers
Top 2.3% on pypi.org
pycm 4.6 💰
Multi-class confusion matrix library in Python
50 versions - Latest release: 8 months ago - 4 dependent packages - 50 dependent repositories - 11.5 thousand downloads last month - 1,509 stars on GitHub - 3 maintainers
fractopo 0.9.2
Fracture Network Analysis
28 versions - Latest release: 5 months ago - 2 dependent repositories - 188 downloads last month - 31 stars on GitHub - 1 maintainer
Top 2.4% on pypi.org
finance-datareader 0.9.202
Financial data reader (price, stock list of markets)
56 versions - Latest release: 6 months ago - 5 dependent packages - 79 dependent repositories - 176 thousand downloads last month - 1,559 stars on GitHub - 1 maintainer
demuxem 0.1.8
demuxEM is the demultiplexing module of Pegasus
11 versions - Latest release: over 1 year ago - 1 dependent repositories - 671 downloads last month - 2 stars on GitHub - 3 maintainers
dataflex 1.1.0
A data-centric training system for Large Language Models
2 versions - Latest release: about 1 month ago - 122 downloads last month - 3,297 stars on GitHub - 1 maintainer
Top 4.9% on pypi.org
retriever 3.1.0
Data Retriever
12 versions - Latest release: over 4 years ago - 3 dependent repositories - 149 downloads last month - 327 stars on GitHub - 2 maintainers
Top 1.5% on pypi.org
pooch 1.9.0
A friend to fetch your data files
35 versions - Latest release: 9 months ago - 298 dependent packages - 2,570 dependent repositories - 12.8 million downloads last month - 745 stars on GitHub - 2 maintainers
ytree 3.3.1
A Python package for analyzing tree data and especially merger trees.
25 versions - Latest release: about 1 year ago - 3 dependent repositories - 1.01 thousand downloads last month - 17 stars on GitHub - 1 maintainer
Top 1.0% on pypi.org
missingno 0.5.2
Missing data visualization module for Python.
26 versions - Latest release: over 3 years ago - 32 dependent packages - 1,920 dependent repositories - 249 thousand downloads last month - 4,212 stars on GitHub - 1 maintainer
category-encoders-dev 2.2.2.post2021
A collection sklearn transformers to encode categorical variables as numeric
1 version - Latest release: about 5 years ago - 1 dependent repositories - 8 downloads last month - 2,510 stars on GitHub - 1 maintainer
pyradigm 0.6.6
Python-based data structure to improve handling of datasets in machine learning workflows
13 versions - Latest release: over 1 year ago - 2 dependent packages - 5 dependent repositories - 106 downloads last month - 30 stars on GitHub - 1 maintainer
pydynpd 0.2.2
A package to estimate dynamic panel data model using difference GMM and system GMM.
21 versions - Latest release: 11 months ago - 1 dependent repositories - 2.93 thousand downloads last month - 36 stars on GitHub - 1 maintainer
sangreal-odo 0.0.5
Data migration utilities
2 versions - Latest release: over 6 years ago - 1 dependent repositories - 13 downloads last month - 1,005 stars on GitHub - 1 maintainer
Top 2.2% on pypi.org
odo 0.5.0
Data migration utilities
8 versions - Latest release: over 10 years ago - 2 dependent packages - 2,044 dependent repositories - 32.7 thousand downloads last month - 1,005 stars on GitHub - 5 maintainers
odo-fixpandas20 0.5.3
Data migration utilities
1 version - Latest release: about 8 years ago - 1 dependent repositories - 19 downloads last month - 1,005 stars on GitHub - 1 maintainer
amisrsynthdata 1.2.0
Tool for generating synthetic AMISR data files.
10 versions - Latest release: 3 months ago - 104 downloads last month - 4 stars on GitHub - 1 maintainer
Top 7.8% on pypi.org
finmarketpy 0.11.19 💰
finmarketpy is a Python based library for backtesting trading strategies
19 versions - Latest release: over 1 year ago - 4 dependent repositories - 489 downloads last month - 3,821 stars on GitHub - 1 maintainer
Top 6.0% on pypi.org
findatapy 0.1.42 💰
Market data library
41 versions - Latest release: 7 months ago - 5 dependent repositories - 1.15 thousand downloads last month - 2,140 stars on GitHub - 1 maintainer
Top 0.7% on pypi.org
great-expectations 1.24.1
Always know what to expect from your data.
372 versions - Latest release: 6 days ago - 58 dependent packages - 284 dependent repositories - 19.2 million downloads last month - 11,908 stars on GitHub - 8 maintainers
superduper-framework 0.10.0
Build compositional and declarative AI applications and agents
60 versions - Latest release: about 1 year ago - 257 downloads last month - 5,326 stars on GitHub - 1 maintainer
dbt-mcp 2.9.0
A MCP (Model Context Protocol) server for interacting with dbt resources.
98 versions - Latest release: 1 day ago - 75.8 thousand downloads last month - 612 stars on GitHub - 1 maintainer
pypillometry 1.0.2
Pupillometry in Python.
4 versions - Latest release: over 6 years ago - 1 dependent repositories - 19 downloads last month - 38 stars on GitHub - 1 maintainer
iflow-mcp_dividor-hdx-mcp-server 1.0.0
MCP server for the Humanitarian Data Exchange (HDX) API
1 version - Latest release: 9 months ago - 53 downloads last month - 1 maintainer
yonk 0.1.1 💰
yonk is a Python package for creating data science structure
1 version - Latest release: over 3 years ago - 17 downloads last month - 2 stars on GitHub - 1 maintainer
iflow-mcp_datuanalytics-datu-core 0.0.1
LLM-Driven Data Transformations
1 version - Latest release: 9 months ago - 16 downloads last month - 41 stars on GitHub - 1 maintainer
clusim 0.4
Clustering simliarity
7 versions - Latest release: over 6 years ago - 2 dependent repositories - 504 downloads last month - 73 stars on GitHub - 1 maintainer
lfake 18.9.0 💰
Fake data
1 version - Latest release: over 3 years ago - 13 downloads last month - 19,447 stars on GitHub - 1 maintainer
Top 0.3% on pypi.org
faker 40.44.0 💰
Faker is a Python package that generates fake data for you.
511 versions - Latest release: about 13 hours ago - 382 dependent packages - 15,807 dependent repositories - 64.7 million downloads last month - 19,447 stars on GitHub - 2 maintainers
mf4-rs 3.7.0
Python bindings for mf4-rs - A minimal library for working with ASAM MDF 4 measurement files
26 versions - Latest release: 11 days ago - 90 downloads last month - 0 stars on GitHub - 1 maintainer
Top 1.8% on pypi.org
dython 0.7.12 💰
A set of data tools in Python
52 versions - Latest release: 11 months ago - 9 dependent packages - 47 dependent repositories - 34 thousand downloads last month - 513 stars on GitHub - 1 maintainer
py-data-juicer 1.6.1
Data Processing for and with Foundation Models.
33 versions - Latest release: 10 days ago - 1.77 thousand downloads last month - 7,189 stars on GitHub - 1 maintainer
naif-pds4-bundler 1.7.3
NAIF PDS4 Bundler (naif-pds4-bundler) is a software package that generates a PDS4 SPICE archives.
18 versions - Latest release: 7 months ago - 1 dependent repositories - 91 downloads last month - 5 stars on GitHub - 7 maintainers
Related Keywords
python 1,498 etl 499 pipeline 496 data-engineering 476 data-analysis 422 snowflake 391 api 380 elt 366 data-integration 361 mysql 345 postgresql 341 bigquery 328 redshift 327 data-science 326 mssql 322 data-pipeline 320 s3 319 data-collection 310 java 305 self-hosted 303 change-data-capture 301 pandas 282 analysis 270 llm 260 science 243 database 237 analytics 229 ai 209 sql 189 rag 184 framework 175 machine-learning 171 cli 166 finance 164 agents 162 visualization 161 json 160 csv 156 fine-tuning 140 python3 136 application 126 vector-database 122 llamaindex 121 multi-agents 118 statistics 115 validation 107 mcp 105 dataset 101 learning 96 testing 94 scraper 89 automation 86 processing 85 machine 84 django 83 open-source 82 dataframe 80 sdk 73 data-visualization 71 ml 71 connectors 70 dataops 67 library 67 data-pipelines 66 client 66 orchestration 65 schema 65 scraping 64 pypi 64 web 62 dbt 62 data-structures 62 parquet 61 agent 60 climate 60 generator 60 data-lineage 60 test 58 quality 57 data-warehouse 57 hacktoberfest 56 stock 56 trading 56 data science 56 web-scraping 55 workflow 53 warehouse 53 openai 53 airbyte 52 duckdb 51 numpy 51 nlp 50 faker 50 excel 50 mining 49 tools 49 connector 49 text 48 ai-agents 48 langchain 48