Reverse Dependencies of python-pptx

The following projects have a declared dependency on python-pptx:

• academia_tts — A package to convert PPTX slide notes to audio and embed them into the slides
• addereq — 地震前兆数据自动处理框架
• agixt — An Artificial Intelligence Automation Platform. AI Instruction management from various providers, has an adaptive memory, and a versatile plugin system with many commands including web browsing. Supports many AI providers and models and growing support every day.
• ainyan — Helpers for AI training
• akasha-terminal — document QA(RAG) package using langchain and chromadb
• algorin-cli — Acceso a GPT-3 y procesamiento de documentos desde la línea de comandos.
• alita-sdk — SDK for building langchain agents using resouces from Alita
• amai-ai-chatbot — African Multimodal Artificial Intelligence
• analysta-index — Extension of Langchain loaders, llms and retrievers for Analysta
• anoteai — An SDK for interacting with the Anote API
• ansys-dynamicreporting-core — Python interface to Ansys Dynamic Reporting
• anydocs — no summary
• arches-templating — Arches templating provides an extensible templating engine for various file types
• Artemisa — Sistema de extración de información de documentos
• astromol — A Database of Molecules Detected in Space
• auto-coder — AutoCoder: AutoCoder
• auto-deep-research — open deep research based on autoagent
• auto-retrieval-plugin — Create and host retrieval plugins for ChatGPT in one click
• autogen-agentchat-um — Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework
• automate-office — Offic自动化工具-自用，在原有包的基础上二次开发, PPT部分暂时告一段落, Word暂时用处不大, Excel做了一些函数和例子
• aws-textract-pipeline — Package short description.
• bacore — BACore is a framework for business analysis and test automation.
• bibletk — Toolkit for bible
• bic-pptx-report-generator — Input folder with pictures and text files where the text files describe the pictures and are named to match the picture they describe. The folders are named what you want the slides to be named, and the names of the pictures match what you would want in the labels.
• bisheng-unstructured — ETLs fro LLMs
• botrun-ask-folder — no summary
• bsrag-unstructured — A Python package with a built-in web application
• burocracy — Templating and pdf generation for docx/pptx files
• cdb-cellmaps — no summary
• chgksuite — A package for chgk automation
• ChurchSong — Download the event agenda from ChurchTool and instantiate a PowerPoint slide template with the names and portraits of service staff as well as song database verification.
• cocopack — Programmatic toolkits for Python and shell scripting
• codemie-tools — Package with CodeMie tools for AI Agents
• com.castsoftware.uc.arg — Assessment Report Generator (ARG)
• com.castsoftware.uc.python.common — A set of common classes and methods for use with python projects
• connor-nlp — Fast and fully local NLP file organizer that organizes files based on their content.
• consultify — Turns analyses on Python into management consulting-style PowerPoint slides.
• convert2ppt — Convert your documents to PPT with AI
• convertextract — Arbitrary transliterations on Microsoft Office documents
• copilot4office — ChatGPT copilot for office files
• dataplaybook — Playbooks for data. Open, process and save table based data.
• dbgpt-ext — Add your description here
• dbnomics-pptx-tools — DBnomics PowerPoint (pptx) tools
• delos-unichunking — Universal chunking functions to extract LLM-friendly chunks from any file type.
• desktop-env — The package provides a desktop environment for setting and evaluating desktop automation tasks.
• DetectBinod — Detect Binod In Files
• df-extract — DecisionFacts Extraction Library extracts content from PDF, PPTX, Docx, png, jpg., and convert as structured JSON data.
• django-template-reports — Generates reports (PPTX) from template files that are flexibly populated using the Django ORM, without hard-coding.
• doc2markdown — A tool to convert various document formats to Markdown
• docetl — ETL with LLM operations.
• docling — SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
• docling-google-ocr — SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
• docowling — SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
• docparser-feb — Document parsing tool for LLM training and Rag
• docs2vecs — A library/cli that allows you to vectorize your data, enabling you to create RAG powered applications.
• DocumentsReader — A package to read and process documents
• dpkits — A small package for data processing
• drag-copilot — A notebook copilot for data analysis
• drawbook — A Python library for illustrating children's books.
• drivescanner — Scan your filesystem to look for files that are a potential GDPR risk
• dspygen — A Ruby on Rails style framework for the DSPy (Demonstrate, Search, Predict) project for Language Models like GPT, BERT, and LLama.
• dsstools — An opiniated wrapper around NetworkX to help with drawing and positioning.
• dummy-kinematics — no summary
• dynamiq — Dynamiq is an orchestration framework for agentic AI and LLM applications
• edge-pptx — 用于生成 PowerPoint 文件的 Python 模块
• edsl — Create and analyze LLM-based surveys
• elliot-markitdown — 一个文档处理和OCR工具包集合
• evodflow — Awesome evoflow created by maycuatroi
• extended-docling — SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications, now with Google OCR support.
• extract-office-content — Tool for extracting content from office files.
• fairy-doc — A lightweight toolbox to manipulate documents
• faker-file — Generate files with fake data.
• farm-haystack — LLM framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data.
• fasthelp — An Useful Python Helper that Bundles some functions (And added some new ones!)
• FeynmanAi — A command-line tool for using RAG model on Local documents
• figuregen — Figure Generator
• filemac — Open source Python CLI toolkit for conversion, manipulation, Analysis of files (All major file operations)
• filesense — A package to rename files based on their content using Generative AI.
• finance-cn — python for wps
• findmyfile — This package allows you to search a directory for documents that match keywords
• firstaid — A First-Aid for Data Analysis and Reporting
• flexidata — FlexiData is an open-source Python package designed for processing unstructured data.
• flowtask — Framework for running Tasks and from CLI and API for orchestation. Component-based Task builder/Runner for non-programmers.
• freamon — Advanced feature engineering, analysis, modeling and optimization for data science
• friday-agent — An self-improving embodied conversational agent seamlessly integrated into the operating system to automate our daily tasks.
• fsearchpy — This package searches for a specified text pattern in various documents, including office and PDFs and prints results including file name, path and size while displaying progress and completion time
• gen-pptx-from-simple-text — CLI to generate powerpoint slides from simple text file[s].
• GeneralAgent — General Agent: From LLM to Agent
• genutility — A collection of various Python utilities
• geoassistant — A Python geotechnical library
• gg_daigua — 方便的工具
• git-bob — git-bob uses AI to solve Github-issues. It runs inside the Github CI, no need to install anything on your computer.
• global-parser-lib — A library for parsing various file types.
• goldretriever — Create and host retrieval plugins for ChatGPT in one click
• gpt3discord — A Chat GPT Discord bot
• gptdb — GPT-DB is an experimental open-source project that uses localized GPT large models to interact with your data and environment. With this solution, you can be assured that there is no risk of data leakage, and your data is 100% private and secure.
• gptswarm — GPTSwarm: Language Agents as Optimizable Graphs
• gramex — Gramex: Low Code Data Solutions Platform
• halerium-utilities — Halerium utilities is a Python package of utility functions for working on the Halerium platform.
• hazelbean — Collection of geospatial algorithms, parallel computation utilities and project management tools.