slide-deck-ai

Co-create a PowerPoint presentation with Generative AI

Stars: 259

Visit

SlideDeck AI is a tool that leverages Generative Artificial Intelligence to co-create slide decks on any topic. Users can describe their topic and let SlideDeck AI generate a PowerPoint slide deck, streamlining the presentation creation process. The tool offers an iterative workflow with a conversational interface for creating and improving presentations. It uses Mistral Nemo Instruct to generate initial slide content, searches and downloads images based on keywords, and allows users to refine content through additional instructions. SlideDeck AI provides pre-defined presentation templates and a history of instructions for users to enhance their presentations.

README:

title: SlideDeck AI emoji: 🏢 colorFrom: yellow colorTo: green sdk: streamlit sdk_version: 1.44.1 app_file: app.py pinned: false license: mit

SlideDeck AI

We spend a lot of time on creating the slides and organizing our thoughts for any presentation. With SlideDeck AI, co-create slide decks on any topic with Generative Artificial Intelligence. Describe your topic and let SlideDeck AI generate a PowerPoint slide deck for you—it's as simple as that!

Star History

Process

SlideDeck AI works in the following way:

Given a topic description, it uses a Large Language Model (LLM) to generate the initial content of the slides. The output is generated as structured JSON data based on a pre-defined schema.
Next, it uses the keywords from the JSON output to search and download a few images with a certain probability.
Subsequently, it uses the python-pptx library to generate the slides, based on the JSON data from the previous step. A user can choose from a set of pre-defined presentation templates.
At this stage onward, a user can provide additional instructions to refine the content. For example, one can ask to add another slide or modify an existing slide. A history of instructions is maintained.
Every time SlideDeck AI generates a PowerPoint presentation, a download button is provided. Clicking on the button will download the file.

In addition, SlideDeck AI can also create a presentation based on PDF files.

Summary of the LLMs

SlideDeck AI allows the use of different LLMs from several online providers—Azure OpenAI, Google, Cohere, Together AI, and OpenRouter. Most of these service providers offer generous free usage of relevant LLMs without requiring any billing information.

Based on several experiments, SlideDeck AI generally recommends the use of Mistral NeMo, Gemini Flash, and GPT-4o to generate the slide decks.

The supported LLMs offer different styles of content generation. Use one of the following LLMs along with relevant API keys/access tokens, as appropriate, to create the content of the slide deck:

LLM	Provider (code)	Requires API key	Characteristics
Gemini 2.0 Flash	Google Gemini API (`gg`)	Mandatory; get here	Faster, longer content
Gemini 2.0 Flash Lite	Google Gemini API (`gg`)	Mandatory; get here	Fastest, longer content
Gemini 2.5 Flash	Google Gemini API (`gg`)	Mandatory; get here	Faster, longer content
Gemini 2.5 Flash Lite	Google Gemini API (`gg`)	Mandatory; get here	Fastest, longer content
GPT	Azure OpenAI (`az`)	Mandatory; get here NOTE: You need to have your subscription/billing set up	Faster, longer content
Command R+	Cohere (`co`)	Mandatory; get here	Shorter, simpler content
Gemini-2.0-flash-001	OpenRouter (`or`)	Mandatory; get here	Faster, longer content
GPT-3.5 Turbo	OpenRouter (`or`)	Mandatory; get here	Faster, longer content
DeepSeek V3-0324	Together AI (`to`)	Mandatory; get here	Slower, medium-length
Llama 3.3 70B Instruct Turbo	Together AI (`to`)	Mandatory; get here	Slower, detailed
Llama 3.1 8B Instruct Turbo 128K	Together AI (`to`)	Mandatory; get here	Faster, shorter

IMPORTANT: SlideDeck AI does NOT store your API keys/tokens or transmit them elsewhere. If you provide your API key, it is only used to invoke the relevant LLM to generate contents. That's it! This is an Open-Source project, so feel free to audit the code and convince yourself.

In addition, offline LLMs provided by Ollama can be used. Read below to know more.

Icons

SlideDeck AI uses a subset of icons from bootstrap-icons-1.11.3 (MIT license) in the slides. A few icons from SVG Repo (CC0, MIT, and Apache licenses) are also used.

Local Development

SlideDeck AI uses LLMs via different providers. To run this project by yourself, you need to use an appropriate API key, for example, in a .env file. Alternatively, you can provide the access token in the app's user interface itself (UI).

Offline LLMs Using Ollama

SlideDeck AI allows the use of offline LLMs to generate the contents of the slide decks. This is typically suitable for individuals or organizations who would like to use self-hosted LLMs for privacy concerns, for example.

Offline LLMs are made available via Ollama. Therefore, a pre-requisite here is to have Ollama installed on the system and the desired LLM pulled locally. You should choose a model to use based on your hardware capacity. However, if you have no GPU, gemma3:1b can be a suitable model to run only on CPU.

In addition, the RUN_IN_OFFLINE_MODE environment variable needs to be set to True to enable the offline mode. This, for example, can be done using a .env file or from the terminal. The typical steps to use SlideDeck AI in offline mode (in a bash shell) are as follows:

# Environment initialization, especially on Debian
sudo apt update -y
sudo apt install python-is-python3 -y
sudo apt install git -y
# Change the package name based on the Python version installed: python -V
sudo apt install python3.11-venv -y

# Install Git Large File Storage (LFS)
sudo apt install git-lfs -y
git lfs install

ollama list  # View locally available LLMs
export RUN_IN_OFFLINE_MODE=True  # Enable the offline mode to use Ollama
git clone https://github.com/barun-saha/slide-deck-ai.git
cd slide-deck-ai
git lfs pull  # Pull the PPTX template files

python -m venv venv  # Create a virtual environment
source venv/bin/activate  # On a Linux system
pip install -r requirements.txt

streamlit run ./app.py  # Run the application

💡If you have cloned the repository locally but cannot open and view the PPTX templates, you may need to run git lfs pull to download the template files. Without this, although content generation will work, the slide deck cannot be created.

The .env file should be created inside the slide-deck-ai directory.

The UI is similar to the online mode. However, rather than selecting an LLM from a list, one has to write the name of the Ollama model to be used in a textbox. There is no API key asked here.

The online and offline modes are mutually exclusive. So, setting RUN_IN_OFFLINE_MODE to False will make SlideDeck AI use the online LLMs (i.e., the "original mode."). By default, RUN_IN_OFFLINE_MODE is set to False.

Finally, the focus is on using offline LLMs, not going completely offline. So, Internet connectivity would still be required to fetch the images from Pexels.

Live Demo

SlideDeck AI on Hugging Face Spaces
Demo video of the chat interface on YouTube
Demo video on using Azure OpenAI

Award

SlideDeck AI has won the 3rd Place in the Llama 2 Hackathon with Clarifai in 2023.

Contributors

SlideDeck AI is glad to have the following community contributions:

Srinivasan Ragothaman: added OpenRouter support and API keys mapping from the .env file.
Aditya: added support for page range selection for PDF files.
Sagar Bharatbhai Bharadia: added support for Gemini 2.5 Flash Lite and Gemini 2.5 Flash LLMs.

Thank you all for your contributions!

For Tasks:

Click tags to check more tools for each tasks

create slides improve presentation refine content download slides generate templates

For Jobs:

presentation designer content creator marketing specialist educational instructor business consultant

Alternative AI tools for slide-deck-ai

Similar Open Source Tools

slide-deck-ai

github

: 259

bolna

Bolna is an open-source platform for building voice-driven conversational applications using large language models (LLMs). It provides a comprehensive set of tools and integrations to handle various aspects of voice-based interactions, including telephony, transcription, LLM-based conversation handling, and text-to-speech synthesis. Bolna simplifies the process of creating voice agents that can perform tasks such as initiating phone calls, transcribing conversations, generating LLM-powered responses, and synthesizing speech. It supports multiple providers for each component, allowing users to customize their setup based on their specific needs. Bolna is designed to be easy to use, with a straightforward local setup process and well-documented APIs. It is also extensible, enabling users to integrate with other telephony providers or add custom functionality.

github

: 205

kaito

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

github

: 405

air-script

AirScript is a domain-specific language for expressing AIR constraints for STARKs, with the goal of enabling writing and auditing constraints without the need to learn a specific programming language. It also aims to perform automated optimizations and output constraint evaluator code in multiple target languages. The project is organized into several crates including Parser, MIR, AIR, Winterfell code generator, ACE code generator, and AirScript CLI for transpiling AIRs to target languages.

github

: 90

ArcticTraining

ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs). It offers modular trainer designs, simplified code structures, and integrated pipelines for creating and cleaning synthetic data, enabling users to enhance LLM capabilities like code generation and complex reasoning with greater efficiency and flexibility.

github

: 56

open-deep-research

Open Deep Research is an open-source project that serves as a clone of Open AI's Deep Research experiment. It utilizes Firecrawl's extract and search method along with a reasoning model to conduct in-depth research on the web. The project features Firecrawl Search + Extract, real-time data feeding to AI via search, structured data extraction from multiple websites, Next.js App Router for advanced routing, React Server Components and Server Actions for server-side rendering, AI SDK for generating text and structured objects, support for various model providers, styling with Tailwind CSS, data persistence with Vercel Postgres and Blob, and simple and secure authentication with NextAuth.js.

github

: 4.4k

LlamaEdge

The LlamaEdge project makes it easy to run LLM inference apps and create OpenAI-compatible API services for the Llama2 series of LLMs locally. It provides a Rust+Wasm stack for fast, portable, and secure LLM inference on heterogeneous edge devices. The project includes source code for text generation, chatbot, and API server applications, supporting all LLMs based on the llama2 framework in the GGUF format. LlamaEdge is committed to continuously testing and validating new open-source models and offers a list of supported models with download links and startup commands. It is cross-platform, supporting various OSes, CPUs, and GPUs, and provides troubleshooting tips for common errors.

github

: 1.3k

codebase-context-spec

The Codebase Context Specification (CCS) project aims to standardize embedding contextual information within codebases to enhance understanding for both AI and human developers. It introduces a convention similar to `.env` and `.editorconfig` files but focused on documenting code for both AI and humans. By providing structured contextual metadata, collaborative documentation guidelines, and standardized context files, developers can improve code comprehension, collaboration, and development efficiency. The project includes a linter for validating context files and provides guidelines for using the specification with AI assistants. Tooling recommendations suggest creating memory systems, IDE plugins, AI model integrations, and agents for context creation and utilization. Future directions include integration with existing documentation systems, dynamic context generation, and support for explicit context overriding.

github

: 75

contoso-chat

Contoso Chat is a Python sample demonstrating how to build, evaluate, and deploy a retail copilot application with Azure AI Studio using Promptflow with Prompty assets. The sample implements a Retrieval Augmented Generation approach to answer customer queries based on the company's product catalog and customer purchase history. It utilizes Azure AI Search, Azure Cosmos DB, Azure OpenAI, text-embeddings-ada-002, and GPT models for vectorizing user queries, AI-assisted evaluation, and generating chat responses. By exploring this sample, users can learn to build a retail copilot application, define prompts using Prompty, design, run & evaluate a copilot using Promptflow, provision and deploy the solution to Azure using the Azure Developer CLI, and understand Responsible AI practices for evaluation and content safety.

github

: 431

cloudflare-rag

This repository provides a fullstack example of building a Retrieval Augmented Generation (RAG) app with Cloudflare. It utilizes Cloudflare Workers, Pages, D1, KV, R2, AI Gateway, and Workers AI. The app features streaming interactions to the UI, hybrid RAG with Full-Text Search and Vector Search, switchable providers using AI Gateway, per-IP rate limiting with Cloudflare's KV, OCR within Cloudflare Worker, and Smart Placement for workload optimization. The development setup requires Node, pnpm, and wrangler CLI, along with setting up necessary primitives and API keys. Deployment involves setting up secrets and deploying the app to Cloudflare Pages. The project implements a Hybrid Search RAG approach combining Full Text Search against D1 and Hybrid Search with embeddings against Vectorize to enhance context for the LLM.

github

: 93

BeamNGpy

BeamNGpy is an official Python library providing an API to interact with BeamNG.tech, a video game focused on academia and industry. It allows remote control of vehicles, AI-controlled vehicles, dynamic sensor models, access to road network and scenario objects, and multiple clients. The library comes with low-level functions and higher-level interfaces for complex actions. BeamNGpy requires BeamNG.tech for usage and offers compatibility information for different versions. It also provides troubleshooting tips and encourages user contributions.

github

: 245

promptpanel

Prompt Panel is a tool designed to accelerate the adoption of AI agents by providing a platform where users can run large language models across any inference provider, create custom agent plugins, and use their own data safely. The tool allows users to break free from walled-gardens and have full control over their models, conversations, and logic. With Prompt Panel, users can pair their data with any language model, online or offline, and customize the system to meet their unique business needs without any restrictions.

github

: 53

jaison-core

J.A.I.son is a Python project designed for generating responses using various components and applications. It requires specific plugins like STT, T2T, TTSG, and TTSC to function properly. Users can customize responses, voice, and configurations. The project provides a Discord bot, Twitch events and chat integration, and VTube Studio Animation Hotkeyer. It also offers features for managing conversation history, training AI models, and monitoring conversations.

github

: 216

ersilia

The Ersilia Model Hub is a unified platform of pre-trained AI/ML models dedicated to infectious and neglected disease research. It offers an open-source, low-code solution that provides seamless access to AI/ML models for drug discovery. Models housed in the hub come from two sources: published models from literature (with due third-party acknowledgment) and custom models developed by the Ersilia team or contributors.

github

: 249

intelligence-layer-sdk

The Aleph Alpha Intelligence Layer️ offers a comprehensive suite of development tools for crafting solutions that harness the capabilities of large language models (LLMs). With a unified framework for LLM-based workflows, it facilitates seamless AI product development, from prototyping and prompt experimentation to result evaluation and deployment. The Intelligence Layer SDK provides features such as Composability, Evaluability, and Traceability, along with examples to get started. It supports local installation using poetry, integration with Docker, and access to LLM endpoints for tutorials and tasks like Summarization, Question Answering, Classification, Evaluation, and Parameter Optimization. The tool also offers pre-configured tasks for tasks like Classify, QA, Search, and Summarize, serving as a foundation for custom development.

github

: 69

langchainjs-quickstart-demo

Discover the journey of building a generative AI application using LangChain.js and Azure. This demo explores the development process from idea to production, using a RAG-based approach for a Q&A system based on YouTube video transcripts. The application allows to ask text-based questions about a YouTube video and uses the transcript of the video to generate responses. The code comes in two versions: local prototype using FAISS and Ollama with LLaMa3 model for completion and all-minilm-l6-v2 for embeddings, and Azure cloud version using Azure AI Search and GPT-4 Turbo model for completion and text-embedding-3-large for embeddings. Either version can be run as an API using the Azure Functions runtime.

github

: 53

For similar tasks

slide-deck-ai

github

: 259

PPTist

PPTist is a web-based presentation application that replicates most features of Microsoft Office PowerPoint. It supports various elements like text, images, shapes, charts, tables, videos, audio, and formulas. Users can edit and present slides directly in a web browser. It offers easy development with Vue 3.x and TypeScript, user-friendly experience with context menu and keyboard shortcuts, and feature-rich functionalities including AI-generated PPTs and mobile editing. PPTist aims to provide a desktop application-level experience for creating presentations.

github

: 6.4k

AI-on-the-edge-device-docs

This repository contains documentation for the AI on the Edge Device Project. Users can edit Markdown documents in the 'docs' folder, create Pull Requests to merge changes, and Github Actions will regenerate the documentation on the 'gh-pages' branch. The documentation includes parameter documentation, template generation for new parameters, formatting options like boxes using the admonition extension, and local testing instructions using MkDocs.

github

: 79

ComfyUI-Tara-LLM-Integration

Tara is a powerful node for ComfyUI that integrates Large Language Models (LLMs) to enhance and automate workflow processes. With Tara, you can create complex, intelligent workflows that refine and generate content, manage API keys, and seamlessly integrate various LLMs into your projects. It comprises nodes for handling OpenAI-compatible APIs, saving and loading API keys, composing multiple texts, and using predefined templates for OpenAI and Groq. Tara supports OpenAI and Grok models with plans to expand support to together.ai and Replicate. Users can install Tara via Git URL or ComfyUI Manager and utilize it for tasks like input guidance, saving and loading API keys, and generating text suitable for chaining in workflows.

github

: 79

For similar jobs

docq

Docq is a private and secure GenAI tool designed to extract knowledge from business documents, enabling users to find answers independently. It allows data to stay within organizational boundaries, supports self-hosting with various cloud vendors, and offers multi-model and multi-modal capabilities. Docq is extensible, open-source (AGPLv3), and provides commercial licensing options. The tool aims to be a turnkey solution for organizations to adopt AI innovation safely, with plans for future features like more data ingestion options and model fine-tuning.

github

: 51

slide-deck-ai

github

: 259

TinyTroupe

TinyTroupe is an experimental Python library that leverages Large Language Models (LLMs) to simulate artificial agents called TinyPersons with specific personalities, interests, and goals in simulated environments. The focus is on understanding human behavior through convincing interactions and customizable personas for various applications like advertisement evaluation, software testing, data generation, project management, and brainstorming. The tool aims to enhance human imagination and provide insights for better decision-making in business and productivity scenarios.

github

: 5.2k

LLMStack

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

github

: 1.5k

daily-poetry-image

Daily Chinese ancient poetry and AI-generated images powered by Bing DALL-E-3. GitHub Action triggers the process automatically. Poetry is provided by Today's Poem API. The website is built with Astro.

github

: 492

exif-photo-blog

EXIF Photo Blog is a full-stack photo blog application built with Next.js, Vercel, and Postgres. It features built-in authentication, photo upload with EXIF extraction, photo organization by tag, infinite scroll, light/dark mode, automatic OG image generation, a CMD-K menu with photo search, experimental support for AI-generated descriptions, and support for Fujifilm simulations. The application is easy to deploy to Vercel with just a few clicks and can be customized with a variety of environment variables.

github

: 992

SillyTavern

SillyTavern is a user interface you can install on your computer (and Android phones) that allows you to interact with text generation AIs and chat/roleplay with characters you or the community create. SillyTavern is a fork of TavernAI 1.2.8 which is under more active development and has added many major features. At this point, they can be thought of as completely independent programs.

github

: 18.4k

Twitter-Insight-LLM

This project enables you to fetch liked tweets from Twitter (using Selenium), save it to JSON and Excel files, and perform initial data analysis and image captions. This is part of the initial steps for a larger personal project involving Large Language Models (LLMs).

github

: 401