malepati/custom_template_working
0
1---2title: Accusaga Slides Presentation3emoji: 📈4colorFrom: blue5colorTo: red6sdk: docker7pinned: false8app_port: 78609---10 11<p align="center">12 <img src="readme_assets/images/presenton-logo.png" height="90" alt="Presenton Logo" />13</p>14 15<p align="center">16 <a href="https://discord.gg/9ZsKKxudNE">17 <img src="https://img.shields.io/badge/Discord-Join%20Community-5865F2?logo=discord&style=for-the-badge" alt="Join our Discord" />18 </a>19 20 <a href="https://x.com/presentonai">21 <img src="https://img.shields.io/badge/X-Follow%20Us-000000?logo=twitter&style=for-the-badge" alt="Follow us on X" />22 </a>23</p>24 25# Open-Source AI Presentation Generator and API (Gamma, Beautiful AI, Decktopus Alternative)26 27**Presenton** is an open-source application for generating presentations with AI — all running locally on your device. Stay in control of your data and privacy while using models like OpenAI and Gemini, or use your own hosted models through Ollama.28 29**✨ Now, generate presentations with your existing PPTX file! Just upload your presentation file to create template design and then use that template to generate on brand and on design presentation on any topic.**30 3132 33> [!NOTE] > **Enterprise Inquiries:**34> For enterprise use, custom deployments, or partnership opportunities, contact us at **[suraj@presenton.ai](mailto:suraj@presenton.ai)**.35 36> [!IMPORTANT]37> Like Presenton? A ⭐ star shows your support and encourages us to keep building!38 39> [!TIP]40> For detailed setup guides, API documentation, and advanced configuration options, visit our **[Official Documentation](https://docs.presenton.ai)**41 42## ✨ More Freedom with AI Presentations43 44Presenton gives you complete control over your AI presentation workflow. Choose your models, customize your experience, and keep your data private.45 46- ✅ **Custom Templates & Themes** — Create unlimited presentation designs with HTML and Tailwind CSS47- ✅ **AI Template Generation** — Create presentation templates from existing Powerpoint documents.48- ✅ **Flexible Generation** — Build presentations from prompts or uploaded documents49- ✅ **Export Ready** — Save as PowerPoint (PPTX) and PDF with professional formatting50- ✅ **Built-In MCP Server** — Generate presentations over Model Context Protocol51- ✅ **Bring Your Own Key** — Use your own API keys for OpenAI, Google Gemini, Anthropic Claude, or any compatible provider. Only pay for what you use, no hidden fees or subscriptions.52- ✅ **Ollama Integration** — Run open-source models locally with full privacy53- ✅ **OpenAI API Compatible** — Connect to any OpenAI-compatible endpoint with your own models54- ✅ **Multi-Provider Support** — Mix and match text and image generation providers55- ✅ **Versatile Image Generation** — Choose from DALL-E 3, Gemini Flash, Pexels, or Pixabay56- ✅ **Rich Media Support** — Icons, charts, and custom graphics for professional presentations57- ✅ **Runs Locally** — All processing happens on your device, no cloud dependencies58- ✅ **API Deployment** — Host as your own API service for your team59- ✅ **Fully Open-Source** — Apache 2.0 licensed, inspect, modify, and contribute60- ✅ **Docker Ready** — One-command deployment with GPU support for local models61 62## Presenton Cloud63 64<a href="https://presenton.ai" target="_blank" align="center">65 66 <img src="readme_assets/cloud-banner.png" height="350" alt="Presenton Logo" />67</a>68 69## Running Presenton Docker70 71#### 1. Start Presenton72 73##### Linux/MacOS (Bash/Zsh Shell):74 75```bash76docker run -it --name presenton -p 5000:80 -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest77```78 79##### Windows (PowerShell):80 81```bash82docker run -it --name presenton -p 5000:80 -v "${PWD}\app_data:/app_data" ghcr.io/presenton/presenton:latest83```84 85#### 2. Open Presenton86 87Open http://localhost:5000 on browser of your choice to use Presenton.88 89> **Note: You can replace 5000 with any other port number of your choice to run Presenton on a different port number.**90 91## Deployment Configurations92 93You may want to directly provide your API KEYS as environment variables and keep them hidden. You can set these environment variables to achieve it.94 95- **CAN_CHANGE_KEYS=[true/false]**: Set this to **false** if you want to keep API Keys hidden and make them unmodifiable.96- **LLM=[openai/google/anthropic/ollama/custom]**: Select **LLM** of your choice.97- **OPENAI_API_KEY=[Your OpenAI API Key]**: Provide this if **LLM** is set to **openai**98- **OPENAI_MODEL=[OpenAI Model ID]**: Provide this if **LLM** is set to **openai** (default: "gpt-4.1")99- **GOOGLE_API_KEY=[Your Google API Key]**: Provide this if **LLM** is set to **google**100- **GOOGLE_MODEL=[Google Model ID]**: Provide this if **LLM** is set to **google** (default: "models/gemini-2.0-flash")101- **ANTHROPIC_API_KEY=[Your Anthropic API Key]**: Provide this if **LLM** is set to **anthropic**102- **ANTHROPIC_MODEL=[Anthropic Model ID]**: Provide this if **LLM** is set to **anthropic** (default: "claude-3-5-sonnet-20241022")103- **OLLAMA_URL=[Custom Ollama URL]**: Provide this if you want to custom Ollama URL and **LLM** is set to **ollama**104- **OLLAMA_MODEL=[Ollama Model ID]**: Provide this if **LLM** is set to **ollama**105- **CUSTOM_LLM_URL=[Custom OpenAI Compatible URL]**: Provide this if **LLM** is set to **custom**106- **CUSTOM_LLM_API_KEY=[Custom OpenAI Compatible API KEY]**: Provide this if **LLM** is set to **custom**107- **CUSTOM_MODEL=[Custom Model ID]**: Provide this if **LLM** is set to **custom**108- **TOOL_CALLS=[Enable/Disable Tool Calls on Custom LLM]**: If **true**, **LLM** will use Tool Call instead of Json Schema for Structured Output.109- **DISABLE_THINKING=[Enable/Disable Thinking on Custom LLM]**: If **true**, Thinking will be disabled.110- **WEB_GROUNDING=[Enable/Disable Web Search for OpenAI, Google And Anthropic]**: If **true**, LLM will be able to search web for better results.111 112You can also set the following environment variables to customize the image generation provider and API keys:113 114- **DISABLE_IMAGE_GENERATION**: If **true**, Image Generation will be disabled for slides.115- **IMAGE_PROVIDER=[pexels/pixabay/gemini_flash/dall-e-3]**: Select the image provider of your choice.116 - Required if **DISABLE_IMAGE_GENERATION** is not set to **true**.117 - Defaults to **dall-e-3** for OpenAI models, **gemini_flash** for Google models if not set.118- **PEXELS_API_KEY=[Your Pexels API Key]**: Required if using **pexels** as the image provider.119- **PIXABAY_API_KEY=[Your Pixabay API Key]**: Required if using **pixabay** as the image provider.120- **GOOGLE_API_KEY=[Your Google API Key]**: Required if using **gemini_flash** as the image provider.121- **OPENAI_API_KEY=[Your OpenAI API Key]**: Required if using **dall-e-3** as the image provider.122 123You can disable anonymous telemetry using the following environment variable:124 125- **DISABLE_ANONYMOUS_TELEMETRY=[true/false]**: Set this to **true** to disable anonymous telemetry.126 127> **Note:** You can freely choose both the LLM (text generation) and the image provider. Supported image providers: **pexels**, **pixabay**, **gemini_flash** (Google), and **dall-e-3** (OpenAI).128 129### Using OpenAI130 131```bash132docker run -it --name presenton -p 5000:80 -e LLM="openai" -e OPENAI_API_KEY="******" -e IMAGE_PROVIDER="dall-e-3" -e CAN_CHANGE_KEYS="false" -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest133```134 135### Using Google136 137```bash138docker run -it --name presenton -p 5000:80 -e LLM="google" -e GOOGLE_API_KEY="******" -e IMAGE_PROVIDER="gemini_flash" -e CAN_CHANGE_KEYS="false" -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest139```140 141### Using Ollama142 143```bash144docker run -it --name presenton -p 5000:80 -e LLM="ollama" -e OLLAMA_MODEL="llama3.2:3b" -e IMAGE_PROVIDER="pexels" -e PEXELS_API_KEY="*******" -e CAN_CHANGE_KEYS="false" -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest145```146 147### Using Anthropic148 149```bash150docker run -it --name presenton -p 5000:80 -e LLM="anthropic" -e ANTHROPIC_API_KEY="******" -e IMAGE_PROVIDER="pexels" -e PEXELS_API_KEY="******" -e CAN_CHANGE_KEYS="false" -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest151```152 153### Using OpenAI Compatible API154 155```bash156docker run -it -p 5000:80 -e CAN_CHANGE_KEYS="false" -e LLM="custom" -e CUSTOM_LLM_URL="http://*****" -e CUSTOM_LLM_API_KEY="*****" -e CUSTOM_MODEL="llama3.2:3b" -e IMAGE_PROVIDER="pexels" -e PEXELS_API_KEY="********" -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest157```158 159#### Running Presenton with GPU Support160 161To use GPU acceleration with Ollama models, you need to install and configure the NVIDIA Container Toolkit. This allows Docker containers to access your NVIDIA GPU.162 163Once the NVIDIA Container Toolkit is installed and configured, you can run Presenton with GPU support by adding the `--gpus=all` flag:164 165```bash166docker run -it --name presenton --gpus=all -p 5000:80 -e LLM="ollama" -e OLLAMA_MODEL="llama3.2:3b" -e IMAGE_PROVIDER="pexels" -e PEXELS_API_KEY="*******" -e CAN_CHANGE_KEYS="false" -v "./app_data:/app_data" ghcr.io/presenton/presenton:latest167```168 169> **Note:** GPU acceleration significantly improves the performance of Ollama models, especially for larger models. Make sure you have sufficient GPU memory for your chosen model.170 171## Generate Presentation over API172 173### Generate Presentation174 175Endpoint: `/api/v1/ppt/presentation/generate`176 177Method: `POST`178 179Content-Type: `application/json`180 181#### Request Body182 183| Parameter | Type | Required | Description |184| ------------------------- | ---------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------ |185| content | string | Yes | The content for generating the presentation |186| slides_markdown | string[] \| null | No | The markdown for the slides |187| instructions | string \| null | No | The instruction for generating the presentation |188| tone | string | No | The tone to use for the text (default: "default"). Available options: "default", "casual", "professional", "funny", "educational", "sales_pitch" |189| verbosity | string | No | How verbose the text should be (default: "standard"). Available options: "concise", "standard", "text-heavy" |190| web_search | boolean | No | Whether to enable web search (default: false) |191| n_slides | integer | No | Number of slides to generate (default: 8) |192| language | string | No | Language for the presentation (default: "English") |193| template | string | No | Template to use for the presentation (default: "general") |194| include_table_of_contents | boolean | No | Whether to include a table of contents (default: false) |195| include_title_slide | boolean | No | Whether to include a title slide (default: true) |196| files | string[] \| null | No | Files to use for the presentation. Use /api/v1/ppt/files/upload to upload files |197| export_as | string | No | Export format (default: "pptx"). Available options: "pptx", "pdf" |198 199#### Response200 201```json202{203 "presentation_id": "string",204 "path": "string",205 "edit_path": "string"206}207```208 209#### Example Request210 211```bash212curl -X POST http://localhost:5000/api/v1/ppt/presentation/generate \213 -H "Content-Type: application/json" \214 -d '{215 "content": "Introduction to Machine Learning",216 "n_slides": 5,217 "language": "English",218 "template": "general",219 "export_as": "pptx"220 }'221```222 223#### Example Response224 225```json226{227 "presentation_id": "d3000f96-096c-4768-b67b-e99aed029b57",228 "path": "/app_data/d3000f96-096c-4768-b67b-e99aed029b57/Introduction_to_Machine_Learning.pptx",229 "edit_path": "/presentation?id=d3000f96-096c-4768-b67b-e99aed029b57"230}231```232 233> **Note:** Make sure to prepend your server's root URL to the path and edit_path fields in the response to construct valid links.234 235For detailed info checkout [API documentation](https://docs.presenton.ai/using-presenton-api).236 237### API Tutorials238 239- [Generate Presentations via API in 5 minutes](https://docs.presenton.ai/tutorial/generate-presentation-over-api)240- [Create Presentations from CSV using AI](https://docs.presenton.ai/tutorial/generate-presentation-from-csv)241- [Create Data Reports Using AI](https://docs.presenton.ai/tutorial/create-data-reports-using-ai)242 243## Roadmap244 245- [x] Support for custom HTML templates by developers246- [x] Support for accessing custom templates over API247- [x] Implement MCP server248- [ ] Ability for users to change system prompt249- [x] Support external SQL database250 251## UI Features252 253### 1. Add prompt, select number of slides and language254 255256 257### 2. Select theme258 259260 261### 3. Review and edit outline262 263264 265### 4. Select theme266 267268 269### 5. Present on app270 271272 273### 6. Change theme274 275276 277### 7. Export presentation as PDF and PPTX278 279280 281## Community282 283[Discord](https://discord.gg/9ZsKKxudNE)284 285## License286 287Apache 2.0288