Onboarding
A Quick Guide to Getting Started with inferia
Welcome to inferia!
This guide will help you navigate and build with inferia, whether you’re a developer, researcher, or AI enthusiast. You'll learn how to explore cutting-edge AI models, rapidly prototype using inferia serverless infrastructure, and scale your projects with powerful on-demand deployments.
Who This Guide is For
This guide is for new inferia users looking to get familiar with the platform. It covers the core features, including the model library, interactive playground, and deployment options—all accessible through the web app.
For experienced users, this guide serves as a launchpad, with more in-depth resources available to dive into advanced features like DashCTL and optimized workflow integrations.
What You'll Learn
✅ Explore the Model Library – Discover AI models tailored for text, image, and audio processing. ✅ Test in the Playground – Experiment with prompts, tweak parameters, and generate real-time outputs. ✅ Prototype with Ease – Use inferia serverless environment for hassle-free AI development. ✅ Scale Seamlessly – Deploy AI models with predictable performance and customization. ✅ Build Advanced AI – Utilize Compound AI, function calling, and retrieval-augmented generation (RAG) for production-ready applications.
By the end of this guide, you’ll be fully equipped to build, optimize, and scale AI-powered solutions with inferia. Let’s dive in!
Step 1: Explore the Model Library
inferia provides a curated selection of top AI models for text generation, code assistance, and image processing.
Available Models
📝 LLMs – Dash-LLM 70B, Deepseek V3, and Qwen2.5 Coder 32B Instruct 🖼️ Vision Models – DashVision 90B, Stable Diffusion 3.5 Large Turbo 🎵 Audio Models – Whisper V3, Whisper V3 Turbo 📊 Embeddings – Nomic AI’s advanced embedding models
Ways to Access inferia
🌍 Web App – Manage models effortlessly through a browser-based UI. 🐍 Python SDK – Integrate inferia into your workflows programmatically. 🔗 Third-Party Tools – Use inferia API keys with external applications. 📚 Community Cookbook – Access notebooks and real-world use cases.
Step 2: Experiment with the Playground
The Model Playground is the fastest way to test and fine-tune AI models.
Playground Features
🎛 Parameter Controls – Adjust temperature, token limits, and response length. 💻 Code Snippets – Instantly copy pre-written Python, TypeScript, and Shell scripts. 📂 File Uploads – Test multimodal AI with images, text, and audio inputs. 🔍 Model Switching – Quickly swap between models with a single command.
Step 3: Prototyping with Serverless
inferia serverless AI lets you experiment and deploy models without managing infrastructure.
Why Use inferia Serverless?
🚀 Instant Deployment – No setup required. 🛠 No Infrastructure Overhead – Focus on AI, not backend complexities. ⚙️ Easily Adjust Parameters – Modify settings for precision control. 💰 Cost-Effective – Pay only for what you use.
🔑 Get Started – Generate your API key in account settings to authenticate requests.
Step 4: Scale with On-Demand Deployments
For more predictable performance, inferia on-demand deployments provide dedicated resources with GPU customization.
Key Benefits
⚡ Consistent Performance – No interruptions from shared workloads. 📈 Dynamic Scaling – Allocate resources as needed. 🔧 Customization – Choose GPU types, enable extended context, and optimize costs. 💰 Cost-Efficient – Reserve capacity for long-term AI workloads.
Step 5: Unlock Advanced AI Capabilities
Go beyond standard AI models with Compound AI, function calling, and RAG.
Advanced Features
🛠 Compound AI – Combine multiple AI models for more complex workflows. 🔗 API Integration – Seamlessly connect AI models with other applications. 📊 Workflow Optimization – Automate and streamline AI-driven processes.
📚 Explore Our Documentation – Learn how to fine-tune models, optimize performance, and scale your AI projects effectively.
🚀 Ready to Build? Dive Into the Docs!
Continue exploring inferia documentation to unlock the full potential of the platform and take your AI solutions to the next level.
Welcome to inferia – where AI innovation meets seamless execution! 💡
Last updated