# io.net

## Docs

- [Overview](https://io.net/docs/guides/announcements/announcements.md): Stay up to date with the latest updates, migrations, and important news from io.net.
- [Action Required for Expired Refresh Tokens](https://io.net/docs/guides/announcements/important-action-required-for-expired-refresh-tokens.md): May 2025
- [Supplier Migration Guide: Upgrading to M4 Series Devices](https://io.net/docs/guides/announcements/supplier-migration-guide-upgrading-to-m4-series-devices.md): April 2025
- [Architectural Layers](https://io.net/docs/guides/architecture/io-architecture.md): The IO Portal architecture is a multi-layered, cohesive structure that provides a seamless, secure, and efficient user experience. Each layer has a distinct role, working in tandem to ensure the system's optimal performance. The architecture is built upon modern technologies, ensuring scalability, r…
- [IO Network](https://io.net/docs/guides/architecture/io-network.md): This article explores the concepts of mesh VPN networks and how we leverage their benefits to improve performance and reliability in the io.net protocol.
- [IO Tunnels](https://io.net/docs/guides/architecture/io-tunnels.md): Reverse tunnels technology provides a way to bypass firewall and NAT restrictions, enabling secure access to remote resources. This article discusses the concept of reverse tunnels, how they work, and how io.net uses them to simplify engineer access to AntMiners Clusters.
- [Overview](https://io.net/docs/guides/block-rewards/block-rewards.md)
- [Monitor Block Rewards](https://io.net/docs/guides/block-rewards/monitor-block-rewards.md)
- [Device Block Reward Multiplier](https://io.net/docs/guides/block-rewards/proposed-device-block-reward-multiplier.md): A detailed comparison of 2025 block reward multipliers by device type, with upcoming staking-related adjustments.
- [Agent Cloud](https://io.net/docs/guides/clouds/agent-cloud.md): Empower your AI agents to provision, manage, and scale GPU infrastructure via the io.net network.
- [Confidential Compute Attestation](https://io.net/docs/guides/clouds/confidential-compute-attestation-overview.md): Learn what confidential compute attestation is and how it can be utilized to verify secure workloads on io.net Cloud. Explore Trusted Execution Environments (TEE), GPU verification, and hardware-based security for sensitive compute.
- [Confidential Compute](https://io.net/docs/guides/clouds/confidential-compute-overview.md): Run secure AI workloads with Intel TDX encryption on io.cloud. Protect data in use on H100, H200, and B200 GPUs at up to 90% lower cost.
- [Data Science Specification](https://io.net/docs/guides/clouds/data-science-image-full-specification.md)
- [Bare Metal (Self Serve) Moving Forward](https://io.net/docs/guides/clouds/deploy-bare-metal-cluster.md): Bare Metal clusters give you direct access to hardware for maximum performance, low latency, high efficiency, and full control over configuration.
- [Deploy CaaS](https://io.net/docs/guides/clouds/deploy-containers.md): Flexible & High-Performance Containers built for rapid deployment and scalable AI workloads
- [Deploy Ray Cluster](https://io.net/docs/guides/clouds/deploy-ray-cluster.md): This document explains how to deploy a Ray cluster by leveraging compute power in io.net's DePIN network.
- [Deploy VM on Demand](https://io.net/docs/guides/clouds/deploy-vm-on-demand.md): Instantly deploy GPU accelerated virtual machines designed for AI and ML workloads. Configure, launch, and manage your compute VMs. CPUs are included with every instance.
- [IO Cloud Overview](https://io.net/docs/guides/clouds/io-cloud.md): Harness the power of io.net’s decentralized network through IO Cloud, your gateway to high-performance GPUs and CPUs for Web3 initiatives.
- [Train a PyTorch Model on Fashion MNIST: Jupyter Notebook](https://io.net/docs/guides/clouds/jupyter-notebook.md): This document describes how to run a job on your cluster that distributes the training workload across multiple workers using Ray's distributed computing capabilities. This allows for parallelizing the training process and potentially reducing the overall training time. In the instructions below, we…
- [Exposing Applications to the Internet](https://io.net/docs/guides/clouds/kubernetes/exposing-to-the-internet.md): Learn how to expose applications to the internet on io.net Kubernetes clusters using ingress controllers, with guidance on DNS automation and SSL certificate management.
- [ExternalDNS Deployment Guide](https://io.net/docs/guides/clouds/kubernetes/externaldns-guide.md): Learn how to deploy ExternalDNS to automate DNS record management for Kubernetes ingress controllers, including Deployment-based and DaemonSet-based ingress setups.
- [Optimizations](https://io.net/docs/guides/clouds/kubernetes/optimizations.md): Explore Kubernetes optimizations on io.net Cloud, including Kubernetes control plane design, minimal GPU cluster sizing, and master node scheduling best practices.
- [Quick Start: Hello World with HTTPS](https://io.net/docs/guides/clouds/kubernetes/quick-start.md): Deploy a Kubernetes Hello World application with HTTPS using Ingress, ExternalDNS, and cert-manager, and expose it securely to the internet step by step.
- [Monitor & Manage Clusters](https://io.net/docs/guides/clouds/monitor-manage-clusters.md): Manage Clusters offers a comprehensive interface for configuring and monitoring GPU and CPU clusters, enabling users to optimize resource allocation and performance. With advanced management tools, users can efficiently deploy workloads, scale resources, and gain real-time insights into cluster heal…
- [Overview](https://io.net/docs/guides/clouds/run-jobs-on-clusters.md): IO Cloud users can run jobs on their clusters using Visual Studio Code and Jupyter Notebook.
- [Overview](https://io.net/docs/guides/clouds/start-using-io-cloud.md): Discover the simple steps for creating, configuring, deploying, and managing clusters, giving you complete control over your computing power.
- [Coin Restrictions](https://io.net/docs/guides/coin/coin-restrictions.md)
- [Overview](https://io.net/docs/guides/coin/io-coin.md): What is IO Coin ($IO)?
- [IO Coin Allocation](https://io.net/docs/guides/coin/io-coin-allocation.md)
- [IO Tokenomics](https://io.net/docs/guides/coin/io-tokenomics.md): Tokenomics defines the structure and mechanics of a token, covering aspects like distribution, supply-demand dynamics, utility, incentives, governance, and value capture. This document provides transparency into the tokenomics of io.net.
- [Monthly Token Emission Schedule](https://io.net/docs/guides/coin/ionet-monthly-token-emission-schedule.md): io.net proposes transitioning from an hourly to a monthly disinflation schedule while maintaining the original objective of emitting 300 million IO tokens over 20 years. This streamlined approach simplifies calculations and management while adhering to the same disinflationary principles.
- [Confidential Chat](https://io.net/docs/guides/confidential-inference/confidential-chat.md): io.net provides a web-based confidential chat interface where you can interact with AI models securely, with full privacy guarantees and verifiable attestation.
- [Overview](https://io.net/docs/guides/confidential-inference/overview.md): io.net's Confidential Inference enables verifiable AI inference where you can cryptographically prove that your prompts were processed securely on trusted hardware, without storing any of your data.
- [Quick Start API](https://io.net/docs/guides/confidential-inference/quick-start.md): This guide walks you through running your first verifiable AI inference with io.net's Confidential Compute.
- [Verification Guide](https://io.net/docs/guides/confidential-inference/verification-guide.md): This guide explains how to verify that your AI inference ran on genuine trusted hardware and that responses haven't been tampered with.
- [Block Rewards](https://io.net/docs/guides/explorer/block-rewards-page.md)
- [Clusters](https://io.net/docs/guides/explorer/clusters-page.md): The Clusters tab provides a public overview of all deployed clusters within the network, along with real-time metrics on active bookings. This feature helps users assess the current status of computational resources and understand the demand for decentralized compute power.
- [Home](https://io.net/docs/guides/explorer/homepage.md): The Home page serves as a central hub, providing users with a comprehensive overview of our services, real-time insights into resource availability, and key metrics on network performance.
- [Inferences](https://io.net/docs/guides/explorer/inferences-page.md): The Inferences tab provides a public overview of all transactions conducted within the network, along with real-time metrics for these transactions.
- [Overview](https://io.net/docs/guides/explorer/io-explorer.md): Real-time open statistics about our service operations without personal data.
- [Network Map](https://io.net/docs/guides/explorer/network-map-page.md): The Network Map simplifies understanding by displaying the distribution of GPUs/CPUs across various countries along with their quantities. The proximity of Workers impacts both cost and speed, with closer Workers offering faster and more cost-effective task handling.
- [Staking Dashboard](https://io.net/docs/guides/explorer/staking-dashboard.md): The Staking Dashboard is your central hub for real-time statistics and trends about staking activity on the io.net platform. Crafted for clarity and efficiency, it offers a comprehensive overview of essential staking metrics to keep you updated.
- [Overview](https://io.net/docs/guides/explorer/tne-on-chain.md): Introducing TNE On Chain — io.net’s next-generation transaction system built on Solana blockchain.
- [Smart Contract Events](https://io.net/docs/guides/explorer/tne-smart-contracts.md): Learn how smart contracts manage booking, payments, extensions, compute tracking, refunds, and earnings within the IO Network. This guide explains each on-chain event, from creating a cluster to final IO Coin settlement, ensuring full transparency and auditability.
- [Workers](https://io.net/docs/guides/explorer/workers-page.md): The Workers tab provides a public overview of all devices connected to the network, along with real-time metrics on active hires. This allows users to gain valuable insights into the current network status and the demand for computing power.
- [FAQ](https://io.net/docs/guides/faq.md): Straightforward answers to general queries.
- [Overview](https://io.net/docs/guides/getting-started.md): Powered by Solana
- [Glossary](https://io.net/docs/guides/glossary.md)
- [Overview](https://io.net/docs/guides/id/io-id.md): IO ID is your central hub for managing all io.net products and services. Learn how to view your usage, credits, and clusters, compare intelligence plans, and get started with the io.net ecosystem from one unified dashboard.
- [Managing your Wallets](https://io.net/docs/guides/id/managing-your-wallets-in-io-id.md): All suppliers must add at least three to their IO ID account to remain eligible.
- [Usage and Billing](https://io.net/docs/guides/id/usage-and-billing.md): Review your usage, transaction history, earnings and billing details. Get full visibility into your IO Credits, block-reward earnings, withdrawals, and platform spend in one place.”
- [Company Origins](https://io.net/docs/guides/inception.md): The origins of io.net.
- [Agentic Workflow Editor](https://io.net/docs/guides/intelligence/agentic-workflow.md): Build, connect, and execute powerful AI workflows using a visual, no-code interface. From simple task chains to full-blown multi-agent orchestration - without writing a single line of code.
- [API Keys and Secrets](https://io.net/docs/guides/intelligence/api-keys-and-secrets.md): Learn how to create and manage API keys and secrets for use across io.net Intelligence, including models, agents, and integrations.
- [Exploring AI Agents](https://io.net/docs/guides/intelligence/exploring-ai-agents.md): Learn about AI Agents on io.net and how to use, configure, and deploy them to build autonomous AI systems.
- [Exploring AI Models](https://io.net/docs/guides/intelligence/exploring-ai-models.md): The AI Models section provides access to a wide range of pre-trained and custom models. These models combine instructions, additional knowledge, and specialized skills for various tasks.
- [Sub-API Keys](https://io.net/docs/guides/intelligence/sub-api-keys.md): Issue scoped API keys to teams, services, or partners — each with independent model restrictions and credit limits that roll up to your account balance.
- [Training as a Service (TaaS)](https://io.net/docs/guides/intelligence/training-as-a-service.md): Customize and fine-tune models to fit your needs - no need to train from scratch.
- [Chat](https://io.net/docs/guides/intelligence/unified-chat.md): One Chat. Every Tool — Powered by IO Cloud
- [Sign Up or Log In to io.net](https://io.net/docs/guides/loginsignup.md)
- [Card Payment FAQs](https://io.net/docs/guides/payment/card-payments-faqs.md): This page answers common questions about using Stripe (Fiat payments) and Credits when purchasing compute or IO Credits.
- [Deploy Cluster and Pay](https://io.net/docs/guides/payment/deploy-cluster-and-pay.md)
- [Extending your Cluster and Pay](https://io.net/docs/guides/payment/extending-your-cluster-and-pay.md)
- [Overview](https://io.net/docs/guides/payment/io-cloud-payments.md): This document describes how to add crypto wallets and pay using the wallet or with credit cards.
- [IO Credits](https://io.net/docs/guides/payment/io-credits.md): Simplify your io.net Cloud payments with IO Credits, a prepaid USD-equivalent credit system you can use across compute products.
- [Overview](https://io.net/docs/guides/payment/io-intelligence-payments.md): Overview of io.net’s AI access plans and model rates.
- [Overview](https://io.net/docs/guides/staking/3rd-party-staking.md): In the world of decentralized networks, staking is a crucial way to secure blockchain systems and reward participants. Collaborative Staking (Co-Staking) takes this idea further by allowing third parties to participate in staking on devices they don't own, earning a share of the block rewards. This…
- [Co-staking](https://io.net/docs/guides/staking/co-staking.md): Co-staking allows third parties to stake on devices and share block rewards. As a co-staker, you contribute to an existing staking offer and receive a share of the block rewards based on the agreed-upon percentage.
- [Create a Co-staking Offer](https://io.net/docs/guides/staking/create-a-co-staking-offer.md): Co-Staking operates as a smart contract on the blockchain, allowing device owners to invite co-stakers to contribute to their stake in exchange for a share of block rewards.
- [Overview](https://io.net/docs/guides/staking/device-owner-staking.md)
- [Device Reliability Score](https://io.net/docs/guides/staking/device-reliability-score.md): The Device Reliability Score is a key metric that helps both worker providers and co-stakers assess the reliability and trustworthiness of a device in the staking network. It reflects how consistently the device performs and whether it meets io.net’s technical and uptime requirements.
- [Unstake and Withdraw $IO](https://io.net/docs/guides/staking/how-to-unstake.md): This document explains how to unstake & withdraw $IO.
- [Overview](https://io.net/docs/guides/staking/io-staking.md): At IO.net, we're committed to building a robust, secure, and decentralized platform for GPU and CPU supply and demand. Our staking program is designed to align incentives, ensure network integrity, and reward active participants in our ecosystem.
- [Protecting your Stake](https://io.net/docs/guides/staking/protecting-your-stake.md): How to Ensure Strengthened Security for Your Stake
- [Solo Staked Devices](https://io.net/docs/guides/staking/solo-staked-devices.md): This section outlines how to individually stake IO and manage your stake effectively. For general information, refer to .
- [How to Stake](https://io.net/docs/guides/staking/staking.md): This document describes how to stake with $IO. Staking is a crucial component of our network security and efficiency. For general information about staking, see .
- [Unstake Your Co-stake & Withdrawing](https://io.net/docs/guides/staking/unstake-your-co-stake.md)
- [Deleting, Unstaking & Withdrawing](https://io.net/docs/guides/staking/unstaking-deleting-withdrawing.md): Co-Staking operates as a smart contract on the blockchain, allowing device owners to invite co-stakers to contribute to their stake in exchange for a share of block rewards.
- [View Co-Staking Device](https://io.net/docs/guides/staking/view-co-staking-device.md)
- [Additional Guides](https://io.net/docs/guides/workers/additional-guides.md)
- [Aptos Wallet](https://io.net/docs/guides/workers/aptos-wallet.md): This document discusses Aptos and provides instructions on how to create a Aptos Wallet.
- [Bare Metal On-Demand Supplier Process](https://io.net/docs/guides/workers/bare-metal-on-demand-supplier-process.md): As a supplier of bare metal on-demand devices, you provide critical hardware that powers high-performance computing tasks for consumers. This guide outlines the steps to register your devices, comply with network standards, and securely reset hardware after bookings, ensuring seamless participation…
- [Connectivity Displays Incorrectly](https://io.net/docs/guides/workers/connectivity-tier-not-displaying-correctly.md): To troubleshoot connectivity tier issues, users can test network speeds via a sample Docker container. Here's how:
- [CUDA Toolkit](https://io.net/docs/guides/workers/cuda-toolkit-optional.md): A step by step process for Downloading the CUDA Toolkit.
- [Overview](https://io.net/docs/guides/workers/device-onboarding.md): This document provides instructions about how to create an account, device onboarding basics, block rewards, staking, and statuses to assist in you in the onboarding process.
- [Device Utilization Threshold](https://io.net/docs/guides/workers/device-utilization-threshold.md): Devices available for hire on io.net should remain idle and not perform any computationally intensive tasks. We are updating device requirements to ensure that your processor utilization rates do not exceed the thresholds specified in the tables below.
- [Docker Not Installed or Running](https://io.net/docs/guides/workers/docker-not-installed-or-running.md): This issue can occur if Docker is not installed or if the user is not added to the Docker group. Here's how to troubleshoot:
- [Earnings & Rewards](https://io.net/docs/guides/workers/earnings-rewards.md): The Earnings & Rewards tab provides transparency and granular insights into your earnings and the jobs your devices have served.
- [MacOS: Install Docker](https://io.net/docs/guides/workers/install-docker-on-macos.md): A step-by-step guide for installing Docker on MacOS-based machines.
- [Windows: Install Docker](https://io.net/docs/guides/workers/install-docker-on-windows.md): A step-by-step guide for installing Docker on Windows-based machines
- [Install Nvidia Drivers](https://io.net/docs/guides/workers/install-nvidia-drivers-on-windows.md): A step-by-step guide for installing Nvidia Drivers on Windows-based machines.
- [HiveOS: Install Worker](https://io.net/docs/guides/workers/install-on-hiveos.md): A step-by-step process for running io.net on HiveOS:
- [Overview](https://io.net/docs/guides/workers/install-on-macos.md): A step-by-step guide for setting up the environment for io.net on Mac OS-based machines
- [Overview](https://io.net/docs/guides/workers/install-on-ubuntu.md): A step-by-step guide for setting up the environment for io.net on Ubuntu-based machines.
- [Overview](https://io.net/docs/guides/workers/install-on-windows.md): A step-by-step guide for setting up the environment for io.net on Windows-based machines.
- [Intro](https://io.net/docs/guides/workers/intro.md)
- [Overview](https://io.net/docs/guides/workers/io-worker.md)
- [Manage, Monitor, & FAQs](https://io.net/docs/guides/workers/manage-and-monitor.md)
- [Optimize PCIe Lane Configuration](https://io.net/docs/guides/workers/optimize-pcie-lane-configuration.md): When onboarding new devices into the IO.NET network, it’s essential to review the hardware installed and ensure that it is fully capable of performing as expected. We recommend verifying that your hardware supports the required PCIe (Peripheral Component Interconnect Express) lanes. PCIe lanes are t…
- [Proof of Work](https://io.net/docs/guides/workers/proof-of-work.md): io.net is committed to providing a reliable and trustworthy platform for distributed CPU/GPU resources. A key challenge in a decentralized network is to ensure that the computational resources offered by suppliers are genuine and perform as intended. We actively verify the authenticity and reliabili…
- [Quick Start Guide](https://io.net/docs/guides/workers/quick-start-guide.md): Get started with IO Worker by following simple steps to create an account, connect your device, and begin earning by sharing your compute power.
- [Overview](https://io.net/docs/guides/workers/rewards-wallets.md): This document explains the financial aspects of supplying compute power to the IO network.
- [Solana Wallet](https://io.net/docs/guides/workers/solana.md): This document discusses Solana and provides instructions on how to create a Solana Wallet.
- [Stop & Restart the Platform](https://io.net/docs/guides/workers/stop-restart-the-platform.md)
- [Supported Devices](https://io.net/docs/guides/workers/supported-devices.md): A list of supported device by device type
- [Overview](https://io.net/docs/guides/workers/troubleshoot-docker-for-linux.md): See the following articles to troubleshoot Linus for Docker:
- [MacOs: Troubleshoot Docker](https://io.net/docs/guides/workers/troubleshoot-docker-for-macs.md)
- [Windows: Troubleshoot Docker](https://io.net/docs/guides/workers/troubleshoot-docker-for-windows.md)
- [MacOS: Troubleshoot Worker](https://io.net/docs/guides/workers/troubleshoot-macos-worker.md): Here we've compiled essential use cases for working with Workers.
- [Windows: Troubleshoot Worker](https://io.net/docs/guides/workers/troubleshoot-windows-worker.md): Here we've compiled essential use cases for working with Workers.
- [General Worker Troubleshooting](https://io.net/docs/guides/workers/troubleshoot-worker-general.md): Here we've compiled essential use cases for working with Workers.
- [Ubuntu: Install Docker](https://io.net/docs/guides/workers/ubuntu-install-docker.md): A step-by-step guide for installing Docker on Linux-based machines
- [Waiting for IO Containers to Start](https://io.net/docs/guides/workers/waiting-for-io-containers-to-start.md): On Linux the above issue can be due to several reasons:
- [Worker Disconnects When Containers Are Running](https://io.net/docs/guides/workers/worker-disconnects-when-containers-are-running.md): If your Worker disconnects even when the containers are up, try the following checks:
- [Agents List](https://io.net/docs/reference/ai-agents/get-agents-list.md): Get a list of all the available agents.
- [Getting Started with AI Agents API](https://io.net/docs/reference/ai-agents/getting-started-with-api-agents.md)
- [Delete a Secret](https://io.net/docs/reference/ai-agents/secret-management-delete.md): Deletes an existing secret and its associated configuration.
- [Get Secret Details](https://io.net/docs/reference/ai-agents/secret-management-get.md): Retrieves details for a specific secret.
- [Update Secret Details](https://io.net/docs/reference/ai-agents/secret-management-patch.md): Updates an existing secret or its associated metadata.Updates an existing secret or its associated metadata.
- [Create a Secret](https://io.net/docs/reference/ai-agents/secret-management-post.md): Creates or registers a new secret for use with specific tools or workflows.
- [Workflows Run](https://io.net/docs/reference/ai-agents/workflows-run.md): Enables users to execute AI-driven workflows by submitting text inputs to one or more AI agents.
- [Workflows Schema](https://io.net/docs/reference/ai-agents/workflows-schema.md): Get a list of default workflows.
- [Create Chat Completion](https://io.net/docs/reference/ai-models/create-chat-completion.md): Creates a model response for a given chat conversation.
- [Create Embeddings](https://io.net/docs/reference/ai-models/create-embedding.md): Computes an embedding vector that encodes the input text.
- [Embedding Models List](https://io.net/docs/reference/ai-models/get-embedding-models-list.md): Retrieves a list of available models for the Embeddings API.
- [Models List](https://io.net/docs/reference/ai-models/get-models-list.md): Retrieves a list of available models for the Chat Completions API.
- [Getting Started with AI Models API](https://io.net/docs/reference/ai-models/get-started-with-io-intelligence-api.md)
- [Uploading Images](https://io.net/docs/reference/ai-models/uploading-images.md): The io.net Intelligence API supports image inputs for vision-enabled AI models. This allows users to send images as part of their API requests, enabling advanced multimodal AI capabilities.
- [Check available replicas per location](https://io.net/docs/reference/caas/available-replicas.md): Returns the number of deployable replicas in each location based on selected hardware type and GPU count per container, useful for matching supply to workload needs.
- [Check maximum GPUs per container](https://io.net/docs/reference/caas/check-maximum-gpus-per-container.md): Returns the maximum number of GPUs available per hardware type across all locations, helping to determine deployment limits by hardware.
- [Container Job Details](https://io.net/docs/reference/caas/container-job-details.md): Inspect job-level details of a specific container within a deployment.
- [Container Logs](https://io.net/docs/reference/caas/container-logs.md): Access real-time or historical logs for a specific container in a deployment.
- [Deploy a Container](https://io.net/docs/reference/caas/deploy-a-container.md): This endpoint is used to deploy a CaaS cluster on IO.NET infrastructure. The container must expose an HTTP server on a single port, and it must run within a single node.
- [Destroy Container](https://io.net/docs/reference/caas/destroy-container.md): Shut down a deployment and release associated resources.
- [Extend Deployment Duration](https://io.net/docs/reference/caas/extend-deployment-duration.md): Increase the runtime of an existing deployment without redeploying.
- [Get All Deployments](https://io.net/docs/reference/caas/get-all-deployments.md): View a list of all your active and past deployments.
- [Get Deployment Details](https://io.net/docs/reference/caas/get-deployment-details.md): Retrieve detailed information about a specific deployment.
- [Getting Started with CaaS API](https://io.net/docs/reference/caas/get-started-with-caas-api.md): The CaaS API lets you programmatically deploy and manage high-performance containerized workloads on io.net’s decentralized GPU network.
- [List Deployment Containers](https://io.net/docs/reference/caas/list-deployment-containers.md): Get information about all containers running within a specific deployment.
- [Deployment Price Check](https://io.net/docs/reference/caas/price-estimation.md): Calculates the estimated deployment cost based on selected location, hardware, GPU count, duration, and number of replicas. Returns a detailed price breakdown.
- [Update Deployment Configuration](https://io.net/docs/reference/caas/update-deployment-configuration.md): Modify runtime container settings such as environment variables or entrypoints.
- [Block Rewards Summary](https://io.net/docs/reference/io-explorer/block-rewards-summary.md): The Block Rewards Summary endpoint returns insight on the block rewards associated with a specific device. This includes, but is not limited to, successful rewards, failed and missed rewards, and an earnings summary - given a specific date range.
- [Device Details for a Block](https://io.net/docs/reference/io-explorer/device-details-for-a-block.md): The Deice Details for a Block endpoint returns granular information about a device in the context of a specific block reward. It offers details about Block Reward challenges, the outcome, and details about the device.
- [Device Summary](https://io.net/docs/reference/io-explorer/device-summary.md): The Device Summary endpoint provides detailed information on a specific device. This allows you to view the device's status, aspects of connectivity, compute hours served, earnings and more.
- [Device Details](https://io.net/docs/reference/io-explorer/get-device-details.md): The Device Details endpoint provides comprehensive insights into a specific device, including its status, connectivity, job activity, rewards earned, hire rate, and other key performance metrics.
- [Getting Started with IO Explorer API](https://io.net/docs/reference/io-explorer/getting-started-with-your-api.md): Use IO Explorer APIs to gain insight into the different elements of our network.
- [Device Object Reference](https://io.net/docs/reference/io-explorer/objects.md): Defines the structure, attributes, and metrics of a Device within the IO Network. Includes details on hardware specs, network performance, compliance, and job history used for monitoring and rewards calculation.
- [PoW Summary](https://io.net/docs/reference/io-explorer/pow-summary.md): This PoW Summary endpoint returns information about the Proof of Work challenges for a device.
- [Overview](https://io.net/docs/reference/rag/chunks.md): The R2R Chunks API defines how processed document segments, called chunks, are created, managed, and searched. It provides endpoints for semantic retrieval, knowledge graph extraction, and metadata-driven filtering to power advanced AI and RAG workflows.
- [Delete Chunk](https://io.net/docs/reference/rag/chunks/delete-chunk.md): Delete a specific chunk by ID.
- [Retrieve Chunk](https://io.net/docs/reference/rag/chunks/get-chunk-by-id.md): Get a specific chunk by its ID.
- [List Chunks](https://io.net/docs/reference/rag/chunks/list-chunks.md): List chunks with pagination support.
- [Search Chunks](https://io.net/docs/reference/rag/chunks/search-chunks.md): Perform a semantic search query over all stored chunks.
- [Update Chunk](https://io.net/docs/reference/rag/chunks/update-chunk.md): Update an existing chunk’s content and/or metadata.
- [Overview](https://io.net/docs/reference/rag/collections.md): The R2R Collections API enables structured organization, sharing, and access control for documents and their related chunks. It provides endpoints to create, manage, and collaborate on collections, supporting team workflows, permission management, and intelligent content organization.
- [Add document to collection](https://io.net/docs/reference/rag/collections/add-document-to-collection.md): Add a document to a collection.
- [Add user to collection](https://io.net/docs/reference/rag/collections/add-user-to-collection.md): This endpoint grants a user access to a specific collection.
- [Create a new collection](https://io.net/docs/reference/rag/collections/create-a-new-collection.md): Create a new collection and automatically add the creating user to it.
- [Delete Collection](https://io.net/docs/reference/rag/collections/delete-collection.md): Delete an existing collection.
- [Get collection details](https://io.net/docs/reference/rag/collections/get-collection-by-id.md): Get details of a specific collection.
- [Get collection by name](https://io.net/docs/reference/rag/collections/get-collection-by-name.md): Retrieve a collection by its (owner_id, name) combination.
- [List collections](https://io.net/docs/reference/rag/collections/list-collections.md): Returns a paginated list of collections the authenticated user has access to.
- [List documents in collection](https://io.net/docs/reference/rag/collections/list-documents-in-collection.md): Get all documents in a collection with pagination and sorting options.
- [List users in collection](https://io.net/docs/reference/rag/collections/list-users-in-a-collection.md): Get all users in a collection with pagination and sorting options.
- [Remove document from collection](https://io.net/docs/reference/rag/collections/remove-document-from-collection.md): This endpoint removes the association between a document and a collection.
- [Remove user from collection](https://io.net/docs/reference/rag/collections/remove-user-from-collection.md): This endpoint revokes a user's access to a specific collection.
- [Extract entities and relationships](https://io.net/docs/reference/rag/collections/trigger-extraction-for-a-collection.md): Extracts entities and relationships from a document.
- [Update Collection](https://io.net/docs/reference/rag/collections/update-collection.md): Update an existing collection's configuration.
- [Overview](https://io.net/docs/reference/rag/conversations.md): The R2R Conversations API enables threaded, context-aware exchanges between users or AI agents. It offers endpoints to create, manage, and update conversations and messages, supporting branching dialogue, metadata attachment, and message history tracking.
- [Add message to conversation](https://io.net/docs/reference/rag/conversations/add-a-message-to-a-conversation.md): Add a new message to a conversation. This endpoint adds a new message to an existing conversation.
- [Create a new conversation](https://io.net/docs/reference/rag/conversations/create-a-new-conversation.md): Create a new conversation. This endpoint initializes a new conversation for the authenticated user.
- [Delete a conversation](https://io.net/docs/reference/rag/conversations/delete-a-conversation.md): Delete an existing conversation. This endpoint deletes a conversation identified by its UUID.
- [Get conversation details](https://io.net/docs/reference/rag/conversations/get-conversation-details.md): Get details of a specific conversation. This endpoint retrieves detailed information about a single conversation identified by its UUID.
- [List conversations](https://io.net/docs/reference/rag/conversations/list-conversations.md): List conversations with pagination and sorting options. This endpoint returns a paginated list of conversations for the authenticated user.
- [Update message in conversation](https://io.net/docs/reference/rag/conversations/update-a-message.md): Update an existing message in a conversation. This endpoint updates the content of an existing message in a conversation.
- [Update conversation](https://io.net/docs/reference/rag/conversations/update-conversation.md): Update an existing conversation. This endpoint updates the name of an existing conversation identified by its UUID.
- [Overview](https://io.net/docs/reference/rag/documents.md): The R2R Documents API handles ingestion, management, and enrichment of digital content. It enables transforming files, text, and media into structured, searchable knowledge objects for RAG, semantic retrieval, and AI-driven workflows.
- [Deduplicate entities](https://io.net/docs/reference/rag/documents/deduplicate-document.md): Deduplicates entities from a document.
- [Delete a document](https://io.net/docs/reference/rag/documents/delete-document-by-id.md): Delete a specific document. All chunks corresponding to the document are deleted, and all other references to the document are removed.
- [Delete documents by filter](https://io.net/docs/reference/rag/documents/delete-documents-by-filter.md): Delete documents based on provided filters.
- [Export multiple documents as zip](https://io.net/docs/reference/rag/documents/download-documents-as-zip.md): Export multiple documents as a zip file. Documents can be filtered by IDs and/or date range.
- [Download document content](https://io.net/docs/reference/rag/documents/download-original-file.md): Downloads the original file content of a document.
- [Extract entities and relationships](https://io.net/docs/reference/rag/documents/extract-entities.md): Extracts entities and relationships from a document.
- [Retrieve a document](https://io.net/docs/reference/rag/documents/get-document-by-id.md): Retrieves detailed information about a specific document by its ID.
- [List document chunks](https://io.net/docs/reference/rag/documents/get-document-chunks.md): Retrieves the text chunks that were generated from a document during ingestion.
- [Get Extracted Entities](https://io.net/docs/reference/rag/documents/get-extracted-entities.md): Fetch list of named entities extracted from the document.
- [Get Relationships](https://io.net/docs/reference/rag/documents/get-relationships.md): View semantic or knowledge graph relationships from extracted content.
- [List documents](https://io.net/docs/reference/rag/documents/list-all-documents.md): Returns a paginated list of documents the authenticated user has access to.
- [Replace document metadata](https://io.net/docs/reference/rag/documents/replace-document-metadata.md): Modify document metadata, given the document ID
- [Search document summaries](https://io.net/docs/reference/rag/documents/search-documents.md): Perform a search query on the automatically generated document summaries in the system.
- [Append metadata to a document](https://io.net/docs/reference/rag/documents/update-document-metadata-partial.md): Appends metadata to a document. This endpoint allows adding new metadata fields or updating existing ones.
- [Create a new document](https://io.net/docs/reference/rag/documents/upload-and-ingest-a-document.md): Creates a new Document object from an input file, text content, or chunks.
- [Overview](https://io.net/docs/reference/rag/getting-started-with-the-rag-api.md): The R2R APIs enables developers to build powerful AI systems that integrates the strengths of semantic search, knowledge graphs, and prompt-based generation for advanced question answering and intelligent assistants.
- [Overview](https://io.net/docs/reference/rag/graphs.md): The R2R Graphs API manages knowledge graphs tied to specific collections. It supports entity and relationship extraction, community detection, and synchronization with document data—enabling structured, queryable knowledge organization for advanced AI reasoning.
- [Overview](https://io.net/docs/reference/rag/graphs/communities.md)
- [Create a new community](https://io.net/docs/reference/rag/graphs/communities/build-graph-communities.md): Creates communities in the graph by analyzing entity relationships and similarities.
- [Community: Delete](https://io.net/docs/reference/rag/graphs/communities/delete-a-community.md): Permanently removes a specific community (cluster) from the graph.
- [Retrieve a community](https://io.net/docs/reference/rag/graphs/communities/get-community-details.md): Retrieves a specific community by its ID.
- [List communities](https://io.net/docs/reference/rag/graphs/communities/list-communities.md): Lists all communities in the graph with pagination support.
- [Update community](https://io.net/docs/reference/rag/graphs/communities/update-a-community.md): Updates an existing community in the graph.
- [Entities](https://io.net/docs/reference/rag/graphs/entities.md)
- [Create Entity](https://io.net/docs/reference/rag/graphs/entities/add-new-entities.md): Creates a new entity in the graph.
- [Get Entity](https://io.net/docs/reference/rag/graphs/entities/get-single-entity-details.md): Retrieves a specific entity by its ID.
- [Get Entities](https://io.net/docs/reference/rag/graphs/entities/list-graph-entities.md): Lists all entities in the graph with pagination support.
- [Retrieve graph details](https://io.net/docs/reference/rag/graphs/get-graph-data-for-a-collection.md): Retrieves detailed information about a specific graph by ID.
- [Get graph overview](https://io.net/docs/reference/rag/graphs/get-graph-overview.md): Returns a paginated list of graphs the authenticated user has access to.
- [Pull latest entities to the graph](https://io.net/docs/reference/rag/graphs/pull-and-rebuild-graph.md): Adds documents to a graph by copying their entities and relationships.
- [Overview](https://io.net/docs/reference/rag/graphs/relationships.md)
- [Get Relationships](https://io.net/docs/reference/rag/graphs/relationships/get-graph-relationships.md): Lists all relationships in the graph with pagination support.
- [Get Relationship](https://io.net/docs/reference/rag/graphs/relationships/get-relationship-details.md): Retrieves a specific relationship by its ID.
- [Overview](https://io.net/docs/reference/rag/indices.md): The R2R Indices API manages vector index structures that enable high-speed similarity search across chunks. It supports multiple index methods, configurable similarity measures, and concurrent building for optimized RAG retrieval performance.
- [Delete Vector Index](https://io.net/docs/reference/rag/indices/delete-an-index.md): Delete an existing vector similarity search index.
- [Get Vector Index Details](https://io.net/docs/reference/rag/indices/get-specific-index-details.md): Get detailed information about a specific vector index.
- [List Vector Indices](https://io.net/docs/reference/rag/indices/list-all-indices.md): List existing vector similarity search indices with pagination support.
- [Overview](https://io.net/docs/reference/rag/prompts.md): The R2R Prompts API manages reusable, type-safe prompt templates that structure interactions with language models. It supports dynamic generation, version control, and centralized governance to ensure consistent, high-quality AI behavior.
- [List all prompts](https://io.net/docs/reference/rag/prompts/list-all-prompts.md): List all available prompts. This endpoint retrieves a list of all prompts in the system. Only superusers can access this endpoint.
- [Overview](https://io.net/docs/reference/rag/retrieval.md): The R2R Retrieval API provides vector search, knowledge graph retrieval, and RAG-based generation capabilities. It powers semantic search, conversational agents, and flexible AI generation across documents, enabling intelligent data interaction and discovery.
- [RAG-Powered Conversational Agent](https://io.net/docs/reference/rag/retrieval/agent-based-query-resolution.md): The R2R Agent endpoint provides a conversational RAG interface for retrieval, reasoning, and research. It supports multi-turn context, tool integration, streaming output, and both RAG and Research modes for dynamic AI-driven analysis.
- [Embeddings](https://io.net/docs/reference/rag/retrieval/generate-embedding.md): The R2R Embedding endpoint generates vector embeddings from text using a specified model. It supports single or batch input, returning semantic vectors for use in search, clustering, and RAG applications.
- [Prompt-Based Completion](https://io.net/docs/reference/rag/retrieval/prompt-based-completion.md): The R2R Completion endpoint generates text completions directly from a language model. It accepts structured messages, supports configurable generation parameters, and enables both streaming and non-streaming responses for flexible AI interaction.
- [RAG Query](https://io.net/docs/reference/rag/retrieval/retrieve-and-generate-rag.md): The R2R RAG Query endpoint performs Retrieval-Augmented Generation by combining semantic search, graph-enhanced context, and LLM generation. It supports streaming, source citation, and multiple model providers for contextually accurate AI responses.
- [Search R2R](https://io.net/docs/reference/rag/retrieval/semantic-search.md): The R2R Search Endpoint provides semantic, hybrid, and graph-enhanced retrieval across documents and chunks. It supports advanced filters, hybrid ranking, and knowledge graph traversal to deliver contextually relevant and explainable results.
- [Streaming Retrieval API](https://io.net/docs/reference/rag/retrieval/streaming-retrieval-api.md): The R2R Streaming Retrieval API provides real-time streaming for RAG and agent interactions, emitting structured events such as search results, reasoning steps, and final responses. It enables interactive, low-latency experiences for AI-driven applications.
- [Overview](https://io.net/docs/reference/rag/system.md): The R2R System API provides health check and monitoring capabilities for verifying platform availability and responsiveness. It enables diagnostics and readiness validation to ensure stable operation across internal and external services.
- [Check system health](https://io.net/docs/reference/rag/system/health-check.md): Checks the availability and uptime status of the R2R API.
- [Overview](https://io.net/docs/reference/rag/users.md): The R2R Users API manages authenticated entities, enabling secure access, permissions, and collaboration. It provides endpoints for user details, collection membership, limits, and administrative control to support reliable identity management.
- [Add user to collection](https://io.net/docs/reference/rag/users/add-collection-to-user.md): Grants a user access to an existing collection.
- [Remove user from collection](https://io.net/docs/reference/rag/users/delete-user-from-collection.md): Remove a user from a collection. Requires either superuser status or access to the collection.
- [Get authenticated user details](https://io.net/docs/reference/rag/users/get-current-user.md): Get detailed information about the currently authenticated user.
- [Get user details](https://io.net/docs/reference/rag/users/get-user-by-id.md): Get detailed information about a specific user. Users can only access their own information unless they are superusers.
- [Fetch User Limits](https://io.net/docs/reference/rag/users/get-user-limits.md): Return the system default limits, user-level overrides, and final “effective” limit settings for the specified user.
- [List user's collections](https://io.net/docs/reference/rag/users/list-users-collections.md): Get all collections associated with a specific user. Users can only access their own collections unless they are superusers.
- [Create Sub-API Key](https://io.net/docs/reference/sub-keys/create-sub-key.md): Creates a new sub-API key scoped under an admin key, with optional model restrictions and per-key credit limits.
- [Get All Sub-Keys Usage](https://io.net/docs/reference/sub-keys/get-all-keys-usage.md): Returns aggregated token usage and credit cost for every sub-key owned by the admin, broken down by model for today and all time.
- [Get Sub-Key Usage](https://io.net/docs/reference/sub-keys/get-key-usage.md): Returns credit status for a specific sub-key: credits used in the current billing period, the configured limit, and remaining allowance.
- [Get Own Usage (Sub-Key Self-Service)](https://io.net/docs/reference/sub-keys/get-own-usage.md): Allows a sub-key to check its own credit status without exposing the admin key to the sub-key holder.
- [List Sub-API Keys](https://io.net/docs/reference/sub-keys/list-sub-keys.md): Returns all active sub-API keys owned by the authenticated admin key, including current-period credit usage for each key.
- [Revoke Sub-API Key](https://io.net/docs/reference/sub-keys/revoke-sub-key.md): Immediately revokes a sub-API key. All subsequent requests using the revoked key receive 401 Unauthorized.
- [Update Sub-API Key](https://io.net/docs/reference/sub-keys/update-sub-key.md): Updates one or more attributes of an existing sub-API key. Omitted fields are left unchanged.
- [Deploy a VM](https://io.net/docs/reference/vmaas/deploy-vms.md)
- [Destroy Deployment](https://io.net/docs/reference/vmaas/destroy-deployment.md): Terminate and remove an existing deployment. All VMs and resources allocated to the deployment will be released.
- [Cluster Deployment using APIs](https://io.net/docs/reference/vmaas/example-deploying-using-APIs.md): Step-by-step guide for developers to deploy, price, and manage GPU clusters programmatically using io.net Cloud VMaaS APIs.
- [Extend Cluster](https://io.net/docs/reference/vmaas/extend-cluster.md): Extend the lifetime or capacity of an existing deployment by adding more resources or increasing its duration.
- [Get All Deployments](https://io.net/docs/reference/vmaas/get-all-deployments.md): Retrieve a list of all VMaaS deployments associated with the enterprise account, including their status, configuration, and metadata.
- [Get Deployment Details](https://io.net/docs/reference/vmaas/get-deployment-details.md): Fetch detailed information about a specific deployment by its ID, including cluster specifications, runtime status, and associated resources.
- [Get Deployment Price](https://io.net/docs/reference/vmaas/get-deployment-price.md): Calculate or retrieve the pricing details for a deployment based on selected resources (CPUs, GPUs, memory, and duration).
- [Get Deployment VMs](https://io.net/docs/reference/vmaas/get-deployment-vms.md): List all virtual machines running within a given deployment, along with their current state and hardware details.
- [Get Hardware List](https://io.net/docs/reference/vmaas/get-hardware-list.md): Retrieve a list of currently available GPUs and configurations.
- [Getting Started with VMaaS API](https://io.net/docs/reference/vmaas/get-started-with-vmaas-api.md)
- [Get a VM's Jobs History](https://io.net/docs/reference/vmaas/get-vms-jobs-history.md): Retrieve the job execution history for a specific VM or container within a deployment. Includes logs and status of completed or active jobs.

## OpenAPI Specs

- [get-max-gpu-count-per-vm](https://io.net/docs/openapi/vmaas/get-max-gpu-count-per-vm.json)
- [get-available-vms](https://io.net/docs/openapi/vmaas/get-available-vms.json)
- [update-sub-key](https://io.net/docs/openapi/sub-keys/update-sub-key.json)
- [revoke-sub-key](https://io.net/docs/openapi/sub-keys/revoke-sub-key.json)
- [list-sub-keys](https://io.net/docs/openapi/sub-keys/list-sub-keys.json)
- [get-own-usage](https://io.net/docs/openapi/sub-keys/get-own-usage.json)
- [get-key-usage](https://io.net/docs/openapi/sub-keys/get-key-usage.json)
- [get-all-keys-usage](https://io.net/docs/openapi/sub-keys/get-all-keys-usage.json)
- [create-sub-key](https://io.net/docs/openapi/sub-keys/create-sub-key.json)
- [replace-document-metadata](https://io.net/docs/openapi/rag-documents/replace-document-metadata.json)
- [get-vms-jobs-history](https://io.net/docs/openapi/vmaas/get-vms-jobs-history.json)
- [get-deployment-vms](https://io.net/docs/openapi/vmaas/get-deployment-vms.json)
- [get-deployment-details](https://io.net/docs/openapi/vmaas/get-deployment-details.json)
- [get-all-deployments](https://io.net/docs/openapi/vmaas/get-all-deployments.json)
- [extend-cluster](https://io.net/docs/openapi/vmaas/extend-cluster.json)
- [destroy-deployment](https://io.net/docs/openapi/vmaas/destroy-deployment.json)
- [deploy-vms](https://io.net/docs/openapi/vmaas/deploy-vms.json)
- [get-deployment-price](https://io.net/docs/openapi/vmaas/get-deployment-price.json)
- [get-hardware-list](https://io.net/docs/openapi/vmaas/get-hardware-list.json)
- [create-chat-completion](https://io.net/docs/openapi/ai-models/create-chat-completion.json)
- [secret-management-post](https://io.net/docs/openapi/ai-agents/secret-management-post.json)
- [secret-management-delete](https://io.net/docs/openapi/ai-agents/secret-management-delete.json)
- [secret-management-patch](https://io.net/docs/openapi/ai-agents/secret-management-patch.json)
- [secret-management-get](https://io.net/docs/openapi/ai-agents/secret-management-get.json)
- [generate-embedding](https://io.net/docs/openapi/rag-retrieval/generate-embedding.json)
- [get-embedding-models-list](https://io.net/docs/openapi/ai-models/get-embedding-models-list.json)
- [create-embedding](https://io.net/docs/openapi/ai-models/create-embedding.json)
- [device-details-for-a-block](https://io.net/docs/openapi/io-explorer/device-details-for-a-block.json)
- [block-rewards-summary](https://io.net/docs/openapi/io-explorer/block-rewards-summary.json)
- [pow-summary](https://io.net/docs/openapi/io-explorer/pow-summary.json)
- [device-summary](https://io.net/docs/openapi/io-explorer/device-summary.json)
- [get-device-details](https://io.net/docs/openapi/io-explorer/get-device-details.json)
- [get-document-by-id](https://io.net/docs/openapi/rag-documents/get-document-by-id.json)
- [update-deployment-configuration](https://io.net/docs/openapi/caas/update-deployment-configuration.json)
- [price-estimation](https://io.net/docs/openapi/caas/price-estimation.json)
- [list-deployment-containers](https://io.net/docs/openapi/caas/list-deployment-containers.json)
- [extend-deployment-duration](https://io.net/docs/openapi/caas/extend-deployment-duration.json)
- [destroy-container](https://io.net/docs/openapi/caas/destroy-container.json)
- [deploy-a-container](https://io.net/docs/openapi/caas/deploy-a-container.json)
- [container-logs](https://io.net/docs/openapi/caas/container-logs.json)
- [container-job-details](https://io.net/docs/openapi/caas/container-job-details.json)
- [check-maximum-gpus-per-container](https://io.net/docs/openapi/caas/check-maximum-gpus-per-container.json)
- [available-replicas](https://io.net/docs/openapi/caas/available-replicas.json)
- [download-documents-as-zip](https://io.net/docs/openapi/rag-documents/download-documents-as-zip.json)
- [get-models-list](https://io.net/docs/openapi/ai-models/get-models-list.json)
- [get-agents-list](https://io.net/docs/openapi/ai-agents/get-agents-list.json)
- [prompt-based-completion](https://io.net/docs/openapi/rag-retrieval/prompt-based-completion.json)
- [workflows-schema](https://io.net/docs/openapi/ai-agents/workflows-schema.json)
- [workflows-run](https://io.net/docs/openapi/ai-agents/workflows-run.json)
- [update-chunk](https://io.net/docs/openapi/rag-chunks/update-chunk.json)
- [get-chunk-by-id](https://io.net/docs/openapi/rag-chunks/get-chunk-by-id.json)
- [delete-chunk](https://io.net/docs/openapi/rag-chunks/delete-chunk.json)
- [update-conversation](https://io.net/docs/openapi/rag-conversations/update-conversation.json)
- [update-a-message](https://io.net/docs/openapi/rag-conversations/update-a-message.json)
- [get-conversation-details](https://io.net/docs/openapi/rag-conversations/get-conversation-details.json)
- [delete-a-conversation](https://io.net/docs/openapi/rag-conversations/delete-a-conversation.json)
- [add-a-message-to-a-conversation](https://io.net/docs/openapi/rag-conversations/add-a-message-to-a-conversation.json)
- [update-collection](https://io.net/docs/openapi/rag-collections/update-collection.json)
- [trigger-extraction-for-a-collection](https://io.net/docs/openapi/rag-collections/trigger-extraction-for-a-collection.json)
- [remove-user-from-collection](https://io.net/docs/openapi/rag-collections/remove-user-from-collection.json)
- [remove-document-from-collection](https://io.net/docs/openapi/rag-collections/remove-document-from-collection.json)
- [list-users-in-a-collection](https://io.net/docs/openapi/rag-collections/list-users-in-a-collection.json)
- [list-documents-in-collection](https://io.net/docs/openapi/rag-collections/list-documents-in-collection.json)
- [get-collection-by-id](https://io.net/docs/openapi/rag-collections/get-collection-by-id.json)
- [delete-collection](https://io.net/docs/openapi/rag-collections/delete-collection.json)
- [add-user-to-collection](https://io.net/docs/openapi/rag-collections/add-user-to-collection.json)
- [add-document-to-collection](https://io.net/docs/openapi/rag-collections/add-document-to-collection.json)
- [list-users-collections](https://io.net/docs/openapi/rag-users/list-users-collections.json)
- [get-user-limits](https://io.net/docs/openapi/rag-users/get-user-limits.json)
- [get-user-by-id](https://io.net/docs/openapi/rag-users/get-user-by-id.json)
- [delete-user-from-collection](https://io.net/docs/openapi/rag-users/delete-user-from-collection.json)
- [update-a-community](https://io.net/docs/openapi/rag-graphs-communities/update-a-community.json)
- [list-communities](https://io.net/docs/openapi/rag-graphs-communities/list-communities.json)
- [get-community-details](https://io.net/docs/openapi/rag-graphs-communities/get-community-details.json)
- [delete-a-community](https://io.net/docs/openapi/rag-graphs-communities/delete-a-community.json)
- [build-graph-communities](https://io.net/docs/openapi/rag-graphs-communities/build-graph-communities.json)
- [get-relationship-details](https://io.net/docs/openapi/rag-graphs-relationships/get-relationship-details.json)
- [get-graph-relationships](https://io.net/docs/openapi/rag-graphs-relationships/get-graph-relationships.json)
- [list-graph-entities](https://io.net/docs/openapi/rag-graphs-entities/list-graph-entities.json)
- [get-single-entity-details](https://io.net/docs/openapi/rag-graphs-entities/get-single-entity-details.json)
- [pull-and-rebuild-graph](https://io.net/docs/openapi/rag-graphs/pull-and-rebuild-graph.json)
- [get-graph-data-for-a-collection](https://io.net/docs/openapi/rag-graphs/get-graph-data-for-a-collection.json)
- [update-document-metadata-partial](https://io.net/docs/openapi/rag-documents/update-document-metadata-partial.json)
- [get-relationships](https://io.net/docs/openapi/rag-documents/get-relationships.json)
- [get-extracted-entities](https://io.net/docs/openapi/rag-documents/get-extracted-entities.json)
- [get-document-chunks](https://io.net/docs/openapi/rag-documents/get-document-chunks.json)
- [extract-entities](https://io.net/docs/openapi/rag-documents/extract-entities.json)
- [download-original-file](https://io.net/docs/openapi/rag-documents/download-original-file.json)
- [delete-document-by-id](https://io.net/docs/openapi/rag-documents/delete-document-by-id.json)
- [deduplicate-document](https://io.net/docs/openapi/rag-documents/deduplicate-document.json)
- [get-current-user](https://io.net/docs/openapi/rag-users/get-current-user.json)
- [add-collection-to-user](https://io.net/docs/openapi/rag-users/add-collection-to-user.json)
- [health-check](https://io.net/docs/openapi/rag-system/health-check.json)
- [list-all-prompts](https://io.net/docs/openapi/rag-prompts/list-all-prompts.json)
- [list-all-indices](https://io.net/docs/openapi/rag-indices/list-all-indices.json)
- [get-specific-index-details](https://io.net/docs/openapi/rag-indices/get-specific-index-details.json)
- [delete-an-index](https://io.net/docs/openapi/rag-indices/delete-an-index.json)
- [get-graph-overview](https://io.net/docs/openapi/rag-graphs/get-graph-overview.json)
- [add-new-entities](https://io.net/docs/openapi/rag-graphs-entities/add-new-entities.json)
- [list-conversations](https://io.net/docs/openapi/rag-conversations/list-conversations.json)
- [create-a-new-conversation](https://io.net/docs/openapi/rag-conversations/create-a-new-conversation.json)
- [list-collections](https://io.net/docs/openapi/rag-collections/list-collections.json)
- [get-collection-by-name](https://io.net/docs/openapi/rag-collections/get-collection-by-name.json)
- [create-a-new-collection](https://io.net/docs/openapi/rag-collections/create-a-new-collection.json)
- [search-chunks](https://io.net/docs/openapi/rag-chunks/search-chunks.json)
- [list-chunks](https://io.net/docs/openapi/rag-chunks/list-chunks.json)
- [semantic-search](https://io.net/docs/openapi/rag-retrieval/semantic-search.json)
- [retrieve-and-generate-rag](https://io.net/docs/openapi/rag-retrieval/retrieve-and-generate-rag.json)
- [agent-based-query-resolution](https://io.net/docs/openapi/rag-retrieval/agent-based-query-resolution.json)
- [upload-and-ingest-a-document](https://io.net/docs/openapi/rag-documents/upload-and-ingest-a-document.json)
- [search-documents](https://io.net/docs/openapi/rag-documents/search-documents.json)
- [list-all-documents](https://io.net/docs/openapi/rag-documents/list-all-documents.json)
- [delete-documents-by-filter](https://io.net/docs/openapi/rag-documents/delete-documents-by-filter.json)
- [device-notifications](https://io.net/docs/openapi/io-explorer/device-notifications.json)
- [RAG](https://io.net/docs/openapi/full/RAG.json)
- [IO_Explorer__IO_CLouds](https://io.net/docs/openapi/full/IO_Explorer__IO_CLouds.json)
- [openapi](https://io.net/docs/api-reference/openapi.json)