[{"data":1,"prerenderedAt":2674},["ShallowReactive",2],{"blog-\u002Fblog\u002F2025\u002F10\u002Fcustom-onnx-model":3,"featureCatalog":1744,"changelog-titles":2139,"blog-all-for-related":2673},{"id":4,"title":5,"authors":6,"body":8,"cta":1724,"date":1725,"description":1726,"extension":1727,"features":1724,"image":1728,"lastUpdated":1724,"meta":1729,"navigation":810,"path":1735,"release":1724,"seo":1736,"sitemap":1737,"stem":1738,"subtitle":1739,"tags":1740,"tldr":1724,"video":1724,"__hash__":1743},"blog\u002Fblog\u002F2025\u002F10\u002Fcustom-onnx-model.md","Deploy Custom-Trained AI Models: Using ONNX with Node-RED and FlowFuse",[7],"stephen-mclaughlin",{"type":9,"value":10,"toc":1704},"minimark",[11,15,20,23,34,38,41,45,48,61,64,68,73,81,87,92,102,133,142,146,157,206,210,213,228,231,248,251,265,271,274,316,319,372,379,398,402,416,641,648,760,764,767,773,791,794,1442,1446,1449,1460,1463,1515,1522,1526,1605,1614,1622,1626,1630,1633,1645,1652,1683,1686,1700],[12,13,14],"p",{},"FlowFuse is introducing a new set of AI nodes to make it easier than ever to integrate AI and machine learning into your Node-RED workflows.\nIn this guide, you will learn how to train an image classifier model, and use it with the new FlowFuse AI Nodes to recognise your own products, components - or anything else you can imagine.",[16,17,19],"h3",{"id":18},"introduction","Introduction",[12,21,22],{},"In this article, we will be building a PyTorch-based image classification model to identify fruit types (apple, kiwi, mango) using a dataset of labelled images.\nOf course, you would typically be classifying your own things like your company widgets and products, but for the sake of learning the process, we will be using images of fruit.\nOnce the model is trained, it is exported to the ONNX format, it is then ready for use with the new FlowFuse AI nodes.",[12,24,25,26,33],{},"Note: The code and sample dataset used in this tutorial can be downloaded from ",[27,28,32],"a",{"href":29,"rel":30},"https:\u002F\u002Fwebsite-data.s3.eu-west-1.amazonaws.com\u002F2025-10-onnx-model-training-dataset.zip",[31],"nofollow","this link",".",[16,35,37],{"id":36},"some-background-first","Some background first",[12,39,40],{},"The process we will use is commonly referred to as \"transfer learning\". This is where you take a pre-trained model and fine-tune it on your own dataset.\nThis is a common approach in deep learning as it allows us to leverage the knowledge learned by the pre-trained model and adapt it to our specific task with a smaller dataset.  For reference, this tutorial will use ResNet-18 which is an 18-layer Residual Network (ResNet), a convolutional neural network (CNN) architecture that uses \"skip connections\" to help train very deep networks by addressing the vanishing gradient problem. Pre-trained ResNet-18 models are often trained on the ImageNet dataset and are widely used for image classification of 1000 categories.",[16,42,44],{"id":43},"overview-of-operations","Overview of operations",[12,46,47],{},"The 3 main steps to achieve this involves:",[49,50,51,55,58],"ol",{},[52,53,54],"li",{},"Setting up a Python environment with PyTorch, TorchVision, ONNX, and ONNX Runtime.",[52,56,57],{},"Organizing your dataset into train, validation, and test folders for each class.",[52,59,60],{},"Perform \"transfer learning\" to fine-tune the model against your images & generate the ONNX model.",[12,62,63],{},"Let's get started...",[16,65,67],{"id":66},"setup-the-environment","Setup the environment",[69,70,72],"h4",{"id":71},"pre-requisites","Pre-requisites",[12,74,75,76,80],{},"This tutorial was tested on Ubuntu using Python 3 and ",[77,78,79],"code",{},"pyenv"," for environment management.",[12,82,83,84,86],{},"For the sake of brevity, from this point forward, the tutorial will assume you are using a debian based operating system and ",[77,85,79],{},".\nInstructions will need to be adapted if you are using something else.",[88,89,91],"h5",{"id":90},"python-tools","Python tools",[12,93,94,95,97,98,101],{},"Ensure you have ",[77,96,79],{}," and ",[77,99,100],{},"pyenv-virtualenv"," installed.",[103,104,109],"pre",{"className":105,"code":106,"language":107,"meta":108,"style":108},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","pyenv --version\npyenv virtualenv --version\n","bash","",[77,110,111,123],{"__ignoreMap":108},[112,113,116,119],"span",{"class":114,"line":115},"line",1,[112,117,79],{"class":118},"sBMFI",[112,120,122],{"class":121},"sfazB"," --version\n",[112,124,126,128,131],{"class":114,"line":125},2,[112,127,79],{"class":118},[112,129,130],{"class":121}," virtualenv",[112,132,122],{"class":121},[12,134,135,136,141],{},"If you don't have them installed, this ",[27,137,140],{"href":138,"rel":139},"https:\u002F\u002Fmedium.com\u002F@aashari\u002Feasy-to-follow-guide-of-how-to-install-pyenv-on-ubuntu-a3730af8d7f0",[31],"Medium article"," worked well in our case.",[88,143,145],{"id":144},"sub-dependencies","Sub dependencies",[12,147,148,149,152,153,156],{},"During setup and testing, my installation failed at the last step due to missing ",[77,150,151],{},"bz2"," support (a TorchVision dependency).\nIf you encounter this, you would need to install ",[77,154,155],{},"libbz2"," then you would need to rebuild your python environment.\nTo save time, I recommend that you perform the steps below now to ensure the dependencies are installed and avoid the mis-step.",[103,158,160],{"className":105,"code":159,"language":107,"meta":108,"style":108},"sudo apt update\nsudo apt install -y libbz2-dev liblzma-dev libsqlite3-dev libssl-dev zlib1g-dev libffi-dev build-essential\n",[77,161,162,173],{"__ignoreMap":108},[112,163,164,167,170],{"class":114,"line":115},[112,165,166],{"class":118},"sudo",[112,168,169],{"class":121}," apt",[112,171,172],{"class":121}," update\n",[112,174,175,177,179,182,185,188,191,194,197,200,203],{"class":114,"line":125},[112,176,166],{"class":118},[112,178,169],{"class":121},[112,180,181],{"class":121}," install",[112,183,184],{"class":121}," -y",[112,186,187],{"class":121}," libbz2-dev",[112,189,190],{"class":121}," liblzma-dev",[112,192,193],{"class":121}," libsqlite3-dev",[112,195,196],{"class":121}," libssl-dev",[112,198,199],{"class":121}," zlib1g-dev",[112,201,202],{"class":121}," libffi-dev",[112,204,205],{"class":121}," build-essential\n",[69,207,209],{"id":208},"virtual-environment-setup","Virtual Environment Setup",[12,211,212],{},"Install python 3.10.14 (or any version compatible with pytorch and onnx):",[103,214,216],{"className":105,"code":215,"language":107,"meta":108,"style":108},"pyenv install 3.10.14\n",[77,217,218],{"__ignoreMap":108},[112,219,220,222,224],{"class":114,"line":115},[112,221,79],{"class":118},[112,223,181],{"class":121},[112,225,227],{"class":226},"sbssI"," 3.10.14\n",[12,229,230],{},"Create a new virtual environment:",[103,232,234],{"className":105,"code":233,"language":107,"meta":108,"style":108},"pyenv virtualenv 3.10.14 venv_py3_10_14_pytorch\n",[77,235,236],{"__ignoreMap":108},[112,237,238,240,242,245],{"class":114,"line":115},[112,239,79],{"class":118},[112,241,130],{"class":121},[112,243,244],{"class":226}," 3.10.14",[112,246,247],{"class":121}," venv_py3_10_14_pytorch\n",[12,249,250],{},"Activate the virtual environment:",[103,252,254],{"className":105,"code":253,"language":107,"meta":108,"style":108},"pyenv activate venv_py3_10_14_pytorch\n",[77,255,256],{"__ignoreMap":108},[112,257,258,260,263],{"class":114,"line":115},[112,259,79],{"class":118},[112,261,262],{"class":121}," activate",[112,264,247],{"class":121},[12,266,267],{},[268,269,270],"em",{},"NOTE: Depending on your shell, your commandline may become decorated with the name of the virtual environment.",[12,272,273],{},"Install the required packages:",[103,275,277],{"className":105,"code":276,"language":107,"meta":108,"style":108},"pip install --upgrade pip\npip install torch torchvision onnx onnxruntime matplotlib numpy\n",[77,278,279,292],{"__ignoreMap":108},[112,280,281,284,286,289],{"class":114,"line":115},[112,282,283],{"class":118},"pip",[112,285,181],{"class":121},[112,287,288],{"class":121}," --upgrade",[112,290,291],{"class":121}," pip\n",[112,293,294,296,298,301,304,307,310,313],{"class":114,"line":125},[112,295,283],{"class":118},[112,297,181],{"class":121},[112,299,300],{"class":121}," torch",[112,302,303],{"class":121}," torchvision",[112,305,306],{"class":121}," onnx",[112,308,309],{"class":121}," onnxruntime",[112,311,312],{"class":121}," matplotlib",[112,314,315],{"class":121}," numpy\n",[12,317,318],{},"Create a working directory",[103,320,322],{"className":105,"code":321,"language":107,"meta":108,"style":108},"mkdir ~\u002Fmy-py-projects\ncd ~\u002Fmy-py-projects\nmkdir pytorch-onnx\ncd pytorch-onnx\n# Associate this directory with the virtual env we created earlier\npyenv local venv_py3_10_14_pytorch\n",[77,323,324,332,340,348,355,362],{"__ignoreMap":108},[112,325,326,329],{"class":114,"line":115},[112,327,328],{"class":118},"mkdir",[112,330,331],{"class":121}," ~\u002Fmy-py-projects\n",[112,333,334,338],{"class":114,"line":125},[112,335,337],{"class":336},"s2Zo4","cd",[112,339,331],{"class":121},[112,341,343,345],{"class":114,"line":342},3,[112,344,328],{"class":118},[112,346,347],{"class":121}," pytorch-onnx\n",[112,349,351,353],{"class":114,"line":350},4,[112,352,337],{"class":336},[112,354,347],{"class":121},[112,356,358],{"class":114,"line":357},5,[112,359,361],{"class":360},"sHwdD","# Associate this directory with the virtual env we created earlier\n",[112,363,365,367,370],{"class":114,"line":364},6,[112,366,79],{"class":118},[112,368,369],{"class":121}," local",[112,371,247],{"class":121},[12,373,374,375,378],{},"(Optional) Create a ",[77,376,377],{},"requirements.txt"," file to document the packages used in this project:",[103,380,382],{"className":105,"code":381,"language":107,"meta":108,"style":108},"pip freeze > requirements.txt\n",[77,383,384],{"__ignoreMap":108},[112,385,386,388,391,395],{"class":114,"line":115},[112,387,283],{"class":118},[112,389,390],{"class":121}," freeze",[112,392,394],{"class":393},"sMK4o"," >",[112,396,397],{"class":121}," requirements.txt\n",[16,399,401],{"id":400},"organizing-your-dataset","Organizing your dataset",[12,403,404,405,410,411,415],{},"For this example, I have created a simple dataset of images of apples, kiwis, and mangos.\nYou can use your own dataset or download a dataset from the internet (e.g. ",[27,406,409],{"href":407,"rel":408},"https:\u002F\u002Fwww.kaggle.com\u002Fdatasets\u002F",[31],"this one"," or ",[27,412,409],{"href":413,"rel":414},"https:\u002F\u002Fimages.cv\u002Fsearch-labeled-image-dataset",[31],").\nJust make sure to organize the images in the following structure:",[103,417,419],{"className":105,"code":418,"language":107,"meta":108,"style":108},"data\u002F\n    train\u002F\n        apples\u002F\n            apple1.jpg\n            apple2.jpg\n            ...\n        kiwis\u002F\n            kiwi1.jpg\n            kiwi2.jpg\n            ...\n        mangos\u002F\n            mango1.jpg\n            mango2.jpg\n            ...\n    val\u002F\n        apples\u002F\n            apple3.jpg\n            apple4.jpg\n            ...\n        kiwis\u002F\n            kiwi3.jpg\n            kiwi4.jpg\n            ...\n        mangos\u002F\n            mango3.jpg\n            mango4.jpg\n            ...\n    test\u002F\n        apples\u002F\n            apple5.jpg\n            apple6.jpg\n            ...\n        kiwis\u002F\n            kiwi5.jpg\n            kiwi6.jpg\n            ...\n        mangos\u002F\n            mango5.jpg\n            mango6.jpg\n            ...\n",[77,420,421,426,431,436,441,446,451,457,463,469,474,480,486,492,497,503,508,514,520,525,530,536,542,547,552,558,564,569,575,580,586,592,597,602,608,614,619,624,630,636],{"__ignoreMap":108},[112,422,423],{"class":114,"line":115},[112,424,425],{"class":118},"data\u002F\n",[112,427,428],{"class":114,"line":125},[112,429,430],{"class":118},"    train\u002F\n",[112,432,433],{"class":114,"line":342},[112,434,435],{"class":118},"        apples\u002F\n",[112,437,438],{"class":114,"line":350},[112,439,440],{"class":118},"            apple1.jpg\n",[112,442,443],{"class":114,"line":357},[112,444,445],{"class":118},"            apple2.jpg\n",[112,447,448],{"class":114,"line":364},[112,449,450],{"class":336},"            ...\n",[112,452,454],{"class":114,"line":453},7,[112,455,456],{"class":118},"        kiwis\u002F\n",[112,458,460],{"class":114,"line":459},8,[112,461,462],{"class":118},"            kiwi1.jpg\n",[112,464,466],{"class":114,"line":465},9,[112,467,468],{"class":118},"            kiwi2.jpg\n",[112,470,472],{"class":114,"line":471},10,[112,473,450],{"class":336},[112,475,477],{"class":114,"line":476},11,[112,478,479],{"class":118},"        mangos\u002F\n",[112,481,483],{"class":114,"line":482},12,[112,484,485],{"class":118},"            mango1.jpg\n",[112,487,489],{"class":114,"line":488},13,[112,490,491],{"class":118},"            mango2.jpg\n",[112,493,495],{"class":114,"line":494},14,[112,496,450],{"class":336},[112,498,500],{"class":114,"line":499},15,[112,501,502],{"class":118},"    val\u002F\n",[112,504,506],{"class":114,"line":505},16,[112,507,435],{"class":118},[112,509,511],{"class":114,"line":510},17,[112,512,513],{"class":118},"            apple3.jpg\n",[112,515,517],{"class":114,"line":516},18,[112,518,519],{"class":118},"            apple4.jpg\n",[112,521,523],{"class":114,"line":522},19,[112,524,450],{"class":336},[112,526,528],{"class":114,"line":527},20,[112,529,456],{"class":118},[112,531,533],{"class":114,"line":532},21,[112,534,535],{"class":118},"            kiwi3.jpg\n",[112,537,539],{"class":114,"line":538},22,[112,540,541],{"class":118},"            kiwi4.jpg\n",[112,543,545],{"class":114,"line":544},23,[112,546,450],{"class":336},[112,548,550],{"class":114,"line":549},24,[112,551,479],{"class":118},[112,553,555],{"class":114,"line":554},25,[112,556,557],{"class":118},"            mango3.jpg\n",[112,559,561],{"class":114,"line":560},26,[112,562,563],{"class":118},"            mango4.jpg\n",[112,565,567],{"class":114,"line":566},27,[112,568,450],{"class":336},[112,570,572],{"class":114,"line":571},28,[112,573,574],{"class":118},"    test\u002F\n",[112,576,578],{"class":114,"line":577},29,[112,579,435],{"class":118},[112,581,583],{"class":114,"line":582},30,[112,584,585],{"class":118},"            apple5.jpg\n",[112,587,589],{"class":114,"line":588},31,[112,590,591],{"class":118},"            apple6.jpg\n",[112,593,595],{"class":114,"line":594},32,[112,596,450],{"class":336},[112,598,600],{"class":114,"line":599},33,[112,601,456],{"class":118},[112,603,605],{"class":114,"line":604},34,[112,606,607],{"class":118},"            kiwi5.jpg\n",[112,609,611],{"class":114,"line":610},35,[112,612,613],{"class":118},"            kiwi6.jpg\n",[112,615,617],{"class":114,"line":616},36,[112,618,450],{"class":336},[112,620,622],{"class":114,"line":621},37,[112,623,479],{"class":118},[112,625,627],{"class":114,"line":626},38,[112,628,629],{"class":118},"            mango5.jpg\n",[112,631,633],{"class":114,"line":632},39,[112,634,635],{"class":118},"            mango6.jpg\n",[112,637,639],{"class":114,"line":638},40,[112,640,450],{"class":336},[12,642,643,644,647],{},"Now, inside ",[77,645,646],{},"~\u002Fmy-py-projects\u002Fpytorch-onnx\u002F"," you should have:",[103,649,651],{"className":105,"code":650,"language":107,"meta":108,"style":108},"pytorch-onnx\u002F\n│\n├── data\u002F\n│   ├── train\u002F\n│   │   ├── apples\u002F\n│   │   ├── kiwis\u002F\n│   │   └── mangos\u002F\n│   ├── val\u002F\n│   └── test\u002F\n│\n├── fruit_classifier.py   # we will create this shortly\n└── requirements.txt      # optional\n",[77,652,653,658,663,671,682,694,705,717,726,735,739,749],{"__ignoreMap":108},[112,654,655],{"class":114,"line":115},[112,656,657],{"class":118},"pytorch-onnx\u002F\n",[112,659,660],{"class":114,"line":125},[112,661,662],{"class":118},"│\n",[112,664,665,668],{"class":114,"line":342},[112,666,667],{"class":118},"├──",[112,669,670],{"class":121}," data\u002F\n",[112,672,673,676,679],{"class":114,"line":350},[112,674,675],{"class":118},"│",[112,677,678],{"class":121},"   ├──",[112,680,681],{"class":121}," train\u002F\n",[112,683,684,686,689,691],{"class":114,"line":357},[112,685,675],{"class":118},[112,687,688],{"class":121},"   │",[112,690,678],{"class":121},[112,692,693],{"class":121}," apples\u002F\n",[112,695,696,698,700,702],{"class":114,"line":364},[112,697,675],{"class":118},[112,699,688],{"class":121},[112,701,678],{"class":121},[112,703,704],{"class":121}," kiwis\u002F\n",[112,706,707,709,711,714],{"class":114,"line":453},[112,708,675],{"class":118},[112,710,688],{"class":121},[112,712,713],{"class":121},"   └──",[112,715,716],{"class":121}," mangos\u002F\n",[112,718,719,721,723],{"class":114,"line":459},[112,720,675],{"class":118},[112,722,678],{"class":121},[112,724,725],{"class":121}," val\u002F\n",[112,727,728,730,732],{"class":114,"line":465},[112,729,675],{"class":118},[112,731,713],{"class":121},[112,733,734],{"class":121}," test\u002F\n",[112,736,737],{"class":114,"line":471},[112,738,662],{"class":118},[112,740,741,743,746],{"class":114,"line":476},[112,742,667],{"class":118},[112,744,745],{"class":121}," fruit_classifier.py",[112,747,748],{"class":360},"   # we will create this shortly\n",[112,750,751,754,757],{"class":114,"line":482},[112,752,753],{"class":118},"└──",[112,755,756],{"class":121}," requirements.txt",[112,758,759],{"class":360},"      # optional\n",[16,761,763],{"id":762},"fine-tune-the-model","Fine-tune the model",[12,765,766],{},"Now we can create a simple pytorch model to classify the images.",[12,768,769,770],{},"Create a new file called ",[77,771,772],{},"fruit_classifier.py",[103,774,776],{"className":105,"code":775,"language":107,"meta":108,"style":108},"# Use nano to create the file (you can use your favorite editor e.g. vim, code, etc)\nnano fruit_classifier.py\n",[77,777,778,783],{"__ignoreMap":108},[112,779,780],{"class":114,"line":115},[112,781,782],{"class":360},"# Use nano to create the file (you can use your favorite editor e.g. vim, code, etc)\n",[112,784,785,788],{"class":114,"line":125},[112,786,787],{"class":118},"nano",[112,789,790],{"class":121}," fruit_classifier.py\n",[12,792,793],{},"Add the following code:",[103,795,799],{"className":796,"code":797,"language":798,"meta":108,"style":108},"language-python shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# fruit_classifier.py\n\nimport torch\nimport torch.nn as nn\nimport torch.optim as optim\nfrom torch.utils.data import DataLoader\nimport torchvision.transforms as transforms\nimport torchvision.datasets as datasets\nimport torchvision.models as models\nimport onnxruntime as ort\nimport numpy as np\n\n# --- Dataset ---\ndata_dir = \"data\"\ntransform = transforms.Compose([\n    transforms.Resize((224, 224)),\n    transforms.ToTensor(),\n    transforms.Normalize(mean=[0.485, 0.456, 0.406],\n                         std=[0.229, 0.224, 0.225])\n])\n\ntrain_dataset = datasets.ImageFolder(f\"{data_dir}\u002Ftrain\", transform=transform)\nval_dataset   = datasets.ImageFolder(f\"{data_dir}\u002Fval\", transform=transform)\ntest_dataset  = datasets.ImageFolder(f\"{data_dir}\u002Ftest\", transform=transform)\n\ntrain_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)\nval_loader   = DataLoader(val_dataset, batch_size=32, shuffle=False)\ntest_loader  = DataLoader(test_dataset, batch_size=32, shuffle=False)\n\nprint(\"Class mapping:\", train_dataset.class_to_idx)\n\ndevice = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n\n# --- Model ---\nmodel = models.resnet18(weights=models.ResNet18_Weights.IMAGENET1K_V1)\nmodel.fc = nn.Linear(model.fc.in_features, len(train_dataset.classes))\nmodel = model.to(device)\n\ncriterion = nn.CrossEntropyLoss()\noptimizer = optim.Adam(model.parameters(), lr=1e-4)\n\n\n# --- Training ---\ndef train(num_epochs=5):\n    for epoch in range(num_epochs):\n        model.train()\n        running_loss = 0.0\n        for inputs, labels in train_loader:\n            inputs, labels = inputs.to(device), labels.to(device)\n\n            optimizer.zero_grad()\n            outputs = model(inputs)\n            loss = criterion(outputs, labels)\n            loss.backward()\n            optimizer.step()\n\n            running_loss += loss.item()\n\n        avg_loss = running_loss \u002F len(train_loader)\n        print(f\"Epoch {epoch+1}, Loss: {avg_loss:.4f}\")\n\n\n# --- Evaluation ---\ndef evaluate(loader):\n    model.eval()\n    correct, total = 0, 0\n    with torch.no_grad():\n        for inputs, labels in loader:\n            inputs, labels = inputs.to(device), labels.to(device)\n            outputs = model(inputs)\n            _, preds = torch.max(outputs, 1)\n            correct += (preds == labels).sum().item()\n            total += labels.size(0)\n    return correct \u002F total\n\n\n# --- Export to ONNX ---\ndef export_model():\n    dummy_input = torch.randn(1, 3, 224, 224, device=device)\n\n    torch.onnx.export(\n        model,               # model being run\n        dummy_input,         # model input (or a tuple for multiple inputs)\n        \"fruit_classifier.onnx\",    # where to save the model (can be a file or file-like object)\n        export_params=True,  # store the trained parameter weights inside the model file\n        opset_version=16,    # the ONNX version to export the model to\n        do_constant_folding=True,  # whether to execute constant folding for optimization\n        input_names=['input'],   # the model's input names\n        output_names=['output'],  # the model's output names\n        dynamic_axes={\"input\": {0: \"batch_size\"}, \"output\": {0: \"batch_size\"}}\n    )\n\n    print(\"Model exported to fruit_classifier.onnx\")\n\n\n# --- Test with ONNX Runtime ---\ndef test_onnx():\n    ort_session = ort.InferenceSession(\"fruit_classifier.onnx\")\n\n    def to_numpy(tensor):\n        return tensor.detach().cpu().numpy() if tensor.requires_grad else tensor.cpu().numpy()\n\n    inputs, _ = next(iter(test_loader))\n    ort_inputs = {\"input\": to_numpy(inputs[:1])}\n    ort_outs = ort_session.run(None, ort_inputs)\n\n    pred_class = np.argmax(ort_outs[0])\n    print(\"ONNX Prediction:\", train_dataset.classes[pred_class])\n\n\n# --- Main ---\nif __name__ == \"__main__\":\n    train(num_epochs=5)\n    val_acc = evaluate(val_loader)\n    print(f\"Validation Accuracy: {val_acc:.2%}\")\n\n    export_model()\n    test_onnx()\n\n","python",[77,800,801,806,812,817,822,827,832,837,842,847,852,857,861,866,871,876,881,886,891,896,901,905,910,915,920,924,929,934,939,943,948,952,957,961,966,971,976,981,985,990,995,1000,1005,1011,1017,1023,1029,1035,1041,1047,1052,1058,1064,1070,1076,1082,1087,1093,1098,1104,1110,1115,1120,1126,1132,1138,1144,1150,1156,1161,1166,1172,1178,1184,1190,1195,1200,1206,1212,1218,1223,1229,1235,1241,1247,1253,1259,1265,1271,1277,1283,1289,1294,1300,1305,1310,1316,1322,1328,1333,1339,1345,1350,1356,1362,1368,1373,1379,1385,1390,1395,1401,1407,1413,1419,1425,1430,1436],{"__ignoreMap":108},[112,802,803],{"class":114,"line":115},[112,804,805],{},"# fruit_classifier.py\n",[112,807,808],{"class":114,"line":125},[112,809,811],{"emptyLinePlaceholder":810},true,"\n",[112,813,814],{"class":114,"line":342},[112,815,816],{},"import torch\n",[112,818,819],{"class":114,"line":350},[112,820,821],{},"import torch.nn as nn\n",[112,823,824],{"class":114,"line":357},[112,825,826],{},"import torch.optim as optim\n",[112,828,829],{"class":114,"line":364},[112,830,831],{},"from torch.utils.data import DataLoader\n",[112,833,834],{"class":114,"line":453},[112,835,836],{},"import torchvision.transforms as transforms\n",[112,838,839],{"class":114,"line":459},[112,840,841],{},"import torchvision.datasets as datasets\n",[112,843,844],{"class":114,"line":465},[112,845,846],{},"import torchvision.models as models\n",[112,848,849],{"class":114,"line":471},[112,850,851],{},"import onnxruntime as ort\n",[112,853,854],{"class":114,"line":476},[112,855,856],{},"import numpy as np\n",[112,858,859],{"class":114,"line":482},[112,860,811],{"emptyLinePlaceholder":810},[112,862,863],{"class":114,"line":488},[112,864,865],{},"# --- Dataset ---\n",[112,867,868],{"class":114,"line":494},[112,869,870],{},"data_dir = \"data\"\n",[112,872,873],{"class":114,"line":499},[112,874,875],{},"transform = transforms.Compose([\n",[112,877,878],{"class":114,"line":505},[112,879,880],{},"    transforms.Resize((224, 224)),\n",[112,882,883],{"class":114,"line":510},[112,884,885],{},"    transforms.ToTensor(),\n",[112,887,888],{"class":114,"line":516},[112,889,890],{},"    transforms.Normalize(mean=[0.485, 0.456, 0.406],\n",[112,892,893],{"class":114,"line":522},[112,894,895],{},"                         std=[0.229, 0.224, 0.225])\n",[112,897,898],{"class":114,"line":527},[112,899,900],{},"])\n",[112,902,903],{"class":114,"line":532},[112,904,811],{"emptyLinePlaceholder":810},[112,906,907],{"class":114,"line":538},[112,908,909],{},"train_dataset = datasets.ImageFolder(f\"{data_dir}\u002Ftrain\", transform=transform)\n",[112,911,912],{"class":114,"line":544},[112,913,914],{},"val_dataset   = datasets.ImageFolder(f\"{data_dir}\u002Fval\", transform=transform)\n",[112,916,917],{"class":114,"line":549},[112,918,919],{},"test_dataset  = datasets.ImageFolder(f\"{data_dir}\u002Ftest\", transform=transform)\n",[112,921,922],{"class":114,"line":554},[112,923,811],{"emptyLinePlaceholder":810},[112,925,926],{"class":114,"line":560},[112,927,928],{},"train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)\n",[112,930,931],{"class":114,"line":566},[112,932,933],{},"val_loader   = DataLoader(val_dataset, batch_size=32, shuffle=False)\n",[112,935,936],{"class":114,"line":571},[112,937,938],{},"test_loader  = DataLoader(test_dataset, batch_size=32, shuffle=False)\n",[112,940,941],{"class":114,"line":577},[112,942,811],{"emptyLinePlaceholder":810},[112,944,945],{"class":114,"line":582},[112,946,947],{},"print(\"Class mapping:\", train_dataset.class_to_idx)\n",[112,949,950],{"class":114,"line":588},[112,951,811],{"emptyLinePlaceholder":810},[112,953,954],{"class":114,"line":594},[112,955,956],{},"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",[112,958,959],{"class":114,"line":599},[112,960,811],{"emptyLinePlaceholder":810},[112,962,963],{"class":114,"line":604},[112,964,965],{},"# --- Model ---\n",[112,967,968],{"class":114,"line":610},[112,969,970],{},"model = models.resnet18(weights=models.ResNet18_Weights.IMAGENET1K_V1)\n",[112,972,973],{"class":114,"line":616},[112,974,975],{},"model.fc = nn.Linear(model.fc.in_features, len(train_dataset.classes))\n",[112,977,978],{"class":114,"line":621},[112,979,980],{},"model = model.to(device)\n",[112,982,983],{"class":114,"line":626},[112,984,811],{"emptyLinePlaceholder":810},[112,986,987],{"class":114,"line":632},[112,988,989],{},"criterion = nn.CrossEntropyLoss()\n",[112,991,992],{"class":114,"line":638},[112,993,994],{},"optimizer = optim.Adam(model.parameters(), lr=1e-4)\n",[112,996,998],{"class":114,"line":997},41,[112,999,811],{"emptyLinePlaceholder":810},[112,1001,1003],{"class":114,"line":1002},42,[112,1004,811],{"emptyLinePlaceholder":810},[112,1006,1008],{"class":114,"line":1007},43,[112,1009,1010],{},"# --- Training ---\n",[112,1012,1014],{"class":114,"line":1013},44,[112,1015,1016],{},"def train(num_epochs=5):\n",[112,1018,1020],{"class":114,"line":1019},45,[112,1021,1022],{},"    for epoch in range(num_epochs):\n",[112,1024,1026],{"class":114,"line":1025},46,[112,1027,1028],{},"        model.train()\n",[112,1030,1032],{"class":114,"line":1031},47,[112,1033,1034],{},"        running_loss = 0.0\n",[112,1036,1038],{"class":114,"line":1037},48,[112,1039,1040],{},"        for inputs, labels in train_loader:\n",[112,1042,1044],{"class":114,"line":1043},49,[112,1045,1046],{},"            inputs, labels = inputs.to(device), labels.to(device)\n",[112,1048,1050],{"class":114,"line":1049},50,[112,1051,811],{"emptyLinePlaceholder":810},[112,1053,1055],{"class":114,"line":1054},51,[112,1056,1057],{},"            optimizer.zero_grad()\n",[112,1059,1061],{"class":114,"line":1060},52,[112,1062,1063],{},"            outputs = model(inputs)\n",[112,1065,1067],{"class":114,"line":1066},53,[112,1068,1069],{},"            loss = criterion(outputs, labels)\n",[112,1071,1073],{"class":114,"line":1072},54,[112,1074,1075],{},"            loss.backward()\n",[112,1077,1079],{"class":114,"line":1078},55,[112,1080,1081],{},"            optimizer.step()\n",[112,1083,1085],{"class":114,"line":1084},56,[112,1086,811],{"emptyLinePlaceholder":810},[112,1088,1090],{"class":114,"line":1089},57,[112,1091,1092],{},"            running_loss += loss.item()\n",[112,1094,1096],{"class":114,"line":1095},58,[112,1097,811],{"emptyLinePlaceholder":810},[112,1099,1101],{"class":114,"line":1100},59,[112,1102,1103],{},"        avg_loss = running_loss \u002F len(train_loader)\n",[112,1105,1107],{"class":114,"line":1106},60,[112,1108,1109],{},"        print(f\"Epoch {epoch+1}, Loss: {avg_loss:.4f}\")\n",[112,1111,1113],{"class":114,"line":1112},61,[112,1114,811],{"emptyLinePlaceholder":810},[112,1116,1118],{"class":114,"line":1117},62,[112,1119,811],{"emptyLinePlaceholder":810},[112,1121,1123],{"class":114,"line":1122},63,[112,1124,1125],{},"# --- Evaluation ---\n",[112,1127,1129],{"class":114,"line":1128},64,[112,1130,1131],{},"def evaluate(loader):\n",[112,1133,1135],{"class":114,"line":1134},65,[112,1136,1137],{},"    model.eval()\n",[112,1139,1141],{"class":114,"line":1140},66,[112,1142,1143],{},"    correct, total = 0, 0\n",[112,1145,1147],{"class":114,"line":1146},67,[112,1148,1149],{},"    with torch.no_grad():\n",[112,1151,1153],{"class":114,"line":1152},68,[112,1154,1155],{},"        for inputs, labels in loader:\n",[112,1157,1159],{"class":114,"line":1158},69,[112,1160,1046],{},[112,1162,1164],{"class":114,"line":1163},70,[112,1165,1063],{},[112,1167,1169],{"class":114,"line":1168},71,[112,1170,1171],{},"            _, preds = torch.max(outputs, 1)\n",[112,1173,1175],{"class":114,"line":1174},72,[112,1176,1177],{},"            correct += (preds == labels).sum().item()\n",[112,1179,1181],{"class":114,"line":1180},73,[112,1182,1183],{},"            total += labels.size(0)\n",[112,1185,1187],{"class":114,"line":1186},74,[112,1188,1189],{},"    return correct \u002F total\n",[112,1191,1193],{"class":114,"line":1192},75,[112,1194,811],{"emptyLinePlaceholder":810},[112,1196,1198],{"class":114,"line":1197},76,[112,1199,811],{"emptyLinePlaceholder":810},[112,1201,1203],{"class":114,"line":1202},77,[112,1204,1205],{},"# --- Export to ONNX ---\n",[112,1207,1209],{"class":114,"line":1208},78,[112,1210,1211],{},"def export_model():\n",[112,1213,1215],{"class":114,"line":1214},79,[112,1216,1217],{},"    dummy_input = torch.randn(1, 3, 224, 224, device=device)\n",[112,1219,1221],{"class":114,"line":1220},80,[112,1222,811],{"emptyLinePlaceholder":810},[112,1224,1226],{"class":114,"line":1225},81,[112,1227,1228],{},"    torch.onnx.export(\n",[112,1230,1232],{"class":114,"line":1231},82,[112,1233,1234],{},"        model,               # model being run\n",[112,1236,1238],{"class":114,"line":1237},83,[112,1239,1240],{},"        dummy_input,         # model input (or a tuple for multiple inputs)\n",[112,1242,1244],{"class":114,"line":1243},84,[112,1245,1246],{},"        \"fruit_classifier.onnx\",    # where to save the model (can be a file or file-like object)\n",[112,1248,1250],{"class":114,"line":1249},85,[112,1251,1252],{},"        export_params=True,  # store the trained parameter weights inside the model file\n",[112,1254,1256],{"class":114,"line":1255},86,[112,1257,1258],{},"        opset_version=16,    # the ONNX version to export the model to\n",[112,1260,1262],{"class":114,"line":1261},87,[112,1263,1264],{},"        do_constant_folding=True,  # whether to execute constant folding for optimization\n",[112,1266,1268],{"class":114,"line":1267},88,[112,1269,1270],{},"        input_names=['input'],   # the model's input names\n",[112,1272,1274],{"class":114,"line":1273},89,[112,1275,1276],{},"        output_names=['output'],  # the model's output names\n",[112,1278,1280],{"class":114,"line":1279},90,[112,1281,1282],{},"        dynamic_axes={\"input\": {0: \"batch_size\"}, \"output\": {0: \"batch_size\"}}\n",[112,1284,1286],{"class":114,"line":1285},91,[112,1287,1288],{},"    )\n",[112,1290,1292],{"class":114,"line":1291},92,[112,1293,811],{"emptyLinePlaceholder":810},[112,1295,1297],{"class":114,"line":1296},93,[112,1298,1299],{},"    print(\"Model exported to fruit_classifier.onnx\")\n",[112,1301,1303],{"class":114,"line":1302},94,[112,1304,811],{"emptyLinePlaceholder":810},[112,1306,1308],{"class":114,"line":1307},95,[112,1309,811],{"emptyLinePlaceholder":810},[112,1311,1313],{"class":114,"line":1312},96,[112,1314,1315],{},"# --- Test with ONNX Runtime ---\n",[112,1317,1319],{"class":114,"line":1318},97,[112,1320,1321],{},"def test_onnx():\n",[112,1323,1325],{"class":114,"line":1324},98,[112,1326,1327],{},"    ort_session = ort.InferenceSession(\"fruit_classifier.onnx\")\n",[112,1329,1331],{"class":114,"line":1330},99,[112,1332,811],{"emptyLinePlaceholder":810},[112,1334,1336],{"class":114,"line":1335},100,[112,1337,1338],{},"    def to_numpy(tensor):\n",[112,1340,1342],{"class":114,"line":1341},101,[112,1343,1344],{},"        return tensor.detach().cpu().numpy() if tensor.requires_grad else tensor.cpu().numpy()\n",[112,1346,1348],{"class":114,"line":1347},102,[112,1349,811],{"emptyLinePlaceholder":810},[112,1351,1353],{"class":114,"line":1352},103,[112,1354,1355],{},"    inputs, _ = next(iter(test_loader))\n",[112,1357,1359],{"class":114,"line":1358},104,[112,1360,1361],{},"    ort_inputs = {\"input\": to_numpy(inputs[:1])}\n",[112,1363,1365],{"class":114,"line":1364},105,[112,1366,1367],{},"    ort_outs = ort_session.run(None, ort_inputs)\n",[112,1369,1371],{"class":114,"line":1370},106,[112,1372,811],{"emptyLinePlaceholder":810},[112,1374,1376],{"class":114,"line":1375},107,[112,1377,1378],{},"    pred_class = np.argmax(ort_outs[0])\n",[112,1380,1382],{"class":114,"line":1381},108,[112,1383,1384],{},"    print(\"ONNX Prediction:\", train_dataset.classes[pred_class])\n",[112,1386,1388],{"class":114,"line":1387},109,[112,1389,811],{"emptyLinePlaceholder":810},[112,1391,1393],{"class":114,"line":1392},110,[112,1394,811],{"emptyLinePlaceholder":810},[112,1396,1398],{"class":114,"line":1397},111,[112,1399,1400],{},"# --- Main ---\n",[112,1402,1404],{"class":114,"line":1403},112,[112,1405,1406],{},"if __name__ == \"__main__\":\n",[112,1408,1410],{"class":114,"line":1409},113,[112,1411,1412],{},"    train(num_epochs=5)\n",[112,1414,1416],{"class":114,"line":1415},114,[112,1417,1418],{},"    val_acc = evaluate(val_loader)\n",[112,1420,1422],{"class":114,"line":1421},115,[112,1423,1424],{},"    print(f\"Validation Accuracy: {val_acc:.2%}\")\n",[112,1426,1428],{"class":114,"line":1427},116,[112,1429,811],{"emptyLinePlaceholder":810},[112,1431,1433],{"class":114,"line":1432},117,[112,1434,1435],{},"    export_model()\n",[112,1437,1439],{"class":114,"line":1438},118,[112,1440,1441],{},"    test_onnx()\n",[69,1443,1445],{"id":1444},"run-the-fruit_classifierpy-python-script","Run the fruit_classifier.py Python script",[12,1447,1448],{},"Now you can run the script that will train the model, export it to ONNX format, and run a quick classification test using the ONNX Runtime:",[103,1450,1452],{"className":105,"code":1451,"language":107,"meta":108,"style":108},"python fruit_classifier.py\n",[77,1453,1454],{"__ignoreMap":108},[112,1455,1456,1458],{"class":114,"line":115},[112,1457,798],{"class":118},[112,1459,790],{"class":121},[12,1461,1462],{},"What you should see:",[103,1464,1468],{"className":1465,"code":1466,"language":1467,"meta":108,"style":108},"language-log shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","Class mapping: {'apple': 0, 'kiwi': 1, 'mango': 2}\nEpoch 1, Loss: 0.7811\nEpoch 2, Loss: 0.1383\nEpoch 3, Loss: 0.0671\nEpoch 4, Loss: 0.0399\nEpoch 5, Loss: 0.0184\nValidation Accuracy: 80.95%\nModel exported to fruit_classifier.onnx\nONNX Prediction: apple\n","log",[77,1469,1470,1475,1480,1485,1490,1495,1500,1505,1510],{"__ignoreMap":108},[112,1471,1472],{"class":114,"line":115},[112,1473,1474],{},"Class mapping: {'apple': 0, 'kiwi': 1, 'mango': 2}\n",[112,1476,1477],{"class":114,"line":125},[112,1478,1479],{},"Epoch 1, Loss: 0.7811\n",[112,1481,1482],{"class":114,"line":342},[112,1483,1484],{},"Epoch 2, Loss: 0.1383\n",[112,1486,1487],{"class":114,"line":350},[112,1488,1489],{},"Epoch 3, Loss: 0.0671\n",[112,1491,1492],{"class":114,"line":357},[112,1493,1494],{},"Epoch 4, Loss: 0.0399\n",[112,1496,1497],{"class":114,"line":364},[112,1498,1499],{},"Epoch 5, Loss: 0.0184\n",[112,1501,1502],{"class":114,"line":453},[112,1503,1504],{},"Validation Accuracy: 80.95%\n",[112,1506,1507],{"class":114,"line":459},[112,1508,1509],{},"Model exported to fruit_classifier.onnx\n",[112,1511,1512],{"class":114,"line":465},[112,1513,1514],{},"ONNX Prediction: apple\n",[12,1516,1517,1518,1521],{},"If you changed the data set from fruit to your use own images and classifications, it will output a different ",[77,1519,1520],{},"Class mapping"," that you will need to use in the Node-RED flow on the next step - make a note of this.",[16,1523,1525],{"id":1524},"using-your-newly-generated-onnx-model-with-the-flowfuse-onnx-node","Using your newly generated ONNX Model with the FlowFuse ONNX Node",[49,1527,1528,1537,1582,1585,1592,1599,1602],{},[52,1529,1530,1531],{},"Import the finished ONNX model into a location in the file system where your Node-RED instance can access it\n",[1532,1533,1534],"ul",{},[52,1535,1536],{},"In FlowFuse cloud you can do this via the Assets tab",[52,1538,1539,1540],{},"Import the demo flow\n",[1532,1541,1542,1545,1556,1564,1571,1577],{},[52,1543,1544],{},"Open your Node-RED editor",[52,1546,1547,1548,1551,1552,1555],{},"Press ",[77,1549,1550],{},"CTRL-I"," or select ",[77,1553,1554],{},"Import"," from the menu to open the Import Dialog",[52,1557,1558,1559,1563],{},"Select the ",[1560,1561,1562],"strong",{},"Examples"," tab",[52,1565,1566,1567,1570],{},"Click the ",[1560,1568,1569],{},"@FlowFuse\u002Fnr-ai-nodes"," entry",[52,1572,1573,1574],{},"Click the demo named ",[1560,1575,1576],{},"advanced-custom-model",[52,1578,1566,1579,1581],{},[1560,1580,1554],{}," Button",[52,1583,1584],{},"Double click the ONNX node to open the configuration dialog",[52,1586,1587,1588,1591],{},"Enter the path to your ONNX model in the ",[1560,1589,1590],{},"Path"," field",[52,1593,1594,1595,1598],{},"If necessary, update the classifications (labels) in the Function node named ",[1560,1596,1597],{},"load labels"," as noted in the previous section",[52,1600,1601],{},"Deploy the flow",[52,1603,1604],{},"Click the inject button on the left of the flow to trigger an inference",[12,1606,1607,1612],{},[1608,1609],"img",{"alt":1610,"dataZoomable":108,"src":1611},"Image showing how to import demo flow","\u002Fblog\u002F2025\u002F10\u002Fimages\u002Fcustom-onnx-mode--import-flow.png",[268,1613,1610],{},[12,1615,1616,1620],{},[1608,1617],{"alt":1618,"dataZoomable":108,"src":1619},"Image showing inference in action","\u002Fblog\u002F2025\u002F10\u002Fimages\u002Fcustom-onnx-mode--in-action.png",[268,1621,1618],{},[16,1623,1625],{"id":1624},"supplementary-notes","Supplementary Notes",[69,1627,1629],{"id":1628},"clean-up","Clean up",[12,1631,1632],{},"To deactivate the virtual environment when you're done, simply run:",[103,1634,1636],{"className":105,"code":1635,"language":107,"meta":108,"style":108},"pyenv deactivate\n",[77,1637,1638],{"__ignoreMap":108},[112,1639,1640,1642],{"class":114,"line":115},[112,1641,79],{"class":118},[112,1643,1644],{"class":121}," deactivate\n",[12,1646,1647,1648,1651],{},"You can remove the ",[77,1649,1650],{},"__pycache__"," and other temporary files if they were created:",[103,1653,1655],{"className":105,"code":1654,"language":107,"meta":108,"style":108},"rm -rf __pycache__\nrm -rf runs\u002F logs\u002F checkpoints\u002F\n",[77,1656,1657,1668],{"__ignoreMap":108},[112,1658,1659,1662,1665],{"class":114,"line":115},[112,1660,1661],{"class":118},"rm",[112,1663,1664],{"class":121}," -rf",[112,1666,1667],{"class":121}," __pycache__\n",[112,1669,1670,1672,1674,1677,1680],{"class":114,"line":125},[112,1671,1661],{"class":118},[112,1673,1664],{"class":121},[112,1675,1676],{"class":121}," runs\u002F",[112,1678,1679],{"class":121}," logs\u002F",[112,1681,1682],{"class":121}," checkpoints\u002F\n",[12,1684,1685],{},"If you want to completely remove the virtual environment, you can do so with:",[103,1687,1689],{"className":105,"code":1688,"language":107,"meta":108,"style":108},"pyenv uninstall venv_py3_10_14_pytorch\n",[77,1690,1691],{"__ignoreMap":108},[112,1692,1693,1695,1698],{"class":114,"line":115},[112,1694,79],{"class":118},[112,1696,1697],{"class":121}," uninstall",[112,1699,247],{"class":121},[1701,1702,1703],"style",{},"html pre.shiki code .sBMFI, html code.shiki .sBMFI{--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B}html pre.shiki code .sfazB, html code.shiki .sfazB{--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D}html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html pre.shiki code .sbssI, html code.shiki .sbssI{--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C}html pre.shiki code .s2Zo4, html code.shiki .s2Zo4{--shiki-light:#6182B8;--shiki-default:#82AAFF;--shiki-dark:#82AAFF}html pre.shiki code .sHwdD, html code.shiki .sHwdD{--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic}html pre.shiki code .sMK4o, html code.shiki .sMK4o{--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF}",{"title":108,"searchDepth":350,"depth":350,"links":1705},[1706,1707,1708,1709,1716,1717,1720,1721],{"id":18,"depth":342,"text":19},{"id":36,"depth":342,"text":37},{"id":43,"depth":342,"text":44},{"id":66,"depth":342,"text":67,"children":1710},[1711,1715],{"id":71,"depth":350,"text":72,"children":1712},[1713,1714],{"id":90,"depth":357,"text":91},{"id":144,"depth":357,"text":145},{"id":208,"depth":350,"text":209},{"id":400,"depth":342,"text":401},{"id":762,"depth":342,"text":763,"children":1718},[1719],{"id":1444,"depth":350,"text":1445},{"id":1524,"depth":342,"text":1525},{"id":1624,"depth":342,"text":1625,"children":1722},[1723],{"id":1628,"depth":350,"text":1629},null,"2025-10-10","Learn how to train and export an image classifier model, and integrate it with FlowFuse AI Nodes for low-code inference in Node-RED.","md","\u002Fblog\u002F2025\u002F10\u002Fimages\u002Fflowfuse-ai-nodes.png",{"keywords":1730,"excerpt":1731},"FlowFuse, Node-RED, industrial automation, low-code platform, data analysis, vision systems, inference, AI, object detection, image classification, depth estimation, transfer learning, PyTorch, ONNX, ResNet",{"type":9,"value":1732},[1733],[12,1734,14],{},"\u002Fblog\u002F2025\u002F10\u002Fcustom-onnx-model",{"title":5,"description":1726},{"loc":1735},"blog\u002F2025\u002F10\u002Fcustom-onnx-model","Using ONNX runtime to run inference in Node-RED",[1741,1742],"flowfuse","ai","mqkLmFA5Ig239jVN4rDqw553ppawFn_ENtKvNpxR9_M",{"id":1745,"extension":1746,"meta":1747,"sections":1748,"stem":2137,"__hash__":2138},"featureCatalog\u002Ffeature-catalog.yml","yml",{},[1749,1800,1901,1963,2040,2119],{"id":1750,"title":1751,"features":1752},"ai-automation","AI & Automation",[1753,1763,1773,1783,1789,1795],{"id":1754,"title":1755,"description":1756,"docsLink":1757,"changelog":1758,"tiers":1762},"flowfuse-expert-ai","FlowFuse Expert AI","Build industrial apps with agents, and query the state of the factory with an agent. Adapt your current hardware and machines so agentic work can be done against them, without ripping and replacing what's already on the plant floor.","\u002Fdocs\u002Fuser\u002Fexpert\u002F",[1759],{"url":1760,"release":1761},"\u002Fchangelog\u002F2026\u002F02\u002Fff-expert-update-banner\u002F","2.28",{"edge":810,"hub":810,"fleet":810},{"id":1764,"title":1765,"description":1766,"docsLink":1767,"changelog":1768,"subfeature":810,"showOnPricing":1771,"tiers":1772},"flowfuse-expert-support-mode","Support Mode","Chat-based assistance for FlowFuse and Node-RED, including Node-RED instance management through natural language.","\u002Fdocs\u002Fuser\u002Fexpert\u002Fchat\u002F#support-mode",[1769],{"url":1770,"release":1761},"\u002Fchangelog\u002F2026\u002F02\u002Fff-expert-debug-log-context\u002F",false,{"edge":810,"hub":810,"fleet":810},{"id":1774,"title":1775,"description":1776,"docsLink":1777,"changelog":1778,"subfeature":810,"showOnPricing":1771,"tiers":1782},"flowfuse-expert-application-building","Application Building","Describe what you want to build and FlowFuse Expert assembles it on your workspace, adding tabs, wiring nodes, and configuring properties.","\u002Fdocs\u002Fuser\u002Fexpert\u002Fchat\u002F",[1779],{"url":1780,"release":1781},"\u002Fchangelog\u002F2026\u002F05\u002Fexpert-application-building\u002F","2.30",{"edge":810,"hub":810,"fleet":810},{"id":1784,"title":1785,"description":1786,"docsLink":1787,"subfeature":810,"beta":810,"showOnPricing":1771,"tiers":1788},"flowfuse-expert-insights-mode","Insights Mode","Connects FlowFuse Expert to MCP servers in your Node-RED instances, enabling real-time data queries and actions through a single chat interface.","\u002Fdocs\u002Fuser\u002Fexpert\u002Fchat\u002F#insights-mode",{"edge":810,"hub":810,"fleet":810},{"id":1790,"title":1791,"description":1792,"docsLink":1793,"tiers":1794},"mcp-servers","Agentic Operations","Expose your Node-RED flows as tools an AI agent can call directly, so agents can query the state of the factory or trigger actions without custom integration work.","\u002Fnode-red\u002Fflowfuse\u002Fmcp\u002F",{"edge":810,"hub":810,"fleet":810},{"id":1796,"title":1797,"description":1798,"tiers":1799},"onnx-integration","ONNX Integration","Run trained machine learning models directly in your flows, including on edge hardware, without sending data out to an external inference service.",{"edge":810,"hub":810,"fleet":810},{"id":1801,"title":1802,"features":1803},"build","Build",[1804,1810,1816,1826,1832,1838,1842,1848,1854,1862,1868,1872,1876,1885,1893],{"id":1805,"title":1806,"description":1807,"docsLink":1808,"tiers":1809},"edge-development","Edge Development","Develop and test Node-RED flows directly on edge devices with a remote editor proxy.","\u002Fdocs\u002Fdevice-agent\u002Fquickstart\u002F",{"edge":810,"hub":1771,"fleet":810},{"id":1811,"title":1812,"description":1813,"docsLink":1814,"tiers":1815},"private-npm-registry","Custom Node-RED Nodes","Create and manage your own private npm registry for Node-RED nodes, so you can share custom nodes across your team and devices without publishing them publicly.","\u002Fdocs\u002Fuser\u002Fcustom-npm-packages\u002F",{"edge":810,"hub":810,"fleet":810},{"id":1817,"title":1818,"description":1819,"docsLink":1820,"changelog":1821,"tiers":1825},"flowfuse-tables","FlowFuse Tables","A managed PostgreSQL database for every application, so you can store and query structured data without standing up and maintaining your own database.","\u002Fdocs\u002Fuser\u002Fff-tables\u002F",[1822],{"url":1823,"release":1824},"\u002Fchangelog\u002F2026\u002F07\u002Fexpert-tables-automation\u002F","2.33",{"edge":810,"hub":810,"fleet":810},{"id":1827,"title":1828,"description":1829,"docsLink":1830,"tiers":1831},"persistent-files","File Storage","Store and retrieve files from your Node-RED flows, with automatic replication and backup across your devices and hosted instances.","\u002Fdocs\u002Finstall\u002Ffile-storage\u002F",{"edge":810,"hub":810,"fleet":810},{"id":1833,"title":1834,"description":1835,"docsLink":1836,"showOnPricing":1771,"tiers":1837},"persistent-context","Persistent Context","In-memory values defined in a Node-RED flow persist across project restarts and upgrades.","\u002Fdocs\u002Fuser\u002Fpersistent-context\u002F",{"edge":810,"hub":810,"fleet":810},{"id":1839,"title":1840,"showOnPricing":1771,"tiers":1841},"static-assets","Static Assets",{"edge":810,"hub":810,"fleet":810},{"id":1843,"title":1844,"description":1845,"docsLink":1846,"tiers":1847},"team-library","Team Library","Set up standard nodes and flows that can be shared with all team members across your organisation.","\u002Fdocs\u002Fuser\u002Fshared-library\u002F",{"edge":810,"hub":810,"fleet":810},{"id":1849,"title":1850,"description":1851,"docsLink":1852,"tiers":1853},"personalised-multi-user-dashboards","Personalised Multi-User Dashboards","Build applications that provide unique data to each logged-in user using personalised multi-user dashboards.","https:\u002F\u002Fdashboard.flowfuse.com\u002Fuser\u002Fmulti-tenancy.html",{"edge":810,"hub":810,"fleet":810},{"id":1855,"title":1856,"description":1857,"changelog":1858,"subfeature":810,"showOnPricing":1771,"tiers":1861},"dashboards-view","Dashboards View","Browse and open every dashboard across your team from a dedicated Dashboards view, at both team and application level, without leaving FlowFuse.",[1859],{"url":1860,"release":1824},"\u002Fchangelog\u002F2026\u002F07\u002Fteam-and-application-dashboards\u002F",{"edge":810,"hub":810,"fleet":810},{"id":1863,"title":1864,"description":1865,"docsLink":1866,"tiers":1867},"blueprints-converge","Blueprints","Ready-made starting points for your apps, from cross-team Converge templates to OT and IT specific blueprints.","\u002Fdocs\u002Fuser\u002Fconcepts\u002F#blueprint",{"edge":810,"hub":810,"fleet":810},{"id":1869,"title":1870,"subfeature":810,"showOnPricing":1771,"tiers":1871},"blueprints-ot-apps","Blueprints - OT APPS",{"edge":810,"hub":1771,"fleet":810},{"id":1873,"title":1874,"subfeature":810,"showOnPricing":1771,"tiers":1875},"blueprints-it-apps","Blueprints - IT APPS",{"edge":1771,"hub":810,"fleet":1771},{"id":1877,"title":1878,"description":1879,"changelog":1880,"showOnPricing":1771,"tiers":1884},"immersive-editor-snapshots","Snapshot Details in Immersive Editor","View and manage snapshot details directly inside the immersive editor without leaving your editing session.",[1881],{"url":1882,"release":1883},"\u002Fchangelog\u002F2026\u002F03\u002Fsnapshot-detail-modal-immersive-editor\u002F","2.29",{"edge":810,"hub":810,"fleet":810},{"id":1886,"title":1887,"description":1888,"changelog":1889,"showOnPricing":1771,"tiers":1892},"immersive-editor-drawer","Customisable Immersive Editor Drawer","Pin, move, resize, or full-screen the immersive editor drawer. Your preferences are remembered between sessions.",[1890],{"url":1891,"release":1781},"\u002Fchangelog\u002F2026\u002F04\u002Fimmersive-editor-drawer\u002F",{"edge":810,"hub":810,"fleet":810},{"id":1894,"title":1895,"description":1896,"changelog":1897,"showOnPricing":1771,"tiers":1900},"embedded-editor-tab-title","Embedded Editor Browser Tab Title","The browser tab title updates to reflect the active Node-RED canvas tab when working in the embedded editor.",[1898],{"url":1899,"release":1883},"\u002Fchangelog\u002F2026\u002F03\u002Fembedded-editor-tab-title\u002F",{"edge":810,"hub":810,"fleet":810},{"id":1902,"title":1903,"features":1904},"deploy","Deploy",[1905,1911,1920,1926,1932,1938,1944,1950,1955],{"id":1906,"title":1907,"description":1908,"docsLink":1909,"tiers":1910},"hosted-instances","Cloud Instances","Run Node-RED instances managed and hosted by FlowFuse.","\u002Fdocs\u002Fuser\u002Fintroduction\u002F#creating-a-node-red-instance",{"edge":810,"hub":810,"fleet":810},{"id":1912,"title":1913,"description":1914,"docsLink":1915,"changelog":1916,"tiers":1919},"edge-devices","Edge Instances","Deploy and mange your Node-RED instances on edge PLCs and gateways, with full visibility and control from the cloud.","\u002Fdocs\u002Fdevice-agent\u002Fintroduction\u002F",[1917],{"url":1918,"release":1761},"\u002Fchangelog\u002F2026\u002F02\u002Fdevice-agent-nodejs-options\u002F",{"edge":810,"hub":1771,"fleet":810},{"id":1921,"title":1922,"description":1923,"docsLink":1924,"tiers":1925},"custom-hostnames","Custom Hostnames","Access your Node-RED application via your own domain name.","\u002Fdocs\u002Fuser\u002Fcustom-hostnames\u002F",{"edge":1771,"hub":810,"fleet":1771},{"id":1927,"title":1928,"description":1929,"docsLink":1930,"tiers":1931},"mqtt-broker","MQTT Broker","Manage and create MQTT clients to transport data for efficient messaging and communication within your applications.","\u002Fdocs\u002Fuser\u002Fteambroker\u002F",{"edge":810,"hub":1771,"fleet":810},{"id":1933,"title":1934,"description":1935,"docsLink":1936,"showOnPricing":1771,"tiers":1937},"project-nodes","Project Nodes aka seamless project comms","FlowFuse Project Nodes enable the passing of data and messages between your Node-RED projects.","\u002Fdocs\u002Fuser\u002Fprojectnodes\u002F",{"edge":810,"hub":810,"fleet":810},{"id":1939,"title":1940,"description":1941,"docsLink":1942,"tiers":1943},"devops-pipelines","DevOps Pipelines","Set up different environments for development, testing, and production Node-RED instances to support a full software delivery lifecycle.","\u002Fdocs\u002Fuser\u002Fdevops-pipelines\u002F",{"edge":810,"hub":810,"fleet":810},{"id":1945,"title":1946,"description":1947,"docsLink":1948,"tiers":1949},"git-integration","Git Integration","Back up your flows to a remote Git repository through a DevOps Pipeline. Supports GitHub and Azure DevOps repositories.","\u002Fdocs\u002Fuser\u002Fdevops-pipelines\u002F#git-repository-stage",{"edge":1771,"hub":810,"fleet":1771},{"id":1951,"title":1952,"description":1953,"docsLink":1948,"subfeature":810,"showOnPricing":1771,"tiers":1954},"git-integration-github","GitHub","Push and pull snapshots to GitHub repositories through DevOps Pipeline Git Stages.",{"edge":1771,"hub":810,"fleet":1771},{"id":1956,"title":1957,"description":1958,"docsLink":1948,"changelog":1959,"subfeature":810,"showOnPricing":1771,"tiers":1962},"git-integration-azure","Azure DevOps","Push and pull snapshots to Azure DevOps repositories through DevOps Pipeline Git Stages.",[1960],{"url":1961,"release":1883},"\u002Fchangelog\u002F2026\u002F03\u002Fazure-dev-ops-gitops\u002F",{"edge":1771,"hub":810,"fleet":1771},{"id":1964,"title":1965,"features":1966},"operate-maintain","Operate & Maintain",[1967,1973,1979,1984,1992,1996,2000,2005,2011,2017,2022,2028,2032,2036],{"id":1968,"title":1969,"description":1970,"docsLink":1971,"tiers":1972},"snapshots","Snapshots & Version History","Automatic snapshots on remote devices and hosted instances, plus a full version history timeline so you can roll back to any prior state.","\u002Fdocs\u002Fuser\u002Fsnapshots\u002F",{"edge":810,"hub":810,"fleet":810},{"id":1974,"title":1975,"description":1976,"docsLink":1977,"subfeature":810,"showOnPricing":1771,"tiers":1978},"auto-snapshot-remote","Auto Snapshot (Remote)","Automatically capture a snapshot every time a remote instance is deployed, so you always have a recoverable history of what was running on each device.","\u002Fdocs\u002Fuser\u002Fsnapshots\u002F#auto-snapshots",{"edge":810,"hub":810,"fleet":810},{"id":1980,"title":1981,"description":1982,"docsLink":1977,"subfeature":810,"showOnPricing":1771,"tiers":1983},"auto-snapshot-hosted","Auto Snapshot (Hosted)","Automatically capture a snapshot every time a hosted instance is deployed, so you always have a recoverable history of what was running.",{"edge":810,"hub":810,"fleet":810},{"id":1985,"title":1986,"description":1987,"changelog":1988,"subfeature":810,"showOnPricing":1771,"tiers":1991},"snapshot-comparison","Snapshot Comparison","Compare two snapshots side-by-side with a navigable diff view. Step through every changed, added, or deleted node and see property and code diffs.",[1989],{"url":1990,"release":1883},"\u002Fchangelog\u002F2026\u002F04\u002Fsnapshot-diff-viewer\u002F",{"edge":810,"hub":810,"fleet":810},{"id":1993,"title":1994,"subfeature":810,"showOnPricing":1771,"tiers":1995},"version-history-timeline","Version History Timeline",{"edge":810,"hub":810,"fleet":810},{"id":1997,"title":1998,"tiers":1999},"unlimited-workflow-executions","Unlimited Workflow Executions",{"edge":810,"hub":810,"fleet":810},{"id":2001,"title":2002,"description":2003,"tiers":2004},"device-fleet-updates","Device Fleet Updates","Connect to edge devices to quickly assess and update logic. Debug one device and roll out improvements to your fleet in minutes, securely without requiring full device access for your whole organisation.",{"edge":810,"hub":1771,"fleet":810},{"id":2006,"title":2007,"description":2008,"docsLink":2009,"tiers":2010},"device-group-management","Device Group Management","Logically group devices assigned to an application and integrate device groups into your DevOps Pipeline for coordinated fleet updates.","\u002Fdocs\u002Fuser\u002Fdevice-groups\u002F",{"edge":810,"hub":1771,"fleet":810},{"id":2012,"title":2013,"description":2014,"docsLink":2015,"tiers":2016},"high-availability","High Availability","Leverage horizontal scaling for reliable and scalable processing of your data through Node-RED.","\u002Fdocs\u002Fuser\u002Fhigh-availability\u002F",{"edge":1771,"hub":810,"fleet":1771},{"id":2018,"title":2019,"description":2020,"tiers":2021},"performance-monitoring","Performance Monitoring & Alerts","Track CPU, memory, and event loop performance across your instances and devices, with email alerts when something needs your attention.",{"edge":810,"hub":810,"fleet":810},{"id":2023,"title":2024,"description":2025,"docsLink":2026,"subfeature":810,"showOnPricing":1771,"tiers":2027},"instance-monitoring","Instance Monitoring","Enable alerts to be sent via email when your Node-RED instances encounter issues.","\u002Fdocs\u002Fuser\u002Finstance-settings\u002F#alerts",{"edge":810,"hub":810,"fleet":810},{"id":2029,"title":2030,"subfeature":810,"showOnPricing":1771,"tiers":2031},"email-alerts","Email Alerts",{"edge":810,"hub":810,"fleet":810},{"id":2033,"title":2034,"showOnPricing":1771,"tiers":2035},"api-debug-length-limit","API\u002FDebug Length Limit",{"edge":810,"hub":810,"fleet":810},{"id":2037,"title":2038,"tiers":2039},"protected-instances","Protected Instances",{"edge":1771,"hub":810,"fleet":1771},{"id":2041,"title":2042,"features":2043},"govern-secure","Govern and Secure",[2044,2053,2059,2065,2070,2076,2082,2088,2096,2102,2108,2114],{"id":2045,"title":2046,"description":2047,"docsLink":2048,"changelog":2049,"tiers":2052},"single-sign-on","Single Sign-On (SSO)","Configure FlowFuse to work with your own SSO provider, allowing users to access FlowFuse with a single set of login credentials.","\u002Fdocs\u002Fadmin\u002Fsso\u002F",[2050],{"url":2051,"release":1824},"\u002Fchangelog\u002F2026\u002F07\u002Fapplication-sso-groups\u002F",{"edge":810,"hub":810,"fleet":810},{"id":2054,"title":2055,"description":2056,"docsLink":2057,"tiers":2058},"two-factor-authentication","Two-Factor Authentication","Two-factor authentication adds an extra layer of security to your FlowFuse account.","\u002Fdocs\u002Fuser\u002Fuser-settings\u002F#two-factor-authentication",{"edge":810,"hub":810,"fleet":810},{"id":2060,"title":2061,"description":2062,"docsLink":2063,"tiers":2064},"certified-nodes-it","Certified Nodes - IT","IT certified node bundle includes: Redis, MQTT, HTTP Request, AI nodes (Gemini, Claude, ChatGPT, Ollama), MCP Server","\u002Fblog\u002F2025\u002F07\u002Fcertified-nodes-v2\u002F",{"edge":1771,"hub":810,"fleet":810},{"id":2066,"title":2067,"description":2068,"tiers":2069},"certified-nodes-ot","Certified OT Connections - OPC-UA, Modbus, etc.","OT certified node bundle includes: OPC-UA, Modbus TCP & RTU, RTSP, EtherNet\u002FIP, AI nodes (Gemini, Claude, ChatGPT, Ollama), MCP Server",{"edge":810,"hub":1771,"fleet":1771},{"id":2071,"title":2072,"description":2073,"docsLink":2074,"tiers":2075},"audit-log","Audit Log","Keep track of everything going on in your Node-RED instances and FlowFuse. Audit Logs provide details on what actions have taken place, when they happened, and who did them.","\u002Fdocs\u002Fuser\u002Flogs\u002F#audit-log",{"edge":810,"hub":810,"fleet":810},{"id":2077,"title":2078,"description":2079,"docsLink":2080,"tiers":2081},"role-based-access-control","Role-Based Access Control","Control who can do what at both the team and application level, from viewers to admins.","\u002Fdocs\u002Fuser\u002Frole-based-access-control\u002F",{"edge":810,"hub":810,"fleet":810},{"id":2083,"title":2084,"description":2085,"docsLink":2086,"subfeature":810,"showOnPricing":1771,"tiers":2087},"application-level-rbac","Application-Level RBAC","Fine-grained access control per application, allowing team members to have different permission levels across different applications without requiring separate teams.","\u002Fdocs\u002Fuser\u002Frole-based-access-control\u002F#application-level-rbac",{"edge":810,"hub":810,"fleet":810},{"id":2089,"title":2090,"description":2091,"changelog":2092,"subfeature":810,"showOnPricing":1771,"tiers":2095},"scoped-personal-access-tokens","Scoped Personal Access Tokens","Restrict a Personal Access Token to specific teams, limit it to read-only operations, or control whether it carries admin privileges.",[2093],{"url":2094,"release":1824},"\u002Fchangelog\u002F2026\u002F07\u002Fscoped-pats\u002F",{"edge":810,"hub":810,"fleet":810},{"id":2097,"title":2098,"description":2099,"docsLink":2100,"showOnPricing":1771,"tiers":2101},"team-members","Team Members","Invite multiple team members to collaborate on the same Node-RED flows.","\u002Fdocs\u002Fuser\u002Fteam\u002F#teams",{"edge":810,"hub":810,"fleet":810},{"id":2103,"title":2104,"description":2105,"docsLink":2106,"showOnPricing":1771,"tiers":2107},"endpoint-security","Endpoint Security","Secure HTTP endpoints for hosted Node-RED instances using FlowFuse credentials.","\u002Fdocs\u002Fuser\u002Finstance-settings\u002F#security",{"edge":810,"hub":810,"fleet":810},{"id":2109,"title":2110,"description":2111,"docsLink":2112,"tiers":2113},"baa-for-hipaa","BAA for HIPAA","FlowFuse can sign a Business Associate Agreement to ensure proper safeguarding of protected health information handled on your behalf.","\u002Fhandbook\u002Fsales\u002Fsubscription-agreement-1.5\u002F",{"edge":1771,"hub":810,"fleet":1771},{"id":2115,"title":2116,"description":2117,"tiers":2118},"sbom","Software Bill of Materials","A complete list of all software components used in your Node-RED instances and hosted applications, including version numbers and license information.",{"edge":1771,"hub":810,"fleet":1771},{"id":2120,"title":2121,"features":2122},"support","Support",[2123,2128,2132],{"id":2124,"title":2125,"docsLink":2126,"tiers":2127},"installation-support","Installation Support","\u002Fdocs\u002Finstall\u002Fintroduction\u002F#do-you-need-help-installation-service",{"edge":810,"hub":810,"fleet":810},{"id":2129,"title":2130,"showOnPricing":1771,"tiers":2131},"live-chat-support","Live Chat Support",{"edge":810,"hub":810,"fleet":810},{"id":2133,"title":2134,"docsLink":2135,"tiers":2136},"enterprise-support","Enterprise Support","\u002Fdocs\u002Fpremium-support\u002F",{"edge":810,"hub":810,"fleet":810},"feature-catalog","0AnkhTIPCECCwP9NmbTWP5HvRYx4FTSao4lG93-HaWM",[2140,2143,2146,2149,2152,2155,2157,2160,2163,2166,2169,2171,2174,2177,2180,2183,2186,2189,2192,2195,2198,2201,2204,2207,2210,2213,2216,2219,2222,2225,2228,2231,2234,2237,2240,2243,2246,2249,2252,2255,2258,2261,2264,2267,2270,2273,2276,2279,2282,2284,2287,2290,2293,2296,2299,2302,2305,2307,2310,2313,2316,2319,2322,2324,2327,2330,2333,2336,2339,2342,2345,2348,2351,2354,2356,2359,2362,2365,2368,2371,2374,2377,2380,2383,2386,2389,2392,2395,2398,2400,2403,2406,2409,2412,2415,2418,2421,2424,2427,2430,2433,2436,2439,2442,2445,2448,2451,2454,2456,2459,2462,2465,2468,2471,2474,2477,2479,2482,2485,2488,2491,2494,2497,2500,2503,2506,2509,2512,2515,2518,2521,2524,2527,2530,2533,2536,2539,2542,2545,2548,2551,2554,2557,2560,2563,2566,2569,2572,2575,2578,2581,2584,2587,2590,2593,2596,2599,2602,2605,2608,2611,2614,2617,2620,2623,2626,2629,2631,2634,2637,2640,2643,2646,2649,2652,2655,2658,2661,2664,2667,2670],{"path":2141,"title":2142},"\u002Fchangelog\u002F2023\u002F09\u002Fcustom-node-support","Custom Node Support",{"path":2144,"title":2145},"\u002Fchangelog\u002F2023\u002F09\u002Fdevops-actions","DevOps Pipeline with action selection",{"path":2147,"title":2148},"\u002Fchangelog\u002F2023\u002F09\u002Fintroduction-enterprise-tier","Introducing the Enterprise Tier",{"path":2150,"title":2151},"\u002Fchangelog\u002F2023\u002F09\u002Fpipeline-api","API Endpoint for DevOps Pipeline",{"path":2153,"title":2154},"\u002Fchangelog\u002F2023\u002F09\u002Fsnapshots-devices","Usability improvements to Device Management",{"path":2156,"title":1864},"\u002Fchangelog\u002F2023\u002F10\u002Fblueprints",{"path":2158,"title":2159},"\u002Fchangelog\u002F2023\u002F10\u002Fcertified-nodes","Certified Nodes",{"path":2161,"title":2162},"\u002Fchangelog\u002F2023\u002F10\u002Fdevice-snapshot-selection","Enhanced Snapshot Selection",{"path":2164,"title":2165},"\u002Fchangelog\u002F2023\u002F10\u002Fpath-bug-fix","Device Agent path bug fix",{"path":2167,"title":2168},"\u002Fchangelog\u002F2023\u002F10\u002Fresource-alerts","Resource Monitoring in Audit Log",{"path":2170,"title":2055},"\u002Fchangelog\u002F2023\u002F11\u002F2fa",{"path":2172,"title":2173},"\u002Fchangelog\u002F2023\u002F11\u002Fdefault-editor","Device Editor enabled by default",{"path":2175,"title":2176},"\u002Fchangelog\u002F2023\u002F11\u002Fdevices-in-pipelines","Devices in DevOps Pipelines",{"path":2178,"title":2179},"\u002Fchangelog\u002F2023\u002F11\u002Fproject-nodes-devices","Project Nodes for Devices",{"path":2181,"title":2182},"\u002Fchangelog\u002F2023\u002F12\u002Fbilling","No Credit Card required for billing",{"path":2184,"title":2185},"\u002Fchangelog\u002F2023\u002F12\u002Fblueprint-selection","Blueprint Selection Update",{"path":2187,"title":2188},"\u002Fchangelog\u002F2023\u002F12\u002Fdevice-groups","Device Groups",{"path":2190,"title":2191},"\u002Fchangelog\u002F2023\u002F12\u002Femail-alerting-node-red-crash","Email Alerts for Audit Log Events",{"path":2193,"title":2194},"\u002Fchangelog\u002F2023\u002F12\u002Fnode-red-updated","Node-RED 3.1.3 now available",{"path":2196,"title":2197},"\u002Fchangelog\u002F2024\u002F01\u002Fdevice-audit-log","Introducing the Device Auditlog Feature",{"path":2199,"title":2200},"\u002Fchangelog\u002F2024\u002F01\u002Fdevice-groups-snapshot","Device Groups - Automatic snapshot assignment",{"path":2202,"title":2203},"\u002Fchangelog\u002F2024\u002F01\u002Ffleet-mode","Renaming \"Default Device Mode\" to \"Fleet Mode\"",{"path":2205,"title":2206},"\u002Fchangelog\u002F2024\u002F01\u002Fhelm-v2","Helm Chart v2.0",{"path":2208,"title":2209},"\u002Fchangelog\u002F2024\u002F01\u002Fnew-blueprints","New Blueprints added",{"path":2211,"title":2212},"\u002Fchangelog\u002F2024\u002F01\u002Fsecurity-updates","Security Updates",{"path":2214,"title":2215},"\u002Fchangelog\u002F2024\u002F01\u002Fsso-team-membership","Managing Team Membership via SSO",{"path":2217,"title":2218},"\u002Fchangelog\u002F2024\u002F01\u002Fstreamlined-device-assignment","Streamlined Device assignment",{"path":2220,"title":2221},"\u002Fchangelog\u002F2024\u002F02\u002Fdevice-auto-snapshot","Device Auto Snapshots",{"path":2223,"title":2224},"\u002Fchangelog\u002F2024\u002F02\u002Fdevice-instance-audit-logs","Device Instance Audit Logging",{"path":2226,"title":2227},"\u002Fchangelog\u002F2024\u002F02\u002Fdevice-onboarding-improvements","Device Onboarding Improvements",{"path":2229,"title":2230},"\u002Fchangelog\u002F2024\u002F02\u002Fdevice-pricing-change","Pricing change for Devices",{"path":2232,"title":2233},"\u002Fchangelog\u002F2024\u002F02\u002Finstance-auto-snapshots","Instance Auto Snapshots",{"path":2235,"title":2236},"\u002Fchangelog\u002F2024\u002F02\u002Fpostgresql-upgrade","PostgreSQL Version update",{"path":2238,"title":2239},"\u002Fchangelog\u002F2024\u002F03\u002Fbearer-token-authentication","Bearer Token Authentication for Node-RED Instances",{"path":2241,"title":2242},"\u002Fchangelog\u002F2024\u002F03\u002Finstance-protection-mode","Instance Protection Mode",{"path":2244,"title":2245},"\u002Fchangelog\u002F2024\u002F03\u002Flimits-debug-payload","Configure HTTP Payload and Debug Message size",{"path":2247,"title":2248},"\u002Fchangelog\u002F2024\u002F03\u002Frestart-devices-remotly","Remote Device Restart",{"path":2250,"title":2251},"\u002Fchangelog\u002F2024\u002F04\u002Fcustom-nodes-on-devices","Custom Nodes Support on Devices",{"path":2253,"title":2254},"\u002Fchangelog\u002F2024\u002F04\u002Fdevice-auto-snapshot","Direct Dashboard Access",{"path":2256,"title":2257},"\u002Fchangelog\u002F2024\u002F04\u002Fimproving-device-groups","Improving Device Groups",{"path":2259,"title":2260},"\u002Fchangelog\u002F2024\u002F04\u002Fpricing-change","Pricing change Enterprise & Teams Tier",{"path":2262,"title":2263},"\u002Fchangelog\u002F2024\u002F04\u002Ftougher-rate-limiting","Tougher Rate Limiting on Public Routes",{"path":2265,"title":2266},"\u002Fchangelog\u002F2024\u002F05\u002Finstance-healthcheck","Customizing instance health-check settings",{"path":2268,"title":2269},"\u002Fchangelog\u002F2024\u002F05\u002Flibrary-blueprints","Blueprints added to Library",{"path":2271,"title":2272},"\u002Fchangelog\u002F2024\u002F05\u002Flibrary-flowviewer","Team Library - Flow Viewer",{"path":2274,"title":2275},"\u002Fchangelog\u002F2024\u002F05\u002Fmanaging-node-red-version-on-devices","Managing Node-RED versions on Devices",{"path":2277,"title":2278},"\u002Fchangelog\u002F2024\u002F05\u002Fsnapshot-improvements","Snapshot Improvements",{"path":2280,"title":2281},"\u002Fchangelog\u002F2024\u002F05\u002Fsnapshot-improvements-pt3","Snapshot Upload",{"path":2283,"title":2281},"\u002Fchangelog\u002F2024\u002F05\u002Fsnapshot-upload",{"path":2285,"title":2286},"\u002Fchangelog\u002F2024\u002F06\u002Fdevice-agent-proxy-support","Running the Device Agent behind an HTTP proxy",{"path":2288,"title":2289},"\u002Fchangelog\u002F2024\u002F06\u002Flibrary-blueprints","Custom hostnames for your instances",{"path":2291,"title":2292},"\u002Fchangelog\u002F2024\u002F06\u002Fmultiline-env-vars","Multi-line Environment Variables",{"path":2294,"title":2295},"\u002Fchangelog\u002F2024\u002F06\u002Fsnapshot-flow-compare","Compare Snapshots flows",{"path":2297,"title":2298},"\u002Fchangelog\u002F2024\u002F07\u002Fapplications-search","Applications Search",{"path":2300,"title":2301},"\u002Fchangelog\u002F2024\u002F07\u002Fdevice-group-clear-snapshot","Device Groups Snapshots",{"path":2303,"title":2304},"\u002Fchangelog\u002F2024\u002F07\u002Fdevice-management-bulk-delete","Managing devices",{"path":2306,"title":2304},"\u002Fchangelog\u002F2024\u002F07\u002Fdevice-management-bulk-move",{"path":2308,"title":2309},"\u002Fchangelog\u002F2024\u002F07\u002Fedit-snapshots","Edit Snapshots",{"path":2311,"title":2312},"\u002Fchangelog\u002F2024\u002F07\u002Fflowfuse-assistant","The FlowFuse Expert",{"path":2314,"title":2315},"\u002Fchangelog\u002F2024\u002F07\u002Fflowfuse-assistant-json","FlowFuse Expert Writes JSON",{"path":2317,"title":2318},"\u002Fchangelog\u002F2024\u002F07\u002Fimmersive-editor","Immersive Editor Experience",{"path":2320,"title":2321},"\u002Fchangelog\u002F2024\u002F07\u002Fnotifications-inbox","Notifications Inbox",{"path":2323,"title":2321},"\u002Fchangelog\u002F2024\u002F07\u002Fnotifications-update",{"path":2325,"title":2326},"\u002Fchangelog\u002F2024\u002F07\u002Fpersistent-storage","Persistent Storage on FlowFuse Cloud",{"path":2328,"title":2329},"\u002Fchangelog\u002F2024\u002F07\u002Fsso","Single Sign On Updates",{"path":2331,"title":2332},"\u002Fchangelog\u002F2024\u002F08\u002Fbill-of-materials","Bill of Materials",{"path":2334,"title":2335},"\u002Fchangelog\u002F2024\u002F08\u002Fenterprise-license-update","Enforcing Enterprise Restrictions",{"path":2337,"title":2338},"\u002Fchangelog\u002F2024\u002F08\u002Fldap-sso-groups","LDAP Single Sign On Updates",{"path":2340,"title":2341},"\u002Fchangelog\u002F2024\u002F08\u002Fstatic-file-service-navigation-visibility","Static File Service Navigation and Visibility",{"path":2343,"title":2344},"\u002Fchangelog\u002F2024\u002F10\u002Fdevice-group-env-vars","Environment Variables for your Device Groups",{"path":2346,"title":2347},"\u002Fchangelog\u002F2024\u002F10\u002Fmqtt-service","MQTT Broker Service",{"path":2349,"title":2350},"\u002Fchangelog\u002F2024\u002F10\u002Fnotifications-bulk-actions","Managing Notifications",{"path":2352,"title":2353},"\u002Fchangelog\u002F2024\u002F10\u002Fsnapshot-download-upload-options","Snapshot Upload and Download Improvements",{"path":2355,"title":1994},"\u002Fchangelog\u002F2024\u002F10\u002Fversion-history-timeline",{"path":2357,"title":2358},"\u002Fchangelog\u002F2024\u002F11\u002Faudit-log-hierarchy","Audit logs show hierarchical events",{"path":2360,"title":2361},"\u002Fchangelog\u002F2024\u002F11\u002Fdevice-agent-release","Device Agent 3.0 released",{"path":2363,"title":2364},"\u002Fchangelog\u002F2024\u002F11\u002Fmqtt-topic-hierarchy","MQTT Topic Hierarchy view",{"path":2366,"title":2367},"\u002Fchangelog\u002F2024\u002F11\u002Fteam-search","Team-wide search",{"path":2369,"title":2370},"\u002Fchangelog\u002F2024\u002F12\u002Fdashboad-iframe","Allow Dashboards to be embedded in iFrames",{"path":2372,"title":2373},"\u002Fchangelog\u002F2024\u002F12\u002Fdevice-editor-cache","Device Editor Access Speed Up",{"path":2375,"title":2376},"\u002Fchangelog\u002F2024\u002F12\u002Fteam-bom-timeline","Team BOM and Pipeline Views",{"path":2378,"title":2379},"\u002Fchangelog\u002F2025\u002F01\u002Ffree-tier-onboarding","New Onboarding Tour for Free Tier Users",{"path":2381,"title":2382},"\u002Fchangelog\u002F2025\u002F01\u002Fhidden-env-vars","Hidden Environment Variables",{"path":2384,"title":2385},"\u002Fchangelog\u002F2025\u002F01\u002Fimproved-diagnostics","Improved Diagnostics",{"path":2387,"title":2388},"\u002Fchangelog\u002F2025\u002F01\u002Fteam-level-groups","Team level view of Groups",{"path":2390,"title":2391},"\u002Fchangelog\u002F2025\u002F02\u002Fadditional-device-version-history-events","New Remote Instances Version History Events",{"path":2393,"title":2394},"\u002Fchangelog\u002F2025\u002F02\u002Fbroker-error-feedback","Improved Broker Connection Feedback",{"path":2396,"title":2397},"\u002Fchangelog\u002F2025\u002F02\u002Fdevice-agent-updates","FlowFuse User Authentication on Remote Instances",{"path":2399,"title":1994},"\u002Fchangelog\u002F2025\u002F02\u002Fdevice-version-history-timeline",{"path":2401,"title":2402},"\u002Fchangelog\u002F2025\u002F02\u002Fexternal-brokers","External MQTT Brokers",{"path":2404,"title":2405},"\u002Fchangelog\u002F2025\u002F02\u002Fmqtt-schema-suggestions","MQTT Smart Schema Suggestions",{"path":2407,"title":2408},"\u002Fchangelog\u002F2025\u002F02\u002Fresend-and-extend-team-invitation-expiration","Re-send Team Invitations",{"path":2410,"title":2411},"\u002Fchangelog\u002F2025\u002F02\u002Fschema-docs","Personalized Schema Documentation",{"path":2413,"title":2414},"\u002Fchangelog\u002F2025\u002F02\u002Ftopic-hierarchy-search","Search & Filter for Topic Hierarchy List",{"path":2416,"title":2417},"\u002Fchangelog\u002F2025\u002F03\u002Fcontainer-tags","Changes to tags for flowfuse\u002Fnode-red",{"path":2419,"title":2420},"\u002Fchangelog\u002F2025\u002F03\u002Fdevice-groups","Multiple Device Groups in a pipeline",{"path":2422,"title":2423},"\u002Fchangelog\u002F2025\u002F03\u002Fdevice-local-login","Local Login for Remote Instances",{"path":2425,"title":2426},"\u002Fchangelog\u002F2025\u002F03\u002Ffree-tier","Free Tier now more accessible to all",{"path":2428,"title":2429},"\u002Fchangelog\u002F2025\u002F03\u002Fresource-notifications","Resource Alerts",{"path":2431,"title":2432},"\u002Fchangelog\u002F2025\u002F03\u002Fsnapshot-filter","Filtering Snapshots",{"path":2434,"title":2435},"\u002Fchangelog\u002F2025\u002F03\u002Fteam-npm-registry","NPM Package Hosting",{"path":2437,"title":2438},"\u002Fchangelog\u002F2025\u002F03\u002Ftopic-deletion","MQTT Topic Management",{"path":2440,"title":2441},"\u002Fchangelog\u002F2025\u002F04\u002Fdevice-provisioning","Remote Instance Provisioning",{"path":2443,"title":2444},"\u002Fchangelog\u002F2025\u002F04\u002Fgit-integration","Git Integration with Pipelines",{"path":2446,"title":2447},"\u002Fchangelog\u002F2025\u002F04\u002Finstance-log-browsing","Better Node-RED log handling",{"path":2449,"title":2450},"\u002Fchangelog\u002F2025\u002F05\u002Fimport-node-red-flows","Import Node-RED Flows During Remote Instance Setup",{"path":2452,"title":2453},"\u002Fchangelog\u002F2025\u002F06\u002Fflowfuse-assistant","FlowFuse Expert just got smarter",{"path":2455,"title":2453},"\u002Fchangelog\u002F2025\u002F06\u002Fflowfuse-assistant-2",{"path":2457,"title":2458},"\u002Fchangelog\u002F2025\u002F06\u002Fgit-integration","Pulling snapshots from Git with Pipelines",{"path":2460,"title":2461},"\u002Fchangelog\u002F2025\u002F06\u002Finstance-performance-memory","Memory Metrics in Instance Performance View",{"path":2463,"title":2464},"\u002Fchangelog\u002F2025\u002F06\u002Fnew-home-page","Introducing the New Home Page Experience",{"path":2466,"title":2467},"\u002Fchangelog\u002F2025\u002F06\u002Fteam-performance","Team Performance Feature",{"path":2469,"title":2470},"\u002Fchangelog\u002F2025\u002F06\u002Fteam-performance-view","Instance Performance View",{"path":2472,"title":2473},"\u002Fchangelog\u002F2025\u002F06\u002Fui-refresh","Navigation UI Refresh",{"path":2475,"title":2476},"\u002Fchangelog\u002F2025\u002F07\u002Fbrowse-node-red-flows","Browse for Node-RED Flows During Remote Instance Setup",{"path":2478,"title":1818},"\u002Fchangelog\u002F2025\u002F07\u002Fflowfuse-tables",{"path":2480,"title":2481},"\u002Fchangelog\u002F2025\u002F07\u002Fimport-blueprints","Import blueprints directly into your existing instances",{"path":2483,"title":2484},"\u002Fchangelog\u002F2025\u002F07\u002Fsimplified-applications-overview","Simplified Applications Page with Summary Tiles",{"path":2486,"title":2487},"\u002Fchangelog\u002F2025\u002F07\u002Fsmart-suggestions","Smart Suggestions",{"path":2489,"title":2490},"\u002Fchangelog\u002F2025\u002F07\u002Fteam-to-pro-plan-rename","Team Plan Renamed to Pro Plan",{"path":2492,"title":2493},"\u002Fchangelog\u002F2025\u002F08\u002Fai-generated-snapshot-descriptions-hosted","Generate snapshot descriptions with AI",{"path":2495,"title":2496},"\u002Fchangelog\u002F2025\u002F08\u002Fai-generated-snapshot-descriptions-remote","AI Snapshot Descriptions Now Work with Remote Instances",{"path":2498,"title":2499},"\u002Fchangelog\u002F2025\u002F08\u002Fdevice-performance","FlowFuse Remote Instance Performance Data",{"path":2501,"title":2502},"\u002Fchangelog\u002F2025\u002F08\u002Fdirect-sso","Direct SSO Login",{"path":2504,"title":2505},"\u002Fchangelog\u002F2025\u002F08\u002Fflowfuse-assistant","FlowFuse Expert documents your flows",{"path":2507,"title":2508},"\u002Fchangelog\u002F2025\u002F08\u002Fflowfuse-mqtt","FlowFuse MQTT",{"path":2510,"title":2511},"\u002Fchangelog\u002F2025\u002F08\u002Fhttp-cors","Configure HTTP CORS",{"path":2513,"title":2514},"\u002Fchangelog\u002F2025\u002F08\u002Fsubflow-export","Export SubFlow as Node-RED module",{"path":2516,"title":2517},"\u002Fchangelog\u002F2025\u002F08\u002Ftables-assistant","FlowFuse Tables with a little help from the Assistant",{"path":2519,"title":2520},"\u002Fchangelog\u002F2025\u002F09\u002Fexpose-saml-groups-to-dashboard","Allow SSO groups to be shared with the Node-RED Dashboard",{"path":2522,"title":2523},"\u002Fchangelog\u002F2025\u002F09\u002Finline-assist","FlowFuse Expert can help you write code",{"path":2525,"title":2526},"\u002Fchangelog\u002F2025\u002F09\u002Fretiring-flowforge-device-agent","No more @flowforge\u002Fflowforge-device-agent releases",{"path":2528,"title":2529},"\u002Fchangelog\u002F2025\u002F09\u002Frevised-instance-snapshot-ui","Streamlined Snapshot Management",{"path":2531,"title":2532},"\u002Fchangelog\u002F2025\u002F09\u002Fteam-broker-async-api","Capture Async API data from FlowFuse Team Broker",{"path":2534,"title":2535},"\u002Fchangelog\u002F2025\u002F10\u002Fapplication-level-rbac","Application-level access control for Enterprise teams",{"path":2537,"title":2538},"\u002Fchangelog\u002F2025\u002F10\u002Fbulk-device-group-assignment","Easier Access to Bulk Device Group Management",{"path":2540,"title":2541},"\u002Fchangelog\u002F2025\u002F10\u002Fduplicate-instances-across-applications","Duplicate Instances Across Different Applications",{"path":2543,"title":2544},"\u002Fchangelog\u002F2025\u002F10\u002Fimport-flows-on-instance-creation","Import flows during instance creation",{"path":2546,"title":2547},"\u002Fchangelog\u002F2025\u002F10\u002Fmcp-nodes","FlowFuse MCP Server Nodes",{"path":2549,"title":2550},"\u002Fchangelog\u002F2025\u002F10\u002Fonnx-nodes","FlowFuse AI Nodes",{"path":2552,"title":2553},"\u002Fchangelog\u002F2025\u002F10\u002Fsettings-page-device-group-management","Device Group Management from Settings Page",{"path":2555,"title":2556},"\u002Fchangelog\u002F2025\u002F11\u002Fff-expert-update","FlowFuse Expert Update",{"path":2558,"title":2559},"\u002Fchangelog\u002F2025\u002F11\u002Fminimum-nodejs-version","Node.js v20 Minimum Version Requirement",{"path":2561,"title":2562},"\u002Fchangelog\u002F2025\u002F11\u002Fsso-session","SSO control over Session life",{"path":2564,"title":2565},"\u002Fchangelog\u002F2025\u002F12\u002Fff-expert-mcp-insights","FlowFuse Expert: Now with MCP-Powered Insights",{"path":2567,"title":2568},"\u002Fchangelog\u002F2025\u002F12\u002Fscheduled-maintenance","Scheduled Maintenance Mode",{"path":2570,"title":2571},"\u002Fchangelog\u002F2026\u002F01\u002Fdevice-agent-containers","Device Agent Docker Containers updated",{"path":2573,"title":2574},"\u002Fchangelog\u002F2026\u002F01\u002Fff-expert-manage-palette","FlowFuse Expert: Enhanced Palette Integration",{"path":2576,"title":2577},"\u002Fchangelog\u002F2026\u002F01\u002Fff-expert-nr-actions","FlowFuse Expert: Integration with Node-RED",{"path":2579,"title":2580},"\u002Fchangelog\u002F2026\u002F01\u002Fff-expert-palette-queries","FlowFuse Expert: Palette Queries",{"path":2582,"title":2583},"\u002Fchangelog\u002F2026\u002F01\u002Fff-expert-select-flows","FlowFuse Expert: Ask about your flows",{"path":2585,"title":2586},"\u002Fchangelog\u002F2026\u002F01\u002Fmcp-rbacs","FlowFuse Expert: MCP-Powered Insights with RBACs",{"path":2588,"title":2589},"\u002Fchangelog\u002F2026\u002F01\u002Fmcp-security","FlowFuse Expert: MCP-Powered Insights",{"path":2591,"title":2592},"\u002Fchangelog\u002F2026\u002F02\u002Fdevice-agent-nodejs-options","Set Node.js Options for Remote Instances",{"path":2594,"title":2595},"\u002Fchangelog\u002F2026\u002F02\u002Fff-expert-debug-log-context","FlowFuse Expert: Helping you make sense of your debug log",{"path":2597,"title":2598},"\u002Fchangelog\u002F2026\u002F02\u002Fff-expert-update-banner","FlowFuse Expert: Never Miss an Update",{"path":2600,"title":2601},"\u002Fchangelog\u002F2026\u002F02\u002Fha-instance-rolling-restart","HA Hosted Instance Rolling Restart",{"path":2603,"title":2604},"\u002Fchangelog\u002F2026\u002F02\u002Fremote-instances-immersive-editor","Immersive Mode for Remote Instances",{"path":2606,"title":2607},"\u002Fchangelog\u002F2026\u002F02\u002Frestoring-snapshots-to-remote-instances","Restoring snapshots to developer-mode Remote Instances",{"path":2609,"title":2610},"\u002Fchangelog\u002F2026\u002F03\u002Fazure-dev-ops-gitops","Azure DevOps Pipeline support",{"path":2612,"title":2613},"\u002Fchangelog\u002F2026\u002F03\u002Fdeveloper-mode-in-immersive-editor","Developer Mode Now Accessible from the Immersive Editor",{"path":2615,"title":2616},"\u002Fchangelog\u002F2026\u002F03\u002Fembedded-editor-tab-title","Embedded Editor Now Shows Active Tab",{"path":2618,"title":2619},"\u002Fchangelog\u002F2026\u002F03\u002Fmarch-scheduled-maintenance","Updated: Upcoming Scheduled Server Maintenance on March 28th, 2026",{"path":2621,"title":2622},"\u002Fchangelog\u002F2026\u002F03\u002Fsnapshot-detail-modal-immersive-editor","View Snapshot Details in the Immersive Editor",{"path":2624,"title":2625},"\u002Fchangelog\u002F2026\u002F04\u002Fexpert-action-links","FlowFuse expert action links",{"path":2627,"title":2628},"\u002Fchangelog\u002F2026\u002F04\u002Fhosted-instance-url-env-var","Hosted Instances know their own URL",{"path":2630,"title":1887},"\u002Fchangelog\u002F2026\u002F04\u002Fimmersive-editor-drawer",{"path":2632,"title":2633},"\u002Fchangelog\u002F2026\u002F04\u002Fsnapshot-diff-viewer","Richer snapshot comparison view",{"path":2635,"title":2636},"\u002Fchangelog\u002F2026\u002F05\u002Fai-opt-out","AI Feature Opt-Out for Teams",{"path":2638,"title":2639},"\u002Fchangelog\u002F2026\u002F05\u002Fexpert-application-building","FlowFuse Expert Builds Your Application",{"path":2641,"title":2642},"\u002Fchangelog\u002F2026\u002F05\u002Fsingle-sso-provider","Single SSO provider for all users",{"path":2644,"title":2645},"\u002Fchangelog\u002F2026\u002F06\u002Fdark-mode","Dark Mode",{"path":2647,"title":2648},"\u002Fchangelog\u002F2026\u002F06\u002Fdevice-agent-v4-released","Device Agent v4 released",{"path":2650,"title":2651},"\u002Fchangelog\u002F2026\u002F06\u002Fgeneric-git-server-support","Connect Pipelines to Any Git Server",{"path":2653,"title":2654},"\u002Fchangelog\u002F2026\u002F06\u002Fjuly-scheduled-maintenance","Updated: Upcoming Scheduled Server Maintenance on July 11th, 2026",{"path":2656,"title":2657},"\u002Fchangelog\u002F2026\u002F07\u002Fapplication-sso-groups","Application Roles from SSO Groups",{"path":2659,"title":2660},"\u002Fchangelog\u002F2026\u002F07\u002Fdevice-agent-onboarding","Getting started with FlowFuse straight from the terminal",{"path":2662,"title":2663},"\u002Fchangelog\u002F2026\u002F07\u002Fexpert-enhancements","FlowFuse Expert Enhancements",{"path":2665,"title":2666},"\u002Fchangelog\u002F2026\u002F07\u002Fexpert-tables-automation","FlowFuse Expert Can Now Work With Your Tables",{"path":2668,"title":2669},"\u002Fchangelog\u002F2026\u002F07\u002Fscoped-pats","Team Scoped Personal Access Tokens",{"path":2671,"title":2672},"\u002Fchangelog\u002F2026\u002F07\u002Fteam-and-application-dashboards","A Dedicated Home for Your Dashboards",[],1786105896161]