{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "dora-rs specification",
"description": "The main configuration structure for defining a Dora dataflow. Dataflows are\nspecified through YAML files that describe the nodes, their connections, and\nexecution parameters.\n\n## Structure\n\nA dataflow consists of:\n- **Nodes**: The computational units that process data\n- **Communication**: Optional communication configuration\n- **Deployment**: Optional deployment configuration (unstable)\n- **Debug options**: Optional development and debugging settings (unstable)\n\n## Example\n\n```yaml\nnodes:\n - id: webcam\n operator:\n python: webcam.py\n inputs:\n tick: dora/timer/millis/100\n outputs:\n - image\n - id: plot\n operator:\n python: plot.py\n inputs:\n image: webcam/image\n```",
"type": "object",
"properties": {
"nodes": {
"description": "List of nodes in the dataflow\n\nThis is the most important field of the dataflow specification.\nEach node must be identified by a unique `id`:\n\n## Example\n\n```yaml\nnodes:\n - id: foo\n path: path/to/the/executable\n # ... (see below)\n - id: bar\n path: path/to/another/executable\n # ... (see below)\n```\n\nFor each node, you need to specify the `path` of the executable or script that Dora should run when starting the node.\nMost of the other node fields are optional, but you typically want to specify at least some `inputs` and/or `outputs`.",
"type": "array",
"items": {
"$ref": "#/$defs/Node"
}
}
},
"additionalProperties": true,
"required": [
"nodes"
],
"$defs": {
"CustomNode": {
"description": "Contains the input and output configuration of the node.",
"type": "object",
"properties": {
"args": {
"description": "Args for the executable.",
"type": [
"string",
"null"
]
},
"build": {
"type": [
"string",
"null"
]
},
"envs": {
"description": "Environment variables for the custom nodes\n\nDeprecated, use outer-level `env` field instead.",
"type": [
"object",
"null"
],
"additionalProperties": {
"$ref": "#/$defs/EnvValue"
}
},
"inputs": {
"description": "Inputs for the nodes as a map from input ID to `node_id/output_id`.\n\ne.g.\n\ninputs:\n\n example_input: example_node/example_output1",
"type": "object",
"additionalProperties": {
"$ref": "#/$defs/Input"
},
"default": {}
},
"outputs": {
"description": "List of output IDs.\n\ne.g.\n\noutputs:\n\n - output_1\n\n - output_2",
"type": "array",
"default": [],
"items": {
"$ref": "#/$defs/DataId"
},
"uniqueItems": true
},
"path": {
"description": "Path of the source code\n\nIf you want to use a specific `conda` environment.\nProvide the python path within the source.\n\nsource: /home/peter/miniconda3/bin/python\n\nargs: some_node.py\n\nSource can match any executable in PATH.",
"type": "string"
},
"restart_policy": {
"$ref": "#/$defs/RestartPolicy",
"default": "never"
},
"send_stdout_as": {
"description": "Send stdout and stderr to another node",
"type": [
"string",
"null"
]
},
"source": {
"$ref": "#/$defs/NodeSource"
}
},
"required": [
"path",
"source"
]
},
"DataId": {
"type": "string"
},
"Duration": {
"type": "object",
"properties": {
"nanos": {
"type": "integer",
"format": "uint32",
"minimum": 0
},
"secs": {
"type": "integer",
"format": "uint64",
"minimum": 0
}
},
"required": [
"secs",
"nanos"
]
},
"EnvValue": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "integer",
"format": "int64"
},
{
"type": "number",
"format": "double"
},
{
"type": "string"
}
]
},
"GitRepoRev": {
"oneOf": [
{
"type": "object",
"properties": {
"Branch": {
"type": "string"
}
},
"additionalProperties": true,
"required": [
"Branch"
]
},
{
"type": "object",
"properties": {
"Tag": {
"type": "string"
}
},
"additionalProperties": true,
"required": [
"Tag"
]
},
{
"type": "object",
"properties": {
"Rev": {
"type": "string"
}
},
"additionalProperties": true,
"required": [
"Rev"
]
}
]
},
"Input": {
"anyOf": [
{
"$ref": "#/$defs/InputMapping"
},
{
"type": "object",
"properties": {
"queue_size": {
"type": [
"integer",
"null"
],
"format": "uint",
"minimum": 0
},
"source": {
"$ref": "#/$defs/InputMapping"
}
},
"required": [
"source"
]
}
]
},
"InputMapping": {
"oneOf": [
{
"type": "object",
"properties": {
"Timer": {
"type": "object",
"properties": {
"interval": {
"$ref": "#/$defs/Duration"
}
},
"required": [
"interval"
]
}
},
"additionalProperties": true,
"required": [
"Timer"
]
},
{
"type": "object",
"properties": {
"User": {
"$ref": "#/$defs/UserInputMapping"
}
},
"additionalProperties": true,
"required": [
"User"
]
}
]
},
"Node": {
"title": "Dora Node Configuration",
"description": "A node represents a computational unit in a Dora dataflow. Each node runs as a\nseparate process and can communicate with other nodes through inputs and outputs.",
"type": "object",
"properties": {
"args": {
"description": "Command-line arguments passed to the executable.\n\nThe command-line arguments that should be passed to the executable/script specified in `path`.\nThe arguments should be separated by space.\nThis field is optional and defaults to an empty argument list.\n\n## Example\n```yaml\nnodes:\n - id: example\n path: example-node\n args: -v --some-flag foo\n```",
"type": [
"string",
"null"
]
},
"branch": {
"description": "Git branch to checkout after cloning.\n\nThe `branch` field is only allowed in combination with the [`git`](#git) field.\nIt specifies the branch that should be checked out after cloning.\nOnly one of `branch`, `tag`, or `rev` can be specified.\n\n## Example\n\n```yaml\nnodes:\n - id: rust-node\n git: https://github.com/dora-rs/dora.git\n branch: some-branch-name\n```",
"type": [
"string",
"null"
]
},
"build": {
"description": "Build commands executed during `dora build`. Each line runs separately.\n\nThe `build` key specifies the command that should be invoked for building the node.\nThe key expects a single- or multi-line string.\n\nEach line is run as a separate command.\nSpaces are used to separate arguments.\n\nNote that all the environment variables specified in the [`env`](Self::env) field are also\napplied to the build commands.\n\n## Special treatment of `pip`\n\nBuild lines that start with `pip` or `pip3` are treated in a special way:\nIf the `--uv` argument is passed to the `dora build` command, all `pip`/`pip3` commands are\nrun through the [`uv` package manager](https://docs.astral.sh/uv/).\n\n## Example\n\n```yaml\nnodes:\n- id: build-example\n build: cargo build -p receive_data --release\n path: target/release/receive_data\n- id: multi-line-example\n build: |\n pip install requirements.txt\n pip install -e some/local/package\n path: package\n```\n\nIn the above example, the `pip` commands will be replaced by `uv pip` when run through\n`dora build --uv`.",
"type": [
"string",
"null"
]
},
"custom": {
"description": "Legacy node configuration (deprecated).\n\nPlease use the top-level [`path`](Self::path), [`args`](Self::args), etc. fields instead.",
"anyOf": [
{
"$ref": "#/$defs/CustomNode"
},
{
"type": "null"
}
]
},
"description": {
"description": "Detailed description of the node's functionality.\n\n## Example\n\n```yaml\nnodes:\n - id: camera_node\n description: \"Captures video frames from webcam\"\n```",
"type": [
"string",
"null"
]
},
"env": {
"description": "Environment variables for node builds and execution.\n\nKey-value map of environment variables that should be set for both the\n[`build`](Self::build) operation and the node execution (i.e. when the node is spawned\nthrough [`path`](Self::path)).\n\nSupports strings, numbers, and booleans.\n\n## Example\n\n```yaml\nnodes:\n - id: example-node\n path: path/to/node\n env:\n DEBUG: true\n PORT: 8080\n API_KEY: \"secret-key\"\n```",
"type": [
"object",
"null"
],
"additionalProperties": {
"$ref": "#/$defs/EnvValue"
}
},
"git": {
"description": "Git repository URL for downloading nodes.\n\nThe `git` key allows downloading nodes (i.e. their source code) from git repositories.\nThis can be especially useful for distributed dataflows.\n\nWhen a `git` key is specified, `dora build` automatically clones the specified repository\n(or reuse an existing clone).\nThen it checks out the specified [`branch`](Self::branch), [`tag`](Self::tag), or\n[`rev`](Self::rev), or the default branch if none of them are specified.\nAfterwards it runs the [`build`](Self::build) command if specified.\n\nNote that the git clone directory is set as working directory for both the\n[`build`](Self::build) command and the specified [`path`](Self::path).\n\n## Example\n\n```yaml\nnodes:\n - id: rust-node\n git: https://github.com/dora-rs/dora.git\n build: cargo build -p rust-dataflow-example-node\n path: target/debug/rust-dataflow-example-node\n```\n\nIn the above example, `dora build` will first clone the specified `git` repository and then\nrun the specified `build` inside the local clone directory.\nWhen `dora run` or `dora start` is invoked, the working directory will be the git clone\ndirectory too. So a relative `path` will start from the clone directory.",
"type": [
"string",
"null"
]
},
"id": {
"description": "Unique node identifier. Must not contain `/` characters.\n\nNode IDs can be arbitrary strings with the following limitations:\n\n- They must not contain any `/` characters (slashes).\n- We do not recommend using whitespace characters (e.g. spaces) in IDs\n\nEach node must have an ID field.\n\n## Example\n\n```yaml\nnodes:\n - id: camera_node\n - id: some_other_node\n```",
"$ref": "#/$defs/NodeId"
},
"inputs": {
"description": "Input data connections from other nodes.\n\nDefines the inputs that this node is subscribing to.\n\nThe `inputs` field should be a key-value map of the following format:\n\n`input_id: source_node_id/source_node_output_id`\n\nThe components are defined as follows:\n\n - `input_id` is the local identifier that should be used for this input.\n\n This will map to the `id` field of\n [`Event::Input`](https://docs.rs/dora-node-api/latest/dora_node_api/enum.Event.html#variant.Input)\n events sent to the node event loop.\n - `source_node_id` should be the `id` field of the node that sends the output that we want\n to subscribe to\n - `source_node_output_id` should be the identifier of the output that that we want\n to subscribe to\n\n## Example\n\n```yaml\nnodes:\n - id: example-node\n outputs:\n - one\n - two\n - id: receiver\n inputs:\n my_input: example-node/two\n```",
"type": "object",
"additionalProperties": {
"$ref": "#/$defs/Input"
},
"default": {}
},
"name": {
"description": "Human-readable node name for documentation.\n\nThis optional field can be used to define a more descriptive name in addition to a short\n[`id`](Self::id).\n\n## Example\n\n```yaml\nnodes:\n - id: camera_node\n name: \"Camera Input Handler\"",
"type": [
"string",
"null"
]
},
"operator": {
"description": "Single operator configuration.\n\nThis is a convenience field for defining runtime nodes that contain only a single operator.\nThis field is an alternative to the [`operators`](Self::operators) field, which can be used\nif there is only a single operator defined for the runtime node.\n\n## Example\n\n```yaml\nnodes:\n - id: runtime-node\n operator:\n id: processor\n python: script.py\n outputs: [data]\n```",
"anyOf": [
{
"$ref": "#/$defs/SingleOperatorDefinition"
},
{
"type": "null"
}
]
},
"operators": {
"description": "Multiple operators running in a shared runtime process.\n\nOperators are an experimental, lightweight alternative to nodes.\nInstead of running as a separate process, operators are linked into a runtime process.\nThis allows running multiple operators to share a single address space (not supported for\nPython currently).\n\nOperators are defined as part of the node list, as children of a runtime node.\nA runtime node is a special node that specifies no [`path`](Self::path) field, but contains\nan `operators` field instead.\n\n## Example\n\n```yaml\nnodes:\n - id: runtime-node\n operators:\n - id: processor\n python: process.py\n```",
"anyOf": [
{
"$ref": "#/$defs/RuntimeNode"
},
{
"type": "null"
}
]
},
"outputs": {
"description": "Output data identifiers produced by this node.\n\nList of output identifiers that the node sends.\nMust contain all `output_id` values that the node uses when sending output, e.g. through the\n[`send_output`](https://docs.rs/dora-node-api/latest/dora_node_api/struct.DoraNode.html#method.send_output)\nfunction.\n\n## Example\n\n```yaml\nnodes:\n - id: example-node\n outputs:\n - processed_image\n - metadata\n```",
"type": "array",
"default": [],
"items": {
"$ref": "#/$defs/DataId"
},
"uniqueItems": true
},
"path": {
"description": "Path to executable or script that should be run.\n\nSpecifies the path of the executable or script that Dora should run when starting the\ndataflow.\nThis can point to a normal executable (e.g. when using a compiled language such as Rust) or\na Python script.\n\nDora will automatically append a `.exe` extension on Windows systems when the specified\nfile name has no extension.\n\n## Example\n\n```yaml\nnodes:\n - id: rust-example\n path: target/release/rust-node\n - id: python-example\n path: ./receive_data.py\n```\n\n## URL as Path\n\nThe `path` field can also point to a URL instead of a local path.\nIn this case, Dora will download the given file when starting the dataflow.\n\nNote that this is quite an old feature and using this functionality is **not recommended**\nanymore. Instead, we recommend using a [`git`][Self::git] and/or [`build`](Self::build)\nkey.",
"type": [
"string",
"null"
]
},
"restart_policy": {
"description": "Whether this node should be restarted on exit or error.\n\nDefaults to `RestartPolicy::Never`.",
"$ref": "#/$defs/RestartPolicy",
"default": "never"
},
"rev": {
"description": "Git revision (e.g. commit hash) to checkout after cloning.\n\nThe `rev` field is only allowed in combination with the [`git`](#git) field.\nIt specifies the git revision (e.g. a commit hash) that should be checked out after cloning.\nOnly one of `branch`, `tag`, or `rev` can be specified.\n\n## Example\n\n```yaml\nnodes:\n - id: rust-node\n git: https://github.com/dora-rs/dora.git\n rev: 64ab0d7c\n```",
"type": [
"string",
"null"
]
},
"send_stdout_as": {
"description": "Redirect stdout/stderr to a data output.\n\nThis field can be used to send all stdout and stderr output of the node as a Dora output.\nEach output line is sent as a separate message.\n\n\n## Example\n\n```yaml\nnodes:\n - id: example\n send_stdout_as: stdout_output\n - id: logger\n inputs:\n example_output: example/stdout_output\n```",
"type": [
"string",
"null"
]
},
"tag": {
"description": "Git tag to checkout after cloning.\n\nThe `tag` field is only allowed in combination with the [`git`](#git) field.\nIt specifies the git tag that should be checked out after cloning.\nOnly one of `branch`, `tag`, or `rev` can be specified.\n\n## Example\n\n```yaml\nnodes:\n - id: rust-node\n git: https://github.com/dora-rs/dora.git\n tag: v0.3.0\n```",
"type": [
"string",
"null"
]
}
},
"additionalProperties": true,
"required": [
"id"
]
},
"NodeId": {
"type": "string"
},
"NodeSource": {
"oneOf": [
{
"type": "string",
"enum": [
"Local"
]
},
{
"type": "object",
"properties": {
"GitBranch": {
"type": "object",
"properties": {
"repo": {
"type": "string"
},
"rev": {
"anyOf": [
{
"$ref": "#/$defs/GitRepoRev"
},
{
"type": "null"
}
]
}
},
"required": [
"repo"
]
}
},
"additionalProperties": true,
"required": [
"GitBranch"
]
}
]
},
"OperatorDefinition": {
"type": "object",
"properties": {
"build": {
"description": "Build commands for this operator",
"type": [
"string",
"null"
]
},
"description": {
"description": "Detailed description of the operator",
"type": [
"string",
"null"
]
},
"id": {
"description": "Unique operator identifier within the runtime",
"$ref": "#/$defs/OperatorId"
},
"inputs": {
"description": "Input data connections",
"type": "object",
"additionalProperties": {
"$ref": "#/$defs/Input"
},
"default": {}
},
"name": {
"description": "Human-readable operator name",
"type": [
"string",
"null"
]
},
"outputs": {
"description": "Output data identifiers",
"type": "array",
"default": [],
"items": {
"$ref": "#/$defs/DataId"
},
"uniqueItems": true
},
"send_stdout_as": {
"description": "Redirect stdout to data output",
"type": [
"string",
"null"
]
}
},
"oneOf": [
{
"type": "object",
"properties": {
"shared-library": {
"type": "string"
}
},
"required": [
"shared-library"
]
},
{
"type": "object",
"properties": {
"python": {
"$ref": "#/$defs/PythonSource"
}
},
"required": [
"python"
]
}
],
"required": [
"id"
]
},
"OperatorId": {
"type": "string"
},
"PythonSource": {
"anyOf": [
{
"type": "string"
},
{
"type": "object",
"properties": {
"conda_env": {
"type": [
"string",
"null"
]
},
"source": {
"type": "string"
}
},
"required": [
"source"
]
}
]
},
"RestartPolicy": {
"description": "Specifies when a node should be restarted.",
"oneOf": [
{
"description": "Never restart the node (default)",
"type": "string",
"const": "never"
},
{
"description": "Restart the node if it exits with a non-zero exit code.",
"type": "string",
"const": "on-failure"
},
{
"description": "Always restart the node when it exits, regardless of exit code.\n\nThe node will not be restarted on the following conditions:\n\n- The node was stopped by the user (e.g., via `dora stop`).\n- All inputs to the node have been closed and the node finished with a non-zero exit code.",
"type": "string",
"const": "always"
}
]
},
"RuntimeNode": {
"description": "List of operators running in this runtime",
"type": "array",
"items": {
"$ref": "#/$defs/OperatorDefinition"
}
},
"SingleOperatorDefinition": {
"type": "object",
"properties": {
"build": {
"description": "Build commands for this operator",
"type": [
"string",
"null"
]
},
"description": {
"description": "Detailed description of the operator",
"type": [
"string",
"null"
]
},
"id": {
"description": "Operator identifier (optional for single operators)",
"anyOf": [
{
"$ref": "#/$defs/OperatorId"
},
{
"type": "null"
}
]
},
"inputs": {
"description": "Input data connections",
"type": "object",
"additionalProperties": {
"$ref": "#/$defs/Input"
},
"default": {}
},
"name": {
"description": "Human-readable operator name",
"type": [
"string",
"null"
]
},
"outputs": {
"description": "Output data identifiers",
"type": "array",
"default": [],
"items": {
"$ref": "#/$defs/DataId"
},
"uniqueItems": true
},
"send_stdout_as": {
"description": "Redirect stdout to data output",
"type": [
"string",
"null"
]
}
},
"oneOf": [
{
"type": "object",
"properties": {
"shared-library": {
"type": "string"
}
},
"required": [
"shared-library"
]
},
{
"type": "object",
"properties": {
"python": {
"$ref": "#/$defs/PythonSource"
}
},
"required": [
"python"
]
}
]
},
"UserInputMapping": {
"type": "object",
"properties": {
"output": {
"$ref": "#/$defs/DataId"
},
"source": {
"$ref": "#/$defs/NodeId"
}
},
"required": [
"source",
"output"
]
}
}
}