dora/libraries/core/dora-schema.json

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "title": "dora-rs specification",
  "description": "The main configuration structure for defining a Dora dataflow. Dataflows are specified through YAML files that describe the nodes, their connections, and execution parameters.\n\n## Structure\n\nA dataflow consists of: - **Nodes**: The computational units that process data - **Communication**: Optional communication configuration - **Deployment**: Optional deployment configuration (unstable) - **Debug options**: Optional development and debugging settings (unstable)\n\n## Example\n\n```yaml nodes: - id: webcam operator: python: webcam.py inputs: tick: dora/timer/millis/100 outputs: - image - id: plot operator: python: plot.py inputs: image: webcam/image ```",
  "type": "object",
  "required": [
    "nodes"
  ],
  "properties": {
    "nodes": {
      "description": "List of nodes in the dataflow\n\nThis is the most important field of the dataflow specification. Each node must be identified by a unique `id`:\n\n## Example\n\n```yaml nodes: - id: foo path: path/to/the/executable # ... (see below) - id: bar path: path/to/another/executable # ... (see below) ```\n\nFor each node, you need to specify the `path` of the executable or script that Dora should run when starting the node. Most of the other node fields are optional, but you typically want to specify at least some `inputs` and/or `outputs`.",
      "type": "array",
      "items": {
        "$ref": "#/definitions/Node"
      }
    }
  },
  "additionalProperties": true,
  "definitions": {
    "CustomNode": {
      "description": "Contains the input and output configuration of the node.",
      "type": "object",
      "required": [
        "path",
        "source"
      ],
      "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": {
            "$ref": "#/definitions/EnvValue"
          }
        },
        "inputs": {
          "description": "Inputs for the nodes as a map from input ID to `node_id/output_id`.\n\ne.g.\n\ninputs:\n\nexample_input: example_node/example_output1",
          "default": {},
          "type": "object",
          "additionalProperties": true
        },
        "outputs": {
          "description": "List of output IDs.\n\ne.g.\n\noutputs:\n\n- output_1\n\n- output_2",
          "default": [],
          "type": "array",
          "items": {
            "$ref": "#/definitions/DataId"
          },
          "uniqueItems": true
        },
        "path": {
          "description": "Path of the source code\n\nIf you want to use a specific `conda` environment. Provide 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"
        },
        "send_stdout_as": {
          "description": "Send stdout and stderr to another node",
          "type": [
            "string",
            "null"
          ]
        },
        "source": {
          "$ref": "#/definitions/NodeSource"
        }
      }
    },
    "DataId": {
      "type": "string"
    },
    "Duration": {
      "type": "object",
      "required": [
        "nanos",
        "secs"
      ],
      "properties": {
        "nanos": {
          "type": "integer",
          "format": "uint32",
          "minimum": 0.0
        },
        "secs": {
          "type": "integer",
          "format": "uint64",
          "minimum": 0.0
        }
      }
    },
    "EnvValue": {
      "anyOf": [
        {
          "type": "boolean"
        },
        {
          "type": "integer",
          "format": "int64"
        },
        {
          "type": "number",
          "format": "double"
        },
        {
          "type": "string"
        }
      ]
    },
    "GitRepoRev": {
      "oneOf": [
        {
          "type": "object",
          "required": [
            "Branch"
          ],
          "properties": {
            "Branch": {
              "type": "string"
            }
          },
          "additionalProperties": true
        },
        {
          "type": "object",
          "required": [
            "Tag"
          ],
          "properties": {
            "Tag": {
              "type": "string"
            }
          },
          "additionalProperties": true
        },
        {
          "type": "object",
          "required": [
            "Rev"
          ],
          "properties": {
            "Rev": {
              "type": "string"
            }
          },
          "additionalProperties": true
        }
      ]
    },
    "Input": {
      "type": "object",
      "required": [
        "mapping"
      ],
      "properties": {
        "mapping": {
          "$ref": "#/definitions/InputMapping"
        },
        "queue_size": {
          "type": [
            "integer",
            "null"
          ],
          "format": "uint",
          "minimum": 0.0
        }
      }
    },
    "InputMapping": {
      "oneOf": [
        {
          "type": "object",
          "required": [
            "Timer"
          ],
          "properties": {
            "Timer": {
              "type": "object",
              "required": [
                "interval"
              ],
              "properties": {
                "interval": {
                  "$ref": "#/definitions/Duration"
                }
              }
            }
          },
          "additionalProperties": true
        },
        {
          "type": "object",
          "required": [
            "User"
          ],
          "properties": {
            "User": {
              "$ref": "#/definitions/UserInputMapping"
            }
          },
          "additionalProperties": true
        }
      ]
    },
    "Node": {
      "title": "Dora Node Configuration",
      "description": "A node represents a computational unit in a Dora dataflow. Each node runs as a separate process and can communicate with other nodes through inputs and outputs.",
      "type": "object",
      "required": [
        "id"
      ],
      "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`. The arguments should be separated by space. This field is optional and defaults to an empty argument list.\n\n## Example ```yaml nodes: - id: example path: example-node args: -v --some-flag foo ```",
          "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. It specifies the branch that should be checked out after cloning. Only one of `branch`, `tag`, or `rev` can be specified.\n\n## Example\n\n```yaml nodes: - id: rust-node git: https://github.com/dora-rs/dora.git branch: some-branch-name ```",
          "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. The key expects a single- or multi-line string.\n\nEach line is run as a separate command. Spaces are used to separate arguments.\n\nNote that all the environment variables specified in the [`env`](Self::env) field are also applied 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: If the `--uv` argument is passed to the `dora build` command, all `pip`/`pip3` commands are run through the [`uv` package manager](https://docs.astral.sh/uv/).\n\n## Example\n\n```yaml nodes: - id: build-example build: cargo build -p receive_data --release path: target/release/receive_data - id: multi-line-example build: | pip install requirements.txt pip install -e some/local/package path: package ```\n\nIn the above example, the `pip` commands will be replaced by `uv pip` when run through `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": [
            {
              "$ref": "#/definitions/CustomNode"
            },
            {
              "type": "null"
            }
          ]
        },
        "description": {
          "description": "Detailed description of the node's functionality.\n\n## Example\n\n```yaml nodes: - id: camera_node description: \"Captures video frames from webcam\" ```",
          "type": [
            "string",
            "null"
          ]
        },
        "env": {
          "description": "Environment variables for node builds and execution.\n\nKey-value map of environment variables that should be set for both the [`build`](Self::build) operation and the node execution (i.e. when the node is spawned through [`path`](Self::path)).\n\nSupports strings, numbers, and booleans.\n\n## Example\n\n```yaml nodes: - id: example-node path: path/to/node env: DEBUG: true PORT: 8080 API_KEY: \"secret-key\" ```",
          "type": [
            "object",
            "null"
          ],
          "additionalProperties": {
            "$ref": "#/definitions/EnvValue"
          }
        },
        "git": {
          "description": "Git repository URL for downloading nodes.\n\nThe `git` key allows downloading nodes (i.e. their source code) from git repositories. This can be especially useful for distributed dataflows.\n\nWhen a `git` key is specified, `dora build` automatically clones the specified repository (or reuse an existing clone). Then it checks out the specified [`branch`](Self::branch), [`tag`](Self::tag), or [`rev`](Self::rev), or the default branch if none of them are specified. Afterwards it runs the [`build`](Self::build) command if specified.\n\nNote that the git clone directory is set as working directory for both the [`build`](Self::build) command and the specified [`path`](Self::path).\n\n## Example\n\n```yaml nodes: - id: rust-node git: https://github.com/dora-rs/dora.git build: cargo build -p rust-dataflow-example-node path: target/debug/rust-dataflow-example-node ```\n\nIn the above example, `dora build` will first clone the specified `git` repository and then run the specified `build` inside the local clone directory. When `dora run` or `dora start` is invoked, the working directory will be the git clone directory 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). - 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 nodes: - id: camera_node - id: some_other_node ```",
          "allOf": [
            {
              "$ref": "#/definitions/NodeId"
            }
          ]
        },
        "inputs": {
          "description": "Input data connections from other nodes.\n\nDefines the inputs that this node is subscribing to.\n\nThe `inputs` field should be a key-value map of the following format:\n\n`input_id: source_node_id/source_node_output_id`\n\nThe components are defined as follows:\n\n- `input_id` is the local identifier that should be used for this input.\n\nThis will map to the `id` field of [`Event::Input`](https://docs.rs/dora-node-api/latest/dora_node_api/enum.Event.html#variant.Input) events sent to the node event loop. - `source_node_id` should be the `id` field of the node that sends the output that we want to subscribe to - `source_node_output_id` should be the identifier of the output that that we want to subscribe to\n\n## Example\n\n```yaml nodes: - id: example-node outputs: - one - two - id: receiver inputs: my_input: example-node/two ```",
          "default": {},
          "type": "object",
          "additionalProperties": true
        },
        "name": {
          "description": "Human-readable node name for documentation.\n\nThis optional field can be used to define a more descriptive name in addition to a short [`id`](Self::id).\n\n## Example\n\n```yaml nodes: - id: camera_node name: \"Camera Input Handler\"",
          "type": [
            "string",
            "null"
          ]
        },
        "operator": {
          "description": "Single operator configuration.\n\nThis is a convenience field for defining runtime nodes that contain only a single operator. This field is an alternative to the [`operators`](Self::operators) field, which can be used if there is only a single operator defined for the runtime node.\n\n## Example\n\n```yaml nodes: - id: runtime-node operator: id: processor python: script.py outputs: [data] ```",
          "anyOf": [
            {
              "$ref": "#/definitions/SingleOperatorDefinition"
            },
            {
              "type": "null"
            }
          ]
        },
        "operators": {
          "description": "Multiple operators running in a shared runtime process.\n\nOperators are an experimental, lightweight alternative to nodes. Instead of running as a separate process, operators are linked into a runtime process. This allows running multiple operators to share a single address space (not supported for Python currently).\n\nOperators are defined as part of the node list, as children of a runtime node. A runtime node is a special node that specifies no [`path`](Self::path) field, but contains an `operators` field instead.\n\n## Example\n\n```yaml nodes: - id: runtime-node operators: - id: processor python: process.py ```",
          "type": [
            "array",
            "null"
          ],
          "items": {
            "$ref": "#/definitions/OperatorDefinition"
          }
        },
        "outputs": {
          "description": "Output data identifiers produced by this node.\n\nList of output identifiers that the node sends. Must contain all `output_id` values that the node uses when sending output, e.g. through the [`send_output`](https://docs.rs/dora-node-api/latest/dora_node_api/struct.DoraNode.html#method.send_output) function.\n\n## Example\n\n```yaml nodes: - id: example-node outputs: - processed_image - metadata ```",
          "default": [],
          "type": "array",
          "items": {
            "$ref": "#/definitions/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 dataflow. This can point to a normal executable (e.g. when using a compiled language such as Rust) or a Python script.\n\nDora will automatically append a `.exe` extension on Windows systems when the specified file name has no extension.\n\n## Example\n\n```yaml nodes: - id: rust-example path: target/release/rust-node - id: python-example path: ./receive_data.py ```\n\n## URL as Path\n\nThe `path` field can also point to a URL instead of a local path. In 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** anymore. Instead, we recommend using a [`git`][Self::git] and/or [`build`](Self::build) key.",
          "type": [
            "string",
            "null"
          ]
        },
        "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. It specifies the git revision (e.g. a commit hash) that should be checked out after cloning. Only one of `branch`, `tag`, or `rev` can be specified.\n\n## Example\n\n```yaml nodes: - id: rust-node git: https://github.com/dora-rs/dora.git rev: 64ab0d7c ```",
          "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. Each output line is sent as a separate message.\n\n## Example\n\n```yaml nodes: - id: example send_stdout_as: stdout_output - id: logger inputs: example_output: example/stdout_output ```",
          "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. It specifies the git tag that should be checked out after cloning. Only one of `branch`, `tag`, or `rev` can be specified.\n\n## Example\n\n```yaml nodes: - id: rust-node git: https://github.com/dora-rs/dora.git tag: v0.3.0 ```",
          "type": [
            "string",
            "null"
          ]
        }
      },
      "additionalProperties": true
    },
    "NodeId": {
      "type": "string"
    },
    "NodeSource": {
      "oneOf": [
        {
          "type": "string",
          "enum": [
            "Local"
          ]
        },
        {
          "type": "object",
          "required": [
            "GitBranch"
          ],
          "properties": {
            "GitBranch": {
              "type": "object",
              "required": [
                "repo"
              ],
              "properties": {
                "repo": {
                  "type": "string"
                },
                "rev": {
                  "anyOf": [
                    {
                      "$ref": "#/definitions/GitRepoRev"
                    },
                    {
                      "type": "null"
                    }
                  ]
                }
              }
            }
          },
          "additionalProperties": true
        }
      ]
    },
    "OperatorDefinition": {
      "type": "object",
      "oneOf": [
        {
          "type": "object",
          "required": [
            "shared-library"
          ],
          "properties": {
            "shared-library": {
              "type": "string"
            }
          },
          "additionalProperties": true
        },
        {
          "type": "object",
          "required": [
            "python"
          ],
          "properties": {
            
          },
          "additionalProperties": true
        }
      ],
      "required": [
        "id"
      ],
      "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",
          "allOf": [
            {
              "$ref": "#/definitions/OperatorId"
            }
          ]
        },
        "inputs": {
          "description": "Input data connections",
          "default": {},
          "type": "object",
          "additionalProperties": true
        },
        "name": {
          "description": "Human-readable operator name",
          "type": [
            "string",
            "null"
          ]
        },
        "outputs": {
          "description": "Output data identifiers",
          "default": [],
          "type": "array",
          "items": {
            "$ref": "#/definitions/DataId"
          },
          "uniqueItems": true
        },
        "send_stdout_as": {
          "description": "Redirect stdout to data output",
          "type": [
            "string",
            "null"
          ]
        }
      }
    },
    "OperatorId": {
      "type": "string"
    },
    "PythonSource": {
      "type": "object",
      "required": [
        "source"
      ],
      "properties": {
        "conda_env": {
          "type": [
            "string",
            "null"
          ]
        },
        "source": {
          "type": "string"
        }
      }
    },
    "SingleOperatorDefinition": {
      "type": "object",
      "oneOf": [
        {
          "type": "object",
          "required": [
            "shared-library"
          ],
          "properties": {
            "shared-library": {
              "type": "string"
            }
          },
          "additionalProperties": true
        },
        {
          "type": "object",
          "required": [
            "python"
          ],
          "properties": {
            
          },
          "additionalProperties": true
        }
      ],
      "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": [
            {
              "$ref": "#/definitions/OperatorId"
            },
            {
              "type": "null"
            }
          ]
        },
        "inputs": {
          "description": "Input data connections",
          "default": {},
          "type": "object",
          "additionalProperties": true
        },
        "name": {
          "description": "Human-readable operator name",
          "type": [
            "string",
            "null"
          ]
        },
        "outputs": {
          "description": "Output data identifiers",
          "default": [],
          "type": "array",
          "items": {
            "$ref": "#/definitions/DataId"
          },
          "uniqueItems": true
        },
        "send_stdout_as": {
          "description": "Redirect stdout to data output",
          "type": [
            "string",
            "null"
          ]
        }
      }
    },
    "UserInputMapping": {
      "type": "object",
      "required": [
        "output",
        "source"
      ],
      "properties": {
        "output": {
          "$ref": "#/definitions/DataId"
        },
        "source": {
          "$ref": "#/definitions/NodeId"
        }
      }
    }
  }
}