---
name: graph-based-node-workflow
version: 1.0.0
description: Create and execute typed node graphs for AI/robotics workflows by defining
  nodes with inputs/outputs and connecting them with edges, then cooking the graph
  to run the workflow.
inputs:
- bn.Graph() - the graph container for the workflow
- Node definitions (Literal, Text, LLMAgent, Concat, Output, etc.) with specified
  inputs and outputs
- Edge connections mapping from_port to to_port between nodes
steps:
- 'Step 1: Initialize a bn.Graph() instance to serve as the workflow container'
- 'Step 2: Define individual nodes with their required inputs and outputs (e.g., Literal
  for data, LLMAgent for inference, Concat for combining, Output for final results)'
- 'Step 3: Create edges connecting nodes by specifying source from_port and destination
  to_port for each data flow'
- 'Step 4: Execute the graph by calling g.cook() to process the defined workflow and
  produce results'
outputs:
- Executed workflow results stored in the graph's output nodes
- Cooked graph ready for inspection, replay, or deployment
- Potential error states if node dependencies are missing or ports don't match
tags: []
metadata:
  source_repo: https://github.com/temiroff/Blacknode.git
  extracted_at: ''
  confidence: 0.95
---

# graph-based-node-workflow

Create and execute typed node graphs for AI/robotics workflows by defining nodes with inputs/outputs and connecting them with edges, then cooking the graph to run the workflow.

## Setup

**Dependencies:**

```text
pip install blacknode (core Python package) anthropic, openai, docker, petgraph (dependencies) Rust extensions in blacknode-core, blacknode-runtime (optional)
```

**Setup steps:**

1. Install blacknode with Python 3.11+ and required dependencies
1. Clone repository and navigate to project directory
1. Run examples/converted_text_pipeline.py to see basic graph execution
1. Modify node definitions and edges to create custom workflows

## Key Files

- `examples/converted_text_pipeline.py - basic pipeline pattern`
- `examples/hello_agent.py - LLM agent workflow pattern`
- `examples/research_pipeline.py - multi-node research workflow`
- `blacknode.py - main CLI entry point`

## Steps

1. Step 1: Initialize a bn.Graph() instance to serve as the workflow container
2. Step 2: Define individual nodes with their required inputs and outputs (e.g., Literal for data, LLMAgent for inference, Concat for combining, Output for final results)
3. Step 3: Create edges connecting nodes by specifying source from_port and destination to_port for each data flow
4. Step 4: Execute the graph by calling g.cook() to process the defined workflow and produce results

## Implementation Details

```python
g = bn.Graph()
```

```python
g._edges = [{"from": "model", "from_port": "value", "to": "agent", "to_port": "model"}]
```

```python
result = g.cook(output, "value")
```

## Inputs

- bn.Graph() - the graph container for the workflow
- Node definitions (Literal, Text, LLMAgent, Concat, Output, etc.) with specified inputs and outputs
- Edge connections mapping from_port to to_port between nodes

## Outputs

- Executed workflow results stored in the graph's output nodes
- Cooked graph ready for inspection, replay, or deployment
- Potential error states if node dependencies are missing or ports don't match

## Failure Modes

- Missing node dependencies causing undefined variable errors
- Port mismatch in edge connections leading to no data flow
- Incomplete graph definition causing cook() to fail
- Model API key missing or invalid for LLMAgent nodes

## Source

Extracted from: [https://github.com/temiroff/Blacknode.git](https://github.com/temiroff/Blacknode.git)
Confidence: 0.95