Quick Start

Install Radhflow, create a pipeline, and run it in 60 seconds.

Install

npm install -g radhflow

Verify the installation:

radhflow --version

Initialize a project

mkdir my-pipeline && cd my-pipeline
radhflow init

This creates a Git-backed workspace:

my-pipeline/
  gain.yaml          # pipeline definition
  nodes/             # generated node code
  .gitignore

Create your first pipeline

Open gain.yaml and replace its contents:

nodes:
  read-leads:
    type: source
    op: file.read_csv
    params:
      path: leads.csv
    outputs:
      leads:
        type: Table
        schema:
          name: { type: string }
          email: { type: string }
          score: { type: number }

  filter-top:
    type: deterministic
    op: sql.query
    params:
      query: "SELECT * FROM leads WHERE score >= 80"
    inputs:
      leads:
        type: Table
        from: ref(read-leads.leads)
    outputs:
      qualified:
        type: Table

  write-output:
    type: deterministic
    op: file.write_json
    params:
      path: qualified-leads.json
    inputs:
      qualified:
        type: Table
        from: ref(filter-top.qualified)

Three nodes. CSV in, SQL filter, JSON out. Every connection is typed.

Add test data

Create leads.csv:

name,email,score
Alice,alice@example.com,92
Bob,bob@example.com,45
Carol,carol@example.com,88
Dave,dave@example.com,71
Eve,eve@example.com,95

Run the pipeline

radhflow run

Output:

[read-leads]   ✔ Read 5 rows from leads.csv
[filter-top]   ✔ 3 rows matched (score >= 80)
[write-output] ✔ Wrote qualified-leads.json

Pipeline completed. 3 nodes executed in 0.4s.

Check the result:

cat qualified-leads.json

[
  { "name": "Alice", "email": "alice@example.com", "score": 92 },
  { "name": "Carol", "email": "carol@example.com", "score": 88 },
  { "name": "Eve", "email": "eve@example.com", "score": 95 }
]

What just happened

1. read-leads read the CSV and produced a typed Table.
2. filter-top ran a DuckDB SQL query against that Table.
3. write-output wrote the filtered rows as JSON.

No LLM ran. No tokens burned. Same input produces identical output every time.

Next steps

• Read Key Concepts to understand pipelines, nodes, ports, and data types.
• Explore What is Radhflow? for the full architecture picture.