> For the complete documentation index, see [llms.txt](https://docs.release.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.release.com/release.ai/release.ai-custom-workflows.md).

# Custom Workflows

Custom workflows allow you to automate complex tasks like streamlining your data ingestion process. The following examples are configurations for a job and a workflow, as well as how to trigger this workflow using a GitHub Action.

## Custom Workflow Examples

To handle the ingestion of your data, you can define a custom workflow in Release. Here's an example configuration for a job that ingests data:

```yaml
jobs:
- name: rag-ingest
  from_services: rag-ingest
  command:
  - python
  - release-data-rag-ingest.py
  envs:
  - key: CHROMA_HOST
    value: chroma
  - key: CHROMA_PORT
    value: 8000
  - key: OLLAMA_BASE_URL
    value: http://ollama:11434
  memory:
    limits: 4Gi
    requests: 100Mi
  cpu:
    limits: 2000m
    requests: 100m
```

This configuration defines a job named `rag-ingest` that runs a Python script to ingest the data. The necessary environment variables, memory, and CPU allocations are also specified to ensure the job runs smoothly.

### Define the Workflow in Release

Next, include the workflow definition that leverages the job you've configured:

```yaml
workflows:
- name: rag-ingest
  parallelize:
  - step: rag-ingest
    tasks:
    - jobs.rag-ingest
```

This workflow specifies that the `rag-ingest` job should be executed.

### Example GitHub Action to Trigger the Workflow

With the Release workflow configured, you can now set up a GitHub Action in your data repository. This action will trigger the Release workflow whenever there's a push to the main branch. Below is a sample GitHub Action configuration:

```yaml
name: Release RAG Ingest Data

on:
  push:
    branches:
      - main

env:
  RELEASE_LOGIN: ${{ secrets.RELEASE_LOGIN }}
  RELEASE_TOKEN: ${{ secrets.RELEASE_TOKEN }}

jobs:
  ingest:
    name: Ingest data
    runs-on: ubuntu-latest
    concurrency: ci-${{ github.ref }}
    container: public.ecr.aws/b4g8c3s2/release-cli
    run: |
      ACCOUNT=HandsUp
      ENVIRONMENT=production
      APP=release-data-rag
      WORKFLOW=rag-ingest
      release deploys create \
        --account "$ACCOUNT" \
        --app "$APP" \
        --environment "$ENVIRONMENT" \
        --workflow "$WORKFLOW" \
        --output json \
        --wait > res.json
```

In this example:

* The workflow triggers on any push to the `main` branch.
* It uses the `RELEASE_LOGIN` and `RELEASE_TOKEN` secrets for authentication.
* The job runs the Release `release-cli` image in a container in your Release environment.
* The `release deploys create` command initiates the custom workflow defined in Release.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.release.com/release.ai/release.ai-custom-workflows.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.