microsoft--promptflow/examples/flows/standard/flow-with-additional-includes/README.md

Flow with additional_includes

User sometimes need to reference some common files or folders, this sample demos how to solve the problem using additional_includes. The file or folders in additional includes will be copied to the snapshot folder by promptflow when operate this flow.

Tools used in this flow

• LLM Tool
• Python Tool

What you will learn

In this flow, you will learn

• how to add additional includes to the flow

Prerequisites

Install promptflow sdk and other dependencies:

pip install -r requirements.txt

Getting Started

1. Add additional includes to flow

You can add this field additional_includes into the flow.dag.yaml. The value of this field is a list of the relative file/folder path to the flow folder.

additional_includes:
- ../web-classification/classify_with_llm.jinja2
- ../web-classification/convert_to_dict.py
- ../web-classification/fetch_text_content_from_url.py
- ../web-classification/prepare_examples.py
- ../web-classification/summarize_text_content.jinja2
- ../web-classification/summarize_text_content__variant_1.jinja2

2. Test & run the flow with additional includes

In this sample, this flow will references some files in the web-classification flow. You can execute this flow with additional_include or submit it to cloud. The snapshot generated by Promptflow contains additional include files/folders.

Test flow with single line data

# test with default input value in flow.dag.yaml
pf flow test --flow .
# test with user specified inputs
pf flow test --flow . --inputs url='https://www.microsoft.com/en-us/d/xbox-wireless-controller-stellar-shift-special-edition/94fbjc7h0h6h'

Run with multi-line data

# create run using command line args
pf run create --flow . --data ./data.jsonl --column-mapping url='${data.url}' --stream
# create run using yaml file
pf run create --file run.yml --stream

You can also skip providing column-mapping if provided data has same column name as the flow. Reference here for default behavior when column-mapping not provided in CLI.

Submit run to cloud

Assume we already have a connection named open_ai_connection in workspace.

# set default workspace
az account set -s <your_subscription_id>
az configure --defaults group=<your_resource_group_name> workspace=<your_workspace_name>

# create run
pfazure run create --flow . --data ./data.jsonl --column-mapping url='${data.url}' --stream
pfazure run create --file run.yml

Note: Click portal_url of the run to view the final snapshot.