wehub-resource-sync
e768098d0e
Flake8 Lint / flake8 (push) Waiting to run
Spell check CI / Spell_Check (push) Waiting to run
tools_continuous_delivery / Private PyPI non-main branch release (push) Has been skipped
tools_continuous_delivery / Private PyPI main branch release (push) Failing after 2m42s
Publish Promptflow Doc / Build (push) Has been cancelled
Publish Promptflow Doc / Deploy (push) Has been cancelled
58 lines
2.7 KiB
Plaintext
58 lines
2.7 KiB
Plaintext
# Common section: this section provides common values for all other sections. Required.
|
|
# Configure 'document_folder', 'document_chunk_size' and 'document_chunk_overlap' if you require document splitting.
|
|
documents_folder: <your-document-folder-path>
|
|
document_chunk_size: 512 # The token chunk size for each chunk.
|
|
document_chunk_overlap: 100 # The token overlap of each chunk when splitting.
|
|
|
|
# However, if you wish to bypass the document split process, simply provide the 'document_nodes_file', which is a JSONL file.
|
|
# When both 'documents_folder' and 'document_nodes_file' are configured, will use 'document_nodes_file' and ignore 'documents_folder'.
|
|
# For cloud mode, both local files and data assets can be used.
|
|
# document_nodes_file: <your-node-file-path>
|
|
|
|
# Test data gen flow configs
|
|
# You can utilize our provided example test data generation flow directly. Alternatively, you can create your own flow and set up corresponding node inputs override.
|
|
# The example flow folder path is <promptflow github repo>\examples\gen_test_data\example_flow
|
|
flow_folder: <your-test-data-gen-flow-folder-path>
|
|
node_inputs_override: # Override some node inputs, if not fill in 'node_inputs_override', will use the values in flow.dag.yaml
|
|
validate_text_chunk: # node name in flow.dag.yaml
|
|
connection: <your-connection-name> # connection name of node 'validate_text_chunk'
|
|
# Use 'deployment_name' for Azure OpenAI connection, 'model' for OpenAI
|
|
deployment_name: <your-deployment-name>
|
|
# model: <your-model>
|
|
generate_question:
|
|
connection: <your-connection-name>
|
|
deployment_name: <your-deployment-name>
|
|
# model: <your-model>
|
|
validate_question:
|
|
connection: <your-connection-name>
|
|
deployment_name: <your-deployment-name>
|
|
# model: <your-model>
|
|
generate_suggested_answer:
|
|
connection: <your-connection-name>
|
|
deployment_name: <your-deployment-name>
|
|
# model: <your-model>
|
|
validate_suggested_answer:
|
|
connection: <your-connection-name>
|
|
deployment_name: <your-deployment-name>
|
|
# model: <your-model>
|
|
|
|
|
|
# Local section: this section is for local test data generation related configuration. Can skip if not run in local.
|
|
output_folder: <your-output-folder-path>
|
|
flow_batch_run_size: 4 # Higher values may speed up flow runs but risk hitting OpenAI's rate limit.
|
|
|
|
|
|
# Cloud section: this section is for cloud test data generation related configuration. Can skip if not run in cloud.
|
|
subscription_id: <your-sub-id>
|
|
resource_group: <your-resource-group>
|
|
workspace_name: <your-workspace-name>
|
|
aml_cluster: <your-compute-name>
|
|
|
|
# Parallel run step configs
|
|
prs_instance_count: 2
|
|
prs_mini_batch_size: 1
|
|
prs_max_concurrency_per_instance: 4
|
|
prs_max_retry_count: 3
|
|
prs_run_invocation_time: 800
|
|
prs_allowed_failed_count: -1
|