Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update pf pipeline tutorial #3488

Merged
merged 7 commits into from
Jul 3, 2024
Merged
Changes from 3 commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 10 additions & 2 deletions examples/tutorials/run-flow-with-pipeline/pipeline.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -147,7 +147,11 @@
"| debug_info | uri_folder | If you run your flow component in __debug mode__, this port provides debugging information for each run of your lines. E.g. intermediate outputs between steps, or LLM response and token usage. |\n",
"\n",
"![prompt flow base component image](./media/cloud/flow-in-pipeline/pf-base-component.png)\n",
" \n",
"\n",
"> __NOTE:__</br>\n",
"> \n",
"> `flow_outputs` and `debug_info` outputs are required to be set `mount` mode as the output mode when you run pf component with multiple nodes. \n",
"\n",
" - Auto-generated parameters \n",
" \n",
" These parameters represent all your flow inputs and connections associated with your flow steps. You can set default values in the flow/run definition, and they can be further customized during job submission. Use '[web-classification](https://github.com/microsoft/promptflow/blob/main/examples/flows/standard/web-classification/flow.dag.yaml)' sample flow for example, this flow has only one input named 'url' and 2 LLM steps 'summarize_text_content' and 'classify_with_llm'. The input parameters of this flow component are:\n",
Expand Down Expand Up @@ -377,9 +381,13 @@
" flow_node.mini_batch_size = 5\n",
" flow_node.max_concurrency_per_instance = 2\n",
" flow_node.resources = {\"instance_count\": 1}\n",
" flow_node.outputs.flow_outputs.mode = \"rw_mount\"\n",
" flow_node.logging_level = \"DEBUG\"\n",
"\n",
" # set output mode to 'mount'\n",
" # This is required for the flow component when the 'instance_count' is set higher than 1\n",
" flow_node.outputs.flow_outputs.mode = \"mount\"\n",
" flow_node.outputs.debug_info.mode = \"mount\"\n",
"\n",
" result_parser_node = result_parser_component(\n",
" source_data=data_prep_node.outputs.output_data_folder,\n",
" pf_output_data=flow_node.outputs.flow_outputs,\n",
Expand Down
Loading