From 8b650ec283d538df3278d5639f00bd1d5f6fc64d Mon Sep 17 00:00:00 2001 From: Brandon Hancock Date: Mon, 9 Sep 2024 11:56:24 -0400 Subject: [PATCH] WIP --- docs/core-concepts/Pipeline.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/docs/core-concepts/Pipeline.md b/docs/core-concepts/Pipeline.md index 7fed4887c..184cce493 100644 --- a/docs/core-concepts/Pipeline.md +++ b/docs/core-concepts/Pipeline.md @@ -38,6 +38,10 @@ Each input creates its own run, flowing through all stages of the pipeline. Mult ## Creating a Pipeline +There are 2 ways to create a pipeline in crewAI: using the CLI and manually. We recommend using the CLI approach for its simplicity and ease of use, but we'll cover both approaches. + +# TODO: UPDATE TO TALK ABOUT BOTH CLI & MANUAL METHOD + When creating a pipeline, you define a series of stages, each consisting of either a single crew or a list of crews for parallel execution. The pipeline ensures that each stage is executed in order, with the output of one stage feeding into the next. ### Example: Assembling a Pipeline @@ -45,6 +49,8 @@ When creating a pipeline, you define a series of stages, each consisting of eith ```python from crewai import Crew, Agent, Task, Pipeline +# Define your agents and tasks here... + # Define your crews research_crew = Crew( agents=[researcher], @@ -72,6 +78,8 @@ my_pipeline = Pipeline( ## Pipeline Methods +# TODO: DROP PROCESS_RUNS AND UPDATE TO KICKOFF + | Method | Description | | :--------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **process_runs** | Executes the pipeline, processing all stages and returning the results. This method initiates one or more runs through the pipeline, handling the flow of data between stages. |