RAG index construction and evaluation

Build a retrievable knowledge index and validate it before publication.

collect documents→extract and clean→chunk→embed→build index→retrieval testsanswer tests→publish index

RAG index construction and evaluation

Activity responsibilities

Activity	Responsibility
collect-documents	Execute the collect documents stage and publish its declared outputs for downstream activities.
extract-and-clean	Execute the extract and clean stage and publish its declared outputs for downstream activities.
chunk	Execute the chunk stage and publish its declared outputs for downstream activities.
embed	Execute the embed stage and publish its declared outputs for downstream activities.
build-index	Execute the build index stage and publish its declared outputs for downstream activities.
retrieval-tests	Execute the retrieval tests stage and publish its declared outputs for downstream activities.
answer-tests	Execute the answer tests stage and publish its declared outputs for downstream activities.
publish-index	Execute the publish index stage and publish its declared outputs for downstream activities.

Inputs

• Source collection
• Chunking policy
• Model revisions

Outputs

• Index snapshot
• Evaluation reports
• Source manifest

Provenance to preserve

• Source revisions
• Chunk identifiers
• Prompts and models

Runnable example

This is the complete checked-in bundle for this pattern. Download the environment, scope, topology, workflow, input, container recipe, runner, and validation contract from this page before executing it.

Read setup instructions ↓Environment YAML ↓Execution scope YAML ↓Network topology YAML ↓Workflow YAML ↓Input data ↓Container recipe ↓Run the workflow ↓Validate outputs ↓Expected output manifest ↓

Verified local execution

These captures and the output manifest were produced by the fixture's local Docker run and validator. They are published with the same bundle as the runnable files.

Workflow evidence

Execution evidence

Output evidence

Open verified output manifest ↓

Execution considerations

Fan out document processing and embedding. Treat the vector database as a service while retaining immutable index evidence.

AkôFlow boundary: the engine schedules, deploys, executes, transfers data, and records evidence. The ML or agent framework remains an implementation choice inside each activity.