Local RAG Factory

The workflow normalizes a local Markdown corpus, creates chunks, builds a hashed TF-IDF index, retrieves evidence, generates extractive answers with citations, and evaluates grounding. Its deterministic implementation makes retrieval behavior inspectable before an optional Ollama adapter is introduced.

Local RAG Factory. Nodes in the same column can run in parallel once their dependencies complete.

Inputs

Versioned Markdown corpus
Questions with expected evidence

Outputs

Normalized documents and chunks
Vector index
Ranked retrieval results
Cited answers
Grounded-accuracy report

Provenance to preserve

Document SHA-256 values
Chunk identifiers
Retrieval scores
Answer citations and evaluation result

Run this example locally

Build a local lexical retrieval index over the bundled text corpus, answer questions by retrieving source evidence, and check the answers against versioned known-answer tests. No hosted embedding or LLM service is required.

Install Go and Python 3.12 or newer.

git clone https://github.com/UFFeScience/akoflow-examples.git &&
cd akoflow-examples &&
git checkout --detach d890c3171e3661890305b763b8fc3ede48bb61b4 &&
cd generative-ai/local-rag &&
./prepare.sh &&
./run.sh

Run the block from the directory where you keep your repositories. If you already cloned the repository, enter this example's directory and run ./prepare.sh && ./run.sh.

Preparation downloads the Go module and any declared Python packages once. The workload then runs locally with offline input data. Every meaningful step is a separate process; independent activities run in parallel after their dependencies complete.

Read outputs/manifest.json for the generated artifacts, outputs/dag-validation.json for dependency waves, and outputs/stage-<activity>.json for each activity's observed result. A failed stage stops the run and prevents a successful final manifest.

Expected outputs: documents.json, chunks.json, index.json, retrieval.json, answers.json, evaluation.json.

Run the same activities in Desktop

Start your local AkôFlow daemon with Docker available and configure AKOFLOW_API_TOKEN in your shell. From this example's directory, run:

go run ../../tools/daemon-local -root ../.. -example generative-ai/local-rag

This command validates the daemon connection, builds the declared image, registers the local environment and workflow, and submits a real run. The daemon owns execution and file transfers. Open the printed run ID in Desktop to inspect each activity.