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.
ingestchunkindexretrieveanswerevaluate
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 locally
git clone https://github.com/UFFeScience/akoflow-examples.git
cd akoflow-examples/generative-ai/local-rag
./run.sh
Execution is offline and uses only Python's standard library. The activity boundaries remain suitable for replacing the deterministic answer stage with a local Ollama model.