A local Python pipeline that turns sensitive Argentine legal PDFs into structured, reviewable JSON without uploading documents to a SaaS model.
recreatedAI-generated editorial still life of the local, reviewable extraction workflow.
At a glance
What I owned
Period
2026
Role
Python extraction prototype development
Team
Independent engineering project
Users
People reviewing sensitive Argentine legal documents
Status
Working offline pipeline; public source; automated test sources
Contribution
Built extraction, local Qwen2.5-7B inference through llama.cpp, structured JSON generation, schema validation, repair, source anchoring, retries, evaluation, and tamper-evident audit logs.
Tradeoff
Keep documents and inference local while turning probabilistic model output into a structured proposal that can be measured, repaired, and reviewed.
Evidence
Public repository, documented local deployment, and automated test sources. The case makes no production-adoption or accuracy claim beyond the implemented evaluation workflow.
Model
Qwen2.5-7B
Runtime
llama.cpp + GGUF
Evaluation
Field-level golden set
Tests
automated test sources
01
Local inference is a product boundary
The pipeline extracts text and runs Qwen2.5-7B through llama.cpp on the local machine. Documents and inference do not leave the environment for a hosted model.
recreatedAI-generated editorial still life of the local-only processing boundary.
02
Model output must become a valid proposal
The LLM produces structured JSON, but the workflow does not trust the first response. JSON repair, schema validation, field-level source anchoring, and bounded retries either produce a reviewable result or an explicit failure.
03
Evaluation sources
The public repository includes a golden evaluation script, schema validation, source anchoring, review reports, and tests. These sources make the prototype available for inspection; no measured accuracy or production-adoption result is claimed here.
04
Reviewability over autonomy
The output is a proposal for human review, not a legal decision or automatic external action. Tamper-evident audit logs preserve what ran and how the result changed.
