Fercedferced
Back to projects

AI / Automation

DocuMind.

On-premise pipeline that processes PDFs with Qwen 2.5 7B running locally. A single Go binary extracts, analyzes and returns structured JSON — zero external APIs, zero data to third parties.

GoLLMllama.cppS3Queue
~/documind
$./documind start
[queue]watching input/ ...
[llm]qwen2.5-7b loaded (4.4GB)
[dash]http://localhost:9090
[queue]processing factura-0042.pdf
[llm]extracted 12 fields → output/
[queue]✓ done in 3.2s
$_
01 / Problem

On-premise pipeline that processes PDFs with Qwen 2.5 7B running locally. A single Go binary extracts, analyzes and returns structured JSON — zero external APIs, zero data to third parties.

02 / Decision

A direct architecture around Go, LLM, llama.cpp to keep the product understandable and maintainable.

03 / Result

On-premise pipeline that processes PDFs with Qwen 2.5 7B running locally. A single Go binary extracts, analyzes and returns structured JSON — zero external APIs, zero data to third parties.