back_office_ops · services · workflow

Building a RAG system for internal engineering knowledge search from 1 TB of project documents

An engineering company needed an internal natural language chat tool to search across nearly a decade of project history totaling 1 TB of mixed technical documents—including OrcaFlex simulation files central to the offshore industry—without relying on external APIs for confidentiality reasons.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Document filtering by extension and pattern
A filtering system excluded files by extension and name patterns before indexing to prevent non-text assets from entering the pipeline.
Tools used
Ollamanomic-embed-textLlamaIndexChromaDBSQLiteFlaskStreamlitPythonAzure Blob Storage · partnerDocker ComposeNVIDIA Container ToolkitGunicornllama3.2:3b
Outcome

The RAG system reached production with 738,470 vectors and a 54 GB index in ChromaDB, achieved a 54% reduction in files to index through filtering, and is described as fast, reliable, and useful for colleagues. The GPU indexing phase cost 184 euros on Hetzner.

What failed first

LlamaIndex overflowed the laptop's RAM when processing large non-text files; a custom checkpoint system suffered data corruption and was too slow; the laptop's integrated GPU required 4-5 hours per 500 MB; and the production VM had only 100 GB of disk, far short of the full document corpus.

Results
Time saved4-5 hours per 500 MB
Volume54%
Cost replaced184 euros
Source

https://en.andros.dev/blog/aa31d744/from-zero-to-a-rag-system-successes-and-failures/

How we source this →

Grounding & classification
Source type: technical build writeup
43 fields verified against source quotes.
conversational aienterprise searchknowledge searchragknowledge basepolicy documentbuilder submittedfailure mode describedhuman review describedmetric backedproduction runtime claimedtools describedworkflow describedenergyprofessional servicesemployee productivitytime savedtechnical build writeupback office opsrag answering