Skip to content
Landry Tchouela
FR
All projects
Personal project · applied AIPublic code

Industrial RAG Assistant

An assistant that answers technical questions from plant manuals, and cites its sources.

Role
End-to-end design and development
Period
Fall 2026
Stack
Python, FastAPI, PostgreSQL, pgvector, Gemini, Next.js, Docker
right passage ranked first (3-document corpus)
12/12
rankings fused: vectors, text, exact codes
3
models to choose from: Gemini or Claude
2

Try it

Ask my background a question.

The assistant’s idea, applied to this site: your question retrieves the most relevant passages, and each answer cites its source.

01The problem

In a factory, the answer often already exists, but it is buried in manuals, maintenance procedures and datasheets. The assistant has to answer and show its sources.

02Architecture

  1. 01DocumentsManuals, procedures, datasheets
  2. 02IngestionFastAPI
  3. 03Hybrid searchPostgreSQL, pgvector
  4. 04Cited answerGemini, Next.js

03Decisions

  1. 1Define service boundaries, the data model and the v1 API contracts first: ingest, ask and health.
  2. 2Make every answer verifiable: the API checks the citations and discards an answer with no valid source.
  3. 3Combine vector search, French full-text and exact codes, because embeddings handle a reference like T88-PROBE-02 poorly.
  4. 4Decline to answer below a relevance threshold rather than make something up.
  5. 5Work without an API key: with no key, or when the provider is down, the app shows the most relevant passages unchanged, and says so.
  6. 6Treat passages as data: the model ignores instructions hidden inside documents.
  7. 7Run all services through Docker Compose.

04Where it stands

The full pipeline works: PDF ingestion, hybrid search, cited answers and automated evaluation in CI. On a small corpus of 3 documents, the right passage ranks first for 12 questions out of 12.