ORIA · client engagement (confidential)

Generative AI and RAG on business data

Contribution to Python solutions for the intelligent use of business data: generative-AI model integration, backend services and production-oriented processing automation.

Client engagementSince 2025

Context

A client held business data and documents from several sources that were hard to use and query. The engagement, carried out as part of a team, aimed to make them usable by production AI processing. The client is not named (confidentiality).

Problem

Collect and structure heterogeneous data, then enable reliable semantic search and generative-AI processing over business documents, with services exposed through APIs.

Approach

  1. Python ETL pipelines to collect, transform and integrate data from several sources.
  2. RAG pipeline: vectorisation of business documents, Hugging Face Transformers embeddings and a FAISS vector index for contextual retrieval.
  3. Integration and adaptation of the Mistral 7B model for AI processing on domain-specific business data.
  4. Python modules for automatic text processing, document structuring and content indexing.
  5. Backend services and REST APIs with FastAPI; transformed data loaded into PostgreSQL with a suitable relational structure.
  6. Contribution to evaluating, tuning and optimising the performance of the AI pipelines.

Stack

  • Python
  • ETL/ELT
  • RAG
  • Hugging Face
  • FAISS
  • Mistral 7B
  • PyTorch
  • FastAPI
  • PostgreSQL
  • React
  • Git

Status

Client engagement

Engagement delivered through ORIA, as part of a team; client details not published.

What I learned

A useful RAG depends as much on document preparation — chunking, structuring, indexing — as on the choice of model. And an open model such as Mistral 7B keeps data control on the client side.