Diploma in Industrial RAG with Documentation and Logs
Online postgraduate diploma of 800 hours in industrial RAG over documentation and logs, with 8 modules covering retrieval-augmented architecture, technical documentation ingestion, log ingestion and analysis, advanced retrieval, reliable generation and agents, evaluation and security, and industrial deployment, with an assigned technical tutor.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Design RAG architectures adapted to technical documentation and logs.
Ingest complex documents with tables, figures and validity metadata.
Index and retrieve log events using hybrid search.
Apply advanced techniques such as reranking, GraphRAG and permission filters.
Generate answers with citations and hallucination control.
Evaluate RAG systems with automatic metrics and expert review.
Deploy secure RAG assistants integrated with industrial systems.
Who it's for
- Generative AI engineers.
- Applied machine learning engineers.
- AI solutions architects.
- Technical knowledge management specialists.
- Digital reliability and maintenance engineers.
- Conversational assistant developers.
- Engineering or science graduates aiming to enter industry and manufacturing.
What you'll work with
- Regulation (EU) 2024/1689 (Artificial Intelligence Act)
- ISO/IEC 42001:2023 (AI management systems)
- ISO/IEC 23894:2023 (AI risk management)
- Regulation (EU) 2016/679 – GDPR (General Data Protection Regulation)
- ISO/IEC 27001:2022 (information security)
- NIST AI 600-1 (generative AI profile)
- ISO/IEC 22989:2022 (AI concepts and terminology)
- LlamaIndex
- LangChain
- Qdrant
- OpenSearch
- RAGAS
8 modules
1.1Language models and knowledge limitations1.2RAG architecture: retriever and generator1.3Dense embeddings and semantic similarity1.4BM25 lexical search1.5Hybrid search and rank fusion1.6Vector databases: HNSW and IVF indexes1.7Context window and token budget1.8RAG versus fine-tuning1.9Industrial cases: manuals, procedures and logs1.10Workshop: first RAG over a maintenance manual
2.1Extracting PDFs, drawings and datasheets2.2OCR and scanned documents2.3Tables, diagrams and figures2.4Structure-based chunking strategies2.5Metadata: equipment, version and validity2.6Normalising technical terminology2.7Document version control2.8Handling multilingual documents2.9Tools: Unstructured and Docling2.10Practical: ingestion pipeline for plant procedures
3.1Log formats and parsing with Drain3.2Event normalisation and templates3.3Time windows and correlation3.4Enrichment with asset context3.5Indexing in Elasticsearch and OpenSearch3.6Embeddings for event sequences3.7Incident summarisation from logs3.8Volume, retention and sampling3.9Sensitive data in logs3.10Lab: semantic search over a system's logs
4.1Reranking with cross-encoders4.2Query expansion and rewriting4.3HyDE and hypothetical queries4.4Multi-hop retrieval across documents4.5GraphRAG and knowledge graphs4.6Metadata and permission filters4.7Retrieval over tables and SQL4.8Multimodal RAG with equipment images4.9Fine-tuning domain embeddings4.10Case study: hybrid search with reranking
5.1Prompt design with source citations5.2Structured responses and JSON5.3Reducing hallucinations5.4Refusal when evidence is lacking5.5Agents with tools and function calling5.6Orchestration with LangChain and LlamaIndex5.7Model Context Protocol for integrations5.8Conversational memory and session context5.9Local models versus APIs5.10Workshop: diagnostic assistant with citations
6.1Domain evaluation datasets6.2Retrieval metrics: recall@k and MRR6.3Faithfulness and relevance with RAGAS6.4Human evaluation with experts6.5Indirect prompt injection6.6Document access control6.7Leakage of confidential information6.8Risks under the OWASP Top 10 for LLMs6.9Logging and auditing of responses6.10Practical: RAGAS test bench
7.1On-premise and cloud architectures7.2Latency, cost and semantic caching7.3Incremental index updates7.4Integration with CMMS and ticketing systems7.5Interfaces for field technicians7.6Observability with LangSmith and Langfuse7.7User feedback7.8Governance under the AI Act7.9Change management in operations7.10Case study: deployment in a maintenance centre
8.1Selecting the corpus and use case8.2Ingesting documentation and logs8.3Index and retrieval design8.4Generation with citations8.5Quantitative and expert evaluation8.6Security and access control8.7Deployment plan8.8Cost and latency analysis8.9Report and presentation8.10Final project: final review with the tutor
How you'll learn
100% online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so it can be combined with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is LlamaIndex, LangChain, Qdrant, OpenSearch and RAGAS, in free, academic or evaluation versions. Real procedures are studied: a query assistant over technical manuals and procedures, semantic search and incident summarisation in logs, and evaluation of answer faithfulness and security. Assessment is continuous by module plus the final integrative project.
Standards covered: Regulation (EU) 2024/1689 (AI Act), ISO/IEC 42001:2023, ISO/IEC 23894:2023, Regulation (EU) 2016/679 (GDPR), ISO/IEC 27001:2022, NIST AI 600-1, ISO/IEC 22989:2022.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Where this takes you
Requirements
- Prior technical training or professional experience in the sector. No university degree is required.
- An internet connection and a computer capable of running the programme's software.
- English sufficient to read technical standards.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme totals 800 hours over 6–8 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with LlamaIndex, LangChain, Qdrant, OpenSearch and RAGAS, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.
A SEIUM Institute diploma, awarded on passing the continuous assessment and the final project. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.
Yes. Modules passed are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.
Prior technical training or professional experience in the sector (no university degree required), a computer able to run the software and English sufficient to read technical standards.
Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.
Related programmes
Diploma in Governance, Quality and Operational Data Catalog
Online postgraduate diploma of 800 hours in operational data governance, quality and cataloguing. 8 modules covering ISO 8000-61, ISO/IEC 25012:2008 and ISO/IEC 38505-1, with OpenMetadata, DataHub,…
Diploma in Dataset Generation and Realism Metrics
Online postgraduate diploma of 800 hours in dataset generation and realism metrics. 8 modules covering the dataset life cycle, capture and annotation, synthetic data generation, realism…
Diploma in Conformity Assessment and AI Audits
Online postgraduate diploma of 800 hours in conformity assessment and AI audits: 8 modules covering conformity assessment, management system audits, technical model audits, bias and fairness,…
More in Data, AI, Simulation & Analytics
All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships