Training course · RAG & LLM Applications · Rust

RAG & LLM Applications for Rust Developers

Develop RAG and LLM applications: embeddings, vector databases, chunking, retrieval, evaluation, cost control and data protection.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

“RAG & LLM Applications for Rust Developers” is a hands-on course for roles such as Rust developers working on systems and back-end projects, C and C++ developers moving to Rust or porting modules and Embedded and IoT developers using Rust. Rather than learning RAG & LLM Applications in the abstract, you work on tasks from your daily routine – with examples, exercises and templates from Rust.

Retrieval-augmented generation connects language models to your own knowledge: manuals, contracts, tickets, wikis or product data are made searchable and handed to the model as context at runtime. The result is assistants that give grounded answers with citations instead of hallucinating. In this two-day course you build a complete RAG pipeline, from document preparation through embeddings and a vector database to answer generation, and you learn which levers actually determine quality.

Day two takes you from prototype to robust application. You compare chunking strategies, combine semantic and lexical search, apply reranking, metadata filters and query rewriting, and measure the effect with systematic evaluations. You also cover prompt caching, cost control, latency optimisation, document-level access control and privacy-compliant operation with an eye on GDPR and the EU AI Act. By the end you know when classic RAG is enough, when a large context window or agentic retrieval is the better option, and how to justify your architecture choices.

Rust is gaining ground wherever memory safety and performance have to go hand in hand: in systems software, embedded projects, network services, WebAssembly and security-critical components. The learning curve is steep – ownership, lifetimes, traits and async runtimes challenge even experienced developers. AI coding assistants and agents prove to be patient sparring partners here: they explain borrow checker errors, suggest suitable ownership structures, write tests and property-based tests, port C or C++ modules incrementally and work through Clippy lints. Because the compiler gives very precise feedback, agents can iterate all the way to compiling, safe code. This course teaches you to exploit that feedback loop and to scrutinise unsafe code with particular care.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • Rust developers working on systems and back-end projects
  • C and C++ developers moving to Rust or porting modules
  • Embedded and IoT developers using Rust
  • Security and platform teams focused on memory safety

Typical challenges we address

  • Hard-to-understand borrow checker and lifetime errors
  • Complex trait hierarchies, generics and async code with Tokio
  • Laborious porting of existing C or C++ codebases across FFI boundaries
  • Handling unsafe blocks responsibly and justifying each one

What you will be able to do

  • You build a complete RAG pipeline from document preparation to answers with citations.
  • You choose embedding model, chunking strategy and vector database on solid grounds.
  • You improve retrieval quality with hybrid search, reranking and metadata filters.
  • You measure application quality with systematic evaluations and detect regressions.
  • Use AI agents as sparring partners for ownership, lifetimes, traits and async Rust.
  • Generate tests, ports and services and verify them with the compiler, Clippy and Miri.
  • Systematically assess generated unsafe and FFI code for memory safety.

Course outline

Day 1

Module 1 Foundations of RAG and LLM applications
  • Anatomy of a RAG pipeline: ingestion, indexing, retrieval, generation
  • Understanding embeddings: semantic similarity, dimensions, model selection
  • Weighing RAG against fine-tuning and long context windows
  • Structured outputs, citations and dealing with hallucinations
Module 2 Document preparation and chunking
  • Reliably extracting PDFs, Office documents, HTML and tables
  • Chunking strategies: fixed size, structure-aware, semantic, with overlap
  • Enriching metadata and generating contextual summaries per chunk
  • Incremental updates and deletion of documents in the index
Module 3 Vector databases and retrieval strategies
  • Comparing vector databases and extensions such as pgvector, Qdrant, Weaviate or OpenSearch
  • Hybrid search combining vector and full-text search with BM25
  • Reranking, metadata filtering and query rewriting
  • Agentic retrieval: letting the model decide on search steps and tools
Module 4 Evaluation and quality assurance
  • Building and maintaining test sets from real user questions
  • Retrieval metrics such as recall and precision, and answer metrics such as faithfulness
  • Using and calibrating LLM-as-a-judge sensibly
  • Regression testing when chunking, model or prompt changes

Day 2

Module 5 Operations, cost and data protection
  • Prompt caching, batch processing and model choice to cut costs
  • Optimising latency and streaming responses
  • Document-level permissions, tenant isolation and protection against prompt injection
  • Data protection: data residency, processing agreements, deletion policies, GDPR and the EU AI Act
Module 6 Practice lab: Rust
  • Understanding and fixing compiler errors
  • Tests and property-based tests
  • Porting C and C++ modules
  • Async services with Tokio
  • Clippy and idiomatic code
  • Reviewing unsafe code
Module 7 Data protection, quality & transfer to daily work
  • Rust is often used in security-critical components for which the Cyber Resilience Act sets requirements on vulnerability handling and SBOMs. Check new crates for vulnerabilities and licences with cargo-audit or cargo-deny, and treat proprietary systems code as confidential when using cloud-hosted models.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

Understanding and fixing compiler errors

The assistant explains borrow checker and lifetime errors in plain language, deliberately proposes alternative ownership structures such as references, Rc or cloning, and iterates with cargo check until the build is clean.

Tests and property-based tests

The AI writes unit and integration tests, doc tests and property-based tests with proptest that check invariants over many generated inputs, uncovering edge cases in parsers or algorithms.

Porting C and C++ modules

Existing code is moved to Rust module by module, FFI bindings are created with bindgen or cbindgen and behaviour is safeguarded by shared tests run against the old and new implementations.

Async services with Tokio

Specifications become HTTP or gRPC services built with Axum or Tonic, including structured error types, graceful shutdown, tracing and sensible handling of cancellation and timeouts.

Clippy and idiomatic code

Clippy lints are worked through systematically, error handling standardised with thiserror or anyhow, and iterators, pattern matching and traits used idiomatically. Existing tests safeguard every change.

Reviewing unsafe code

The agent inventories unsafe blocks, documents their safety invariants, proposes safe alternatives and runs Miri to detect undefined behaviour. Each justification is recorded as a SAFETY comment in the code.

Possible hands-on projects

Fast log parser

A Rust CLI that streams large log files, detects patterns with regular expressions and outputs statistics – with benchmarks comparing it against a scripting-language version.

Axum microservice

A small REST service using Axum, SQLx, structured tracing and integration tests, planned and implemented end to end by an AI agent.

WebAssembly module

A compute-heavy function, such as image processing or validation, packaged as a WebAssembly module with wasm-bindgen and embedded in a simple web page.

Prerequisites

Solid programming skills in Python (or TypeScript as an alternative), basic knowledge of databases and REST APIs, and some experience with LLM APIs. Basic Rust experience with Cargo, ownership and traits, plus experience in at least one other systems or back-end language.

Technical requirements

A laptop with Python, Git, Docker and a code editor, plus API access to at least one LLM and embedding provider. Credentials for the exercises can be provided if needed.

Data protection & compliance

Rust is often used in security-critical components for which the Cyber Resilience Act sets requirements on vulnerability handling and SBOMs. Check new crates for vulnerabilities and licences with cargo-audit or cargo-deny, and treat proprietary systems code as confidential when using cloud-hosted models.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Wed, 25 November 2026 – Thu, 26 November 2026 Online Request
  • Tue, 8 December 2026 – Wed, 9 December 2026 Salzburg Request
  • Thu, 17 December 2026 – Fri, 18 December 2026 Online Request
  • Tue, 19 January 2027 – Wed, 20 January 2027 Online Request
  • Wed, 27 January 2027 – Thu, 28 January 2027 Augsburg Request
  • Wed, 10 February 2027 – Thu, 11 February 2027 Online Request

Frequently asked questions

When is RAG better than fine-tuning?

RAG is the right choice when a model needs access to current, extensive or frequently changing knowledge and should cite its sources. Fine-tuning mainly changes style, format or specialised behaviour. In many projects RAG is the faster, cheaper and more controllable route, sometimes complemented by fine-tuning for niche tasks.

Which vector database should we use?

That depends on data volume, existing infrastructure, filtering needs and operating model. If you already run PostgreSQL, pgvector often takes you a long way, while specialised systems shine with large datasets and hybrid search. In the course you compare several options hands-on and derive criteria for your own decision.

How can RAG be run in a GDPR-compliant way?

Key factors are choosing providers with suitable data residency and a data processing agreement, enforcing document-level permissions, having a deletion policy for the index and logs, and minimising personal data. For highly sensitive data, self-hosted models are also an option. We work through these choices using realistic architectures.

Can AI help me get started with Rust?

Very much so. AI assistants explain compiler errors patiently and in the context of your own code, show alternative approaches and explain why the borrow checker rejects a construct. The key is to understand the explanations rather than accept suggestions blindly, so the course relies on hands-on exercises in which you work out solutions together with the AI.

How reliable are AI ports from C++ to Rust?

They work well for clearly bounded modules when behaviour is protected by tests. The tricky parts are pointer arithmetic, shared mutable state or undefined behaviour in the original. On the course you learn to port incrementally, run differential tests against the old implementation and keep unsafe code to a deliberate minimum.

How much does “RAG & LLM Applications for Rust Developers” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for Rust Developers

More RAG & LLM Applications courses

All 29 RAG & LLM Applications courses

RAG & LLM Applications · MunichRAG & LLM Applications · SalzburgRAG & LLM Applications · BerlinRAG & LLM Applications · AugsburgRAG & LLM Applications · HanoverRAG & LLM Applications · BremenRAG & LLM Applications · StuttgartRAG & LLM Applications · KaiserslauternRAG & LLM Applications · Online