ProzessX
Academy ↗DEBook a free consultation
Example scenario · Field service

Use case: Multi-modal service co-pilot.

Technical architecture for field service: shorter mean time to repair through context-aware solution knowledge, right at the machine.

30 minutes, online, free and non-binding.

The key points

A RAG co-pilot searches maintenance logs, manuals and wiring diagrams. Hybrid search finds exact error codes and semantic problem descriptions at the same time. A photo of the nameplate plus a voice message automatically filter for the right device, and every answer comes with a cited source. Runs on-premise or in a private cloud.

Example scenario

This is the technical blueprint for a solution we build for field service technicians. Performance figures will only be published once measured in a concrete project.

The scenario: a technician is standing in front of a machine that's down, has no internet signal in the basement, and needs access to thousands of pages of manuals, wiring diagrams and maintenance logs.

We're not building a simple search engine here, but a retrieval-augmented generation system (RAG) with hybrid search. The technical goal: shorter repair times through context-aware solution knowledge in a matter of seconds. And just as important: avoiding hallucinations as far as possible through strict grounding.

The system architecture

Three layers of knowledge processing

1 · Ingestion layer (ETL)

Preparing documents

Unstructured data (PDFs, TIFF wiring diagrams, Word) gets processed via OCR. For parsing and splitting into manageable chunks, we use tools such as Unstructured.io.

  • Example: RecursiveCharacterTextSplitter
  • Chunk size 1000 tokens, overlap 200
2 · Storage (vector DB)

Storing meaning

We store the semantic meaning of the chunks as embeddings (vectors), for example in Qdrant or Pinecone, for fast similarity search.

  • Embedding model depends on hosting variant
  • Metric: cosine similarity
3 · Reasoning

Generating the answer

The orchestrator (for example LangChain) connects the question with the retrieved knowledge and generates the answer. The ReAct pattern matters here for logical reasoning.

  • Strict grounding
  • Mandatory sourcing
Deep dive

Why vector search alone isn't enough

Dense retrieval (vector): semantic context
  • Understands concepts like "the motor is running hot"
  • Finds "hydraulic overheating issues" even if someone just types "the pump is warm"
  • Often fails on exact identifiers like "error code E-404-X"
Hybrid search: the best of both worlds
  • BM25 searches exact keywords like part number "XJ-500-2" or error code "E33"
  • Vector search adds the semantic connection
  • Reciprocal Rank Fusion (RRF) merges both result lists and passes the best result to the language model
The technician loop

Four steps on site

1

Input processing

The technician photographs the nameplate and dictates: "What's the torque spec for the main bolt on this series?" Multimodal input from image and speech.

2

Query transformation

The system turns the often vague question into precise search queries (query expansion). Metadata filters, driven by image recognition, automatically narrow the search to the right machine series.

3

Citation & verification

The language model generates the answer, for example the prescribed torque value for a bolted connection, with a link to the original PDF and page number. No verifiable source, no output. That's our hard guardrail.

4

Feedback loop

The technician clicks "worked" or "wrong." This feedback feeds back into improving the index and the answers.

Request an architecture review
Technical specifications

What carries the business case

Performance

Response time

Target: an answer in a matter of seconds, even for complex hybrid searches. Measured during pilot operation.

Capacity

Context window

Depends on the chosen model and gets fixed during pilot operation.

Data security

On-premise

Private cloud or on-site server, your choice. No training on public data.

Business impact

Fewer follow-up queries

Target: fewer escalated follow-up queries in the back office and first-level support, measured during pilot operation.

Free download

The RAG architecture check for industry and service

Data ingestion setup

The blueprint for turning your own manuals into a working AI service.

Embedding and chunking

Best practices for preparing technical documents.

Hardware sizing

Sizing for on-premise operation.

Request the architecture guide →
Frequently asked questions

Tech FAQ

What's the difference between vector search and hybrid search?

Pure vector search finds documents by semantic connection. That's good, but often not enough in technical contexts. Hybrid search combines it with BM25 keyword matching. That way you find both the conceptual solution and the exact part number that a vector search easily misses.

Does the service co-pilot also work without an internet connection?

The core architecture can run entirely in your private cloud or on on-premise servers. If the technician is in the basement with no signal, the request can be buffered until the company network or mobile signal returns, depending on the deployment strategy.

How are AI hallucinations prevented?

We minimize hallucinations through strict grounding in the orchestrator. The model refers exclusively to the retrieved document chunks. If the manual contains no information, the answer is "information not found." In addition, every statement is linked with a source and page number.

Which document formats can be processed?

The ingestion layer processes nearly all unstructured formats: text files, Word documents, complex PDFs (including multi-column), HTML, and, via OCR, image files such as scanned TIFF wiring diagrams.

More on this

Agentic RAG explainedExample scenario: mechanical engineeringUse case: real estate acquisition with AISystem and tool consultingAI implementation for SMEsAI chatbot with RAGKnowledge Hub: practical AI knowledge

Shall we build your technical co-pilot?

The technology is ready. The challenge lies in clean data preparation and the architecture. Let's check whether your data is ready for RAG.

Sami Can Yolasigmaz
Sami Can YolasigmazYour contact

By submitting this form you agree to the processing of your data under our privacy policy .