Home / Articles

A Fleet Repair Chatbot as a Plain-Language RAG Example With Chroma and Ollama

RAG explained with a fleet repair chatbot: car repair reports arrive over WhatsApp, and Chroma, MiniLM embeddings and Llama 3.2 on Ollama do the first pass.

Publisher: REACTAPP.TOP7 min read1636 words

This article is published in English.

Sources: Understanding RAG in simplified manner with an actual use case

RAG is easier to grasp through a concrete case than through diagrams, and a small car fleet makes a good one. Picture an operator whose cars are nearly all the same model, a Daihatsu Mira, and who keeps a detailed manual covering many repair defects. When a driver reports a problem, that manual often lets the operator troubleshoot the most common symptoms quickly. A mechanic still has to inspect the car, but from an agentic AI angle it's appealing to let retrieval handle the first diagnostic pass.

The scenario

Drivers report problems to a chatbot over WhatsApp. The message reaches an API through a webhook and gets processed, and somewhere in the middle an automated agent produces a diagnosis with a possible suggestion, which is recorded as the diagnosis output.

A sample exchange: the driver writes that the brakes make a screeching noise when pressed and need checking. An automated diagnosis might look like this:

The screeching noise when pressing the brake pedal is a symptom that requires attention.
Possible causes
- The screeching noise may be caused by:
 • Glazed or contaminated brake-pad friction material
• Loose, damaged, incorrectly installed, or missing pad hardware and shims
• Dry or seized caliper slide pins
• Debris, corrosion, scoring, or an uneven surface on the brake rotor
• Normal vibration characteristics of some pad and rotor combinations
Diagnostic checks
• Confirm when the sound occurs during a cautious test in a safe area
• Identify the wheel area producing the noise
• Inspect both the inner and outer brake pads for glazing, contamination, cracking, or uneven wear
• Check whether a wear indicator is touching the rotor and inspect all clips, shims, and mounting hardware
• Inspect the rotor for embedded debris, scoring, heat spots, corrosion, and excessive runout or thickness variation
• Check that the caliper piston and slide pins move correctly and inspect for damaged boots or brake-fluid leakage
Safety
Noise alone does not prove one cause. If the noise becomes grinding, braking performance is reduced, the vehicle pulls while braking, a brake warning light is illuminated, or brake fluid is leaking, stop driving and obtain qualified help immediately.

Where RAG fits

The repair manuals serve as the diagnostic knowledge. One of them is a PDF about brake pads. When a driver's message arrives, the RAG pipeline takes over, and the stack used here is the Llama 3.2 model served through Ollama, Chroma DB for vector storage and the all-MiniLM-L6-v2 model, via SentenceTransformerEmbeddingFunction, for embeddings.

The flow runs in seven steps:

  1. The driver sends a message through the chatbot.
  2. The message hits the webhook.
  3. The RAG pipeline is triggered.
  4. Retrieval comes first. The PDF manuals are read and split into chunks, metadata such as the page number and manual name is attached, each chunk is embedded with the sentence-transformer function, and the vectors go into Chroma DB.
  5. The incoming message is then used to query Chroma and fetch the context that matters for this type of repair question.
  6. The prompt is augmented with the retrieved context together with the question.
  7. The augmented prompt goes to the LLM, and its response comes back to the user.

A sample Python script for the brake-pad maintenance manual implements all of this:

"""A small, real RAG pipeline for the brake-pad maintenance manual."""

import os
import re
from pathlib import Path

os.environ["TOKENIZERS_PARALLELISM"] = "false"

import chromadb
from chromadb.utils.embedding_functions import SentenceTransformerEmbeddingFunction
from langchain_ollama import OllamaLLM
from langchain_text_splitters import RecursiveCharacterTextSplitter
from pypdf import PdfReader


PDF_PATH = Path(__file__).with_name("brake_pad_maintenance_manual.pdf")
USER_QUERY = "My brakes are making screeching noises when I press the pedal."


def ingest_pdf(collection, pdf_path: Path) -> None:
    """Extract, chunk, and add a real PDF to ChromaDB."""
    if not pdf_path.exists():
        raise FileNotFoundError(f"Manual not found: {pdf_path}")

    splitter = RecursiveCharacterTextSplitter(chunk_size=1200, chunk_overlap=150)
    chunks = []
    metadatas = []
    ids = []

    for page_number, page in enumerate(PdfReader(pdf_path).pages, start=1):
        page_text = re.sub(r"\s+", " ", page.extract_text() or "").strip()

        for chunk_number, chunk in enumerate(splitter.split_text(page_text)):
            if not chunk.strip():
                continue

            chunks.append(chunk)
            metadatas.append(
                {
                    "source_file": pdf_path.name,
                    "page": page_number,
                }
            )
            ids.append(f"page_{page_number}_chunk_{chunk_number}")

    if not chunks:
        raise ValueError(f"No text could be extracted from {pdf_path.name}.")

    collection.add(documents=chunks, metadatas=metadatas, ids=ids)
    print(f"Ingested {len(chunks)} chunks from {pdf_path.name}.\n")


def generate_llm_response(prompt: str) -> str:
    """Generate a grounded answer with the local Ollama model."""
    return OllamaLLM(model="llama3.2", temperature=0).invoke(prompt)


def run_rag_pipeline(collection, user_query: str):
    """Retrieve relevant PDF passages, augment the prompt, and generate."""
    results = collection.query(
        query_texts=[user_query],
        n_results=min(2, collection.count()),
    )

    retrieved_chunks = results["documents"][0]
    retrieved_metadata = results["metadatas"][0]

    if not retrieved_chunks:
        raise ValueError("No relevant manual passages were retrieved.")

    context = "\n\n".join(
        f"[{source['source_file']}, page {source['page']}]\n{chunk}"
        for chunk, source in zip(retrieved_chunks, retrieved_metadata)
    )

    augmented_prompt = f"""
You are a cautious fleet mechanic assistant.

Answer strictly from the supplied manual passages in no more than 180 words.
For a reported symptom, use these four headings: Assessment, Possible causes,
Diagnostic checks, and Safety. Make clear that noise alone does not prove one
cause. Cover the relevant checks in concise bullets without claiming that an
inspection has already been performed or asking the user to continue. Do not
mention a measurement unless it appears in the context and directly helps
answer the question. Cite the source file and page number. If the answer is
absent, say it was not found in the manual.

=== MANUAL CONTEXT ===
{context}

=== USER QUERY ===
{user_query}

=== ANSWER ===
"""

    response = generate_llm_response(augmented_prompt).rstrip()
    citations = sorted(
        {
            f"{source['source_file']}, page {source['page']}"
            for source in retrieved_metadata
        }
    )
    response = f"{response}\n\nSources: {'; '.join(citations)}"

    return response, augmented_prompt


def main() -> None:
    embedding_function = SentenceTransformerEmbeddingFunction(
        model_name="all-MiniLM-L6-v2"
    )
    collection = chromadb.Client().create_collection(
        name="brake_pad_manual_rag",
        embedding_function=embedding_function,
    )

    ingest_pdf(collection, PDF_PATH)
    response, assembled_prompt = run_rag_pipeline(collection, USER_QUERY)

    print("=== AUGMENTED PROMPT SENT TO LLM ===")
    print(assembled_prompt)
    print("=== FINAL GENERATED RESPONSE ===")
    print(response)


if __name__ == "__main__":
    main()

The demo manual it reads is a short training document:

Demo Brake-Pad Maintenance Manual

Training document only. Brake systems are safety-critical. Always use the vehicle manufacturer's service
manual, specified service limits, approved lifting points, and torque values.
Brake-pad inspection
1. Park on a level surface, prevent vehicle movement, and lift the vehicle only at approved points. Support it
securely with rated stands.
2. Remove the wheel using the vehicle manufacturer's procedure.
3. Inspect the inner and outer pads. Check friction material at several points and compare it with the vehiclespecific
minimum thickness.
4. Replace pads that are at or below their service limit, contaminated, cracked, damaged, or wearing unevenly.
5. Inspect the rotor for scoring, heat damage, cracks, and excessive corrosion. Measure rotor thickness and
runout against vehicle-specific limits.
6. Check the caliper, slide pins, dust boots, and brake hose for seizure, damage, or fluid leakage.
Symptom: screeching when the brake pedal is pressed
A high-pitched screech or squeal during braking can indicate that a brake-pad wear indicator is contacting the
rotor, but noise alone does not prove that the pads are worn out.
Other possible causes
Glazed or contaminated brake-pad friction material.
Loose, damaged, incorrectly installed, or missing pad hardware and shims.
Dry or seized caliper slide pins that cause uneven pad contact.
Debris, corrosion, scoring, or an uneven surface on the brake rotor.
Normal vibration characteristics of some pad and rotor combinations.
Possible diagnostic procedure
1. Confirm when the sound occurs during a cautious test in a safe area. Note whether it occurs only while
braking, at low or high speed, or continuously while the wheel rotates.
2. Identify the wheel area producing the noise. Do not assume that the loudest apparent location is the exact
source.
3. Inspect both the inner and outer brake pads. Compare their thickness with the vehicle-specific service limit
and look for glazing, contamination, cracking, or uneven wear.
4. Check whether a wear indicator is touching the rotor and inspect all clips, shims, and mounting hardware.
5. Inspect the rotor for embedded debris, scoring, heat spots, corrosion, and excessive runout or thickness
variation.
6. Check that the caliper piston and slide pins move correctly and inspect for damaged boots or brake-fluid
leakage.
7. Correct the confirmed cause using the vehicle manufacturer's procedure, then verify the repair with a
cautious low-speed brake test.
Stop driving and obtain qualified help if the noise becomes grinding, braking performance is reduced, the
vehicle pulls while braking, a brake warning light is illuminated, or brake fluid is leaking.
Brake-pad replacement
1. Follow the model-specific caliper removal procedure. Never let the caliper hang from the brake hose.
2. Retract the caliper piston using the correct tool and procedure. Put an electronic parking brake into service
mode when the manufacturer requires it.
3. Clean the pad supports and inspect the hardware. Apply only manufacturer-approved brake lubricant to
specified contact points. Keep lubricant away from pad and rotor friction surfaces.
4. Install new pads as a complete axle set. Replace clips, shims, or wear sensors when required.
5. Reinstall the caliper and wheel. Tighten every fastener to the vehicle manufacturer's torque specification.
6. Before moving the vehicle, pump the brake pedal until it is firm. Check the brake-fluid level and inspect for
leaks.
7. Follow the pad manufacturer's bedding procedure, then perform a cautious low-speed function test in a safe
area.
Stop and obtain qualified help if
The pedal remains soft, brake fluid is leaking, the caliper is damaged or seized, the rotor is below its service limit,
or any required specification is unavailable.

and the dependencies live in a requirements file:

scikit-learn
pydantic
langchain
langchain-community
langchain-huggingface
langchain-ollama
langchain-text-splitters
chromadb
pypdf
sentence-transformers