Un chatbot de réparation de flotte en tant qu’exemple de RAG en langage simple avec Chroma et Ollama
RAG expliqué à l’aide d’un chatbot de réparation de flotte : les rapports de réparation de véhicules arrivent par WhatsApp, et Chroma, les embeddings MiniLM ainsi que Llama 3.2 sur Ollama effectuent la première analyse.
Sources: Understanding RAG in simplified manner with an actual use case
RAG est plus facile à comprendre à travers un cas concret qu’à l’aide de diagrammes, et un petit parc de voitures constitue un bon exemple. Imaginez un opérateur dont les voitures sont presque toutes du même modèle, une Daihatsu Mira, et qui dispose d’un manuel détaillé couvrant de nombreux défauts de réparation. Lorsqu’un conducteur signale un problème, ce manuel permet souvent à l’opérateur de diagnostiquer rapidement les symptômes les plus courants. Un mécanicien doit encore inspecter la voiture, mais du point de vue d’une IA agente, il est avantageux de laisser le système de récupération effectuer la première étape de diagnostic.
Le scénario
Les conducteurs signalent leurs problèmes à un chatbot via WhatsApp. Le message atteint une API par l’intermédiaire d’un webhook et est traité ; à un moment donné, un agent automatisé établit un diagnostic accompagné d’une suggestion possible, qui est enregistrée comme résultat du diagnostic.
Exemple d’échange : le conducteur indique que les freins émettent un bruit strident lorsqu’ils sont actionnés et doivent être vérifiés. Un diagnostic automatique pourrait ressembler à ceci :
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.
Où RAG trouve sa place
Les manuels de réparation constituent les connaissances diagnostiques. L’un d’eux est un PDF concernant les disques de frein. Lorsqu’un message du conducteur arrive, le pipeline RAG prend le relais ; le modèle utilisé ici est Llama 3.2 fourni via Ollama, Chroma DB pour le stockage vectoriel, ainsi que le modèle all-MiniLM-L6-v2, via SentenceTransformerEmbeddingFunction, pour les embeddings.
Le processus s’effectue en sept étapes :
- Le conducteur envoie un message par l’intermédiaire du chatbot.
- Le message atteint le webhook.
- Le pipeline RAG est déclenché.
- D’abord la récupération des informations : les manuels PDF sont lus et divisés en fragments, des métadonnées telles que le numéro de page et le nom du manuel y sont ajoutées, chaque fragment est transformé en embedding à l’aide de la fonction sentence-transformer, et les vecteurs sont stockés dans Chroma DB.
- Le message reçu est ensuite utilisé pour interroger Chroma et récupérer le contexte pertinent pour ce type de question de réparation.
- Le prompt est enrichi du contexte obtenu ainsi que de la question elle-même.
- Le prompt enrichi est envoyé à l’LLM, et sa réponse revient à l’utilisateur.
Un exemple de script Python pour le manuel de maintenance des disques de frein met en œuvre tout ceci :
"""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()
Le manuel de démonstration qu’il lit est un court document pédagogique :
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.
et les dépendances se trouvent dans un fichier de spécifications :
scikit-learn
pydantic
langchain
langchain-community
langchain-huggingface
langchain-ollama
langchain-text-splitters
chromadb
pypdf
sentence-transformers