Ein Flottenreparatur-Chatbot als Beispiel für RAG in einfachem Sprachstil mit Chroma und Ollama
RAG wird durch einen Flottenreparatur-Chatbot erklärt: Die Reparaturberichte der Autos kommen per WhatsApp, und Chroma, MiniLM-Embeddings sowie Llama 3.2 auf Ollama übernehmen die erste Analyse.
Quellen: Understanding RAG in simplified manner with an actual use case
RAG lässt sich durch einen konkreten Fall leichter verstehen als durch Diagramme, und eine kleine Fahrzeugflotte eignet sich hervorragend dafür. Stellen Sie sich einen Betreiber vor, dessen Fahrzeuge fast alle vom gleichen Modell sind – einem Daihatsu Mira – und der ein detailliertes Handbuch besitzt, das viele Reparaturfehler beschreibt. Wenn ein Fahrer ein Problem meldet, ermöglicht dieses Handbuch dem Betreiber oft, die häufigsten Symptome schnell zu diagnostizieren. Ein Mechaniker muss das Fahrzeug zwar trotzdem überprüfen, doch aus Sicht einer agierenden KI ist es vorteilhaft, die erste Diagnose von einem Retrieval-System durchführen zu lassen.
Das Szenario
Fahrer melden Probleme über WhatsApp an einen Chatbot. Die Nachricht erreicht über einen webhook eine API und wird verarbeitet; irgendwann dazwischen erstellt ein automatisierter Agent eine Diagnose mit einer möglichen Empfehlung, die als Diagnoseergebnis aufgezeichnet wird.
Ein Beispiel für einen Austausch: Der Fahrer schreibt, dass die Bremsen beim Betätigen ein quietschendes Geräusch machen und überprüft werden müssen. Eine automatische Diagnose könnte so aussehen:
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.
Wo RAG zum Einsatz kommt
Die Reparaturhandbücher dienen als diagnostisches Wissen. Eines davon ist ein PDF über Bremsbeläge. Wenn eine Nachricht des Fahrers eintrifft, übernimmt der RAG-Pipeline, wobei hier das Llama 3.2-Modell über Ollama genutzt wird, Chroma DB für die Vektorlagerei sowie das all-MiniLM-L6-v2-Modell über SentenceTransformerEmbeddingFunction zur Erstellung von Embeddings.
Der Ablauf erfolgt in sieben Schritten:
- Der Fahrer sendet eine Nachricht über den Chatbot.
- Die Nachricht erreicht den webhook.
- Der RAG-Pipeline wird ausgelöst.
- Zuerst findet die Datenerfassung statt. Die PDF-Handbücher werden gelesen und in Blöcke aufgeteilt, Metadaten wie Seitenzahl und Handbuchname werden hinzugefügt, jeder Block wird mit der sentence-transformer-Funktion in Embeddings umgewandelt, und die Vektoren werden in Chroma DB gespeichert.
- Die eingehende Nachricht wird anschließend verwendet, um Chroma abzufragen und den für diese Art von Reparaturfrage relevanten Kontext abzurufen.
- Der Prompt wird zusammen mit der abgerufenen Information und der Frage erweitert.
- Der erweiterte Prompt wird an das LLM gesendet, und dessen Antwort gelangt zurück zum Benutzer.
Ein Beispiel für ein Python-Skript zum Wartungshandbuch für Bremsscheiben implementiert all das:
"""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()
Das Demo-Handbuch, das angezeigt wird, ist ein kurzes Schulungsdokument:
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.
und die Abhängigkeiten befinden sich in einer Anforderungsdatei:
scikit-learn
pydantic
langchain
langchain-community
langchain-huggingface
langchain-ollama
langchain-text-splitters
chromadb
pypdf
sentence-transformers