Strona główna / Artykuły

Bot do naprawy floty jako przykład RAG w prostym języku z użyciem Chromy i Ollamy

RAG wyjaśniono za pomocą chatbota do naprawy floty: raporty z napraw samochodów przychodzą przez WhatsApp, a Chroma, embeddingi MiniLM oraz Llama 3.2 w Ollama przeprowadzają pierwszą analizę.

Wydawca: REACTAPP.TOP7 min czytania1636 słów

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

RAG jest łatwiejszy do zrozumienia poprzez konkretny przypadek niż za pomocą diagramów, a niewielka flota samochodów stanowi doskonały przykład. Wyobraźmy sobie operatora, którego samochody to niemal wyłącznie ten sam model – Daihatsu Mira – i który posiada szczegółowy podręcznik opisujący liczne usterki. Gdy kierowca zgłasza problem, ten podręcznik często pozwala operatorowi szybko zdiagnozować najczęstsze objawy. Mechanik nadal musi sprawdzić samochód, ale z punktu widzenia sztucznej inteligencji typu agent atrakcyjne jest pozostawienie pierwszej fazy diagnostyki systemowi do wyszukiwania informacji.

Sytuacja

Kierowcy zgłaszają problemy botowi czatowemu przez WhatsApp. Wiadomość trafia do API za pośrednictwem webhooka i jest przetwarzana, a w pewnym momencie automatyczny agent tworzy diagnozę wraz z możliwą sugestią, która jest zapisywana jako wynik diagnostyki.

Przykład wymiany informacji: kierowca pisze, że hamulce wydają piskliwy dźwięk przy naciskaniu i wymagają sprawdzenia. Automatyczna diagnostyka mogłaby wyglądać w ten sposób:

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.

Gdzie pasuje RAG

Manualy serwisowe stanowią wiedzę diagnostyczną. Jeden z nich to plik PDF dotyczący tarcz hamulcowych. Gdy przychodzi wiadomość od kierowcy, przejmuje kontrolę pipeline RAG, a używany tu model to Llama 3.2 dostarczany przez Ollama, Chroma DB do przechowywania wektorów oraz model all-MiniLM-L6-v2 za pośrednictwem SentenceTransformerEmbeddingFunction do tworzenia wektorów.

Proces przebiega w siedmiu krokach:

  1. Kierowca wysyła wiadomość przez chatbota.
  2. Wiadomość trafia do webhooka.
  3. Uruchamiany jest pipeline RAG.
  4. Najpierw następuje pobieranie danych. Manualy w formacie PDF są czytane i dzielone na fragmenty, do których dołączane są metadane takie jak numer strony i nazwa manualu, każdy fragment jest przetwarzany za pomocą funkcji sentence-transformer, a uzyskane wektory są przechowywane w Chroma DB.
  5. Nadchodząca wiadomość jest następnie wykorzystywana do zapytania Chromy w celu pobrania kontekstu istotnego dla tego typu pytania dotyczącego napraw.
  6. Pytanie jest wzbogacane o pobrany kontekst wraz z samym pytaniem.
  7. Wzbogacone pytanie trafia do modelu LLM, a jego odpowiedź wraca do użytkownika.

Przykładowy skrypt w Pythonie do podręcznika konserwacji tarcz hamulcowych implementuje to wszystko:

"""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()

Manual demonstracyjny, który jest czytany, to krótki dokument szkoleniowy:

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.

a zależności znajdują się w pliku wymagań:

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