How to Summarise Shopify Products with LangChain

import os

import requests
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_openai import ChatOpenAI

# Step 1: Define target Shopify product URLs and the extraction schema
product_urls = [url.strip() for url in os.environ["SHOPIFY_PRODUCT_URLS"].split(",")]  # public Shopify product page URLs

schema = {
    "name": "The product's display name",
    "price": "The current selling price, including currency if shown",
    "availability": "Whether the product is in stock, sold out, or otherwise unavailable",
    "description": "The product description in plain prose",
}

# Step 2: Call Distill — synchronous, no job_id, no polling, no download step
# Distill requires a paid plan; the free tier returns 402
response = requests.post(
    "https://api.enconvert.com/v2/distill",
    headers={
        "X-API-Key": os.environ["ENCONVERT_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
        "urls": product_urls,
        "schema": schema,
    },
    timeout=120,  # increase for larger batches
)
if response.status_code == 402:
    raise RuntimeError("Distill requires a paid plan")
response.raise_for_status()

# Step 3: Parse results — failed pages arrive as rows, not as request errors
products = []
for result in response.json()["results"]:
    if result["status"] != "completed":
        print(f"Skipped {result['url']}: {result['status']}")
        continue
    if result.get("render_quality", 1.0) < 0.5:
        # Low render_quality flags anti-bot challenges or login walls
        print(f"Low render quality for {result['url']}: {result['render_quality']}")
        continue
    # result["data"] contains exactly the schema keys above
    products.append({"url": result["url"], **(result.get("data") or {})})

if not products:
    raise RuntimeError("No Shopify products were extracted successfully")

print(f"Extracted {len(products)} products")

# Step 4: Pass the structured product data into a LangChain chain
prompt = ChatPromptTemplate.from_messages([
    (
        "system",
        "Summarise Shopify product records for a merchandising review. "
        "Use only the supplied structured data. Do not invent availability, pricing, or product features.",
    ),
    ("human", "Summarise these products:\n\n{products}"),
])

chain = prompt | ChatOpenAI(model="gpt-4.1", api_key=os.environ["OPENAI_API_KEY"]) | StrOutputParser()

summary = chain.invoke({
    "products": "\n\n".join(str(p) for p in products)
})
print(summary)