Cracking PDF Catalogs: AI to Airtable for SKUs and Prices

Description and use

Automating SKU, description, and price extraction from vendor PDF catalogs using an LLM and Airtable reduced processing time from half a day to 30 seconds.

Problem

Manual extraction of SKUs, product descriptions, and prices from vendor PDF catalogs was time‑consuming, error‑prone, and required constant updates.

Outcome

Processing time reduced from half‑day to ~30 seconds per catalog; 90% accuracy on first pass; human review needed for remaining errors.

Workflow

• Extract raw text from PDF with pypdf
• Prompt self‑hosted Llama‑3‑70b‑instruct via Ollama with clear instructions and JSON output format
• Parse LLM JSON output
• Use pyairtable to insert records into Airtable, setting Review Status to 'Needs Review'

Evidence

Each one was a unique snowflake of inconsistent formatting, and my team's job was to manually pull out SKUs, product descriptions, and prices into our Airtable database.

Source

I fed this raw, often unstructured, text into an LLM. I'm using a self-hosted llama-3-70b-instruct instance via Ollama – saved me a ton on API costs.

Source

From there, it was straightforward. A simple Python script takes the JSON output and uses the pyairtable library to push the extracted products into our Airtable base.

Source