Cracking PDF Catalogs: AI to Airtable for SKUs and Prices

说明与用途

使用LLM和Airtable自动化从供应商PDF目录中提取SKU、描述和价格，将处理时间从半天缩短到30秒。

问题

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

结果

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

工作流

• 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'

证据

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.

来源

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.

来源

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.

来源