ChatPDF–Gemini API Integration

I’m running ChatPDF in production and now need it to tap directly into the Gemini 2.5 Pro API so every PDF that lands in the system is processed automatically—no more manual clicks. The flow I have in mind is simple: the moment a file is uploaded, your integration calls Gemini, performs text extraction, attaches or updates metadata tags, converts formats when needed, and hands the results back to ChatPDF as plain-text output that downstream services can read instantly.

Here’s what I’d like handed over:

• A lightweight script, function, or micro-service (Python or Node is fine) that authenticates with Gemini 2.5 Pro, listens or polls for new PDFs from ChatPDF, and returns the processed data.
• Clear mapping so extracted plain text, metadata, and any converted files are routed to the correct ChatPDF endpoints or storage buckets I specify.
• README with setup steps, required environment variables, and quick test commands so I can redeploy on another machine without surprises.
• Brief notes on error handling—rate limits, malformed PDFs, API timeouts—so the process fails gracefully.

You’ll have API keys for both platforms as soon as we start; everything else is yours to wire together and prove with a short demo run.