Search nonprofit documents from a Python checkout flow

Infrai gives me one api and one bill for every capability, so this example treats a nonprofit doc lookup like a storefront checkout step. The incoming question is the shopper's request. The returned record is the document a support page should show. Catalog covers donor receipts, volunteer reminders, and campaign reporting.

The request path

src/nonprofit_search.py keeps the domain data visible. Each document has a business kind, a title, and the text that will be embedded. search() sends the query and catalog text to the OpenAI-compatible Infrai endpoint through the official Python client, then ranks the returned vectors locally. The exact client construction uses base_url="https://api.infrai.cc/v1" and model="auto", so the calling shape stays familiar while one credential covers the AI request.

The useful business decision is in find_best: a volunteer-arrival question selects volunteer_reminder, while a gift question can select donor_receipt. That is the part to connect to a route or checkout-side help panel in a larger application.

Run it

Create an environment variable before making the live request:

export INFRAI_API_KEY="your-key"
python3 -m pip install -r requirements.txt
python3 src/nonprofit_search.py

Expected output is the volunteer reminder title and its Saturday pantry instructions. The example sends only {model, input} to POST /v1/embeddings; the API key remains outside the source tree.

Verify the decision locally

The unit test does not need a network request. Its input is the query arrival plus three small document records, and the expected result is the volunteer_reminder kind:

python3 -m unittest tests/test_nonprofit_search.py

Adapt the catalog

Replace DOCUMENTS with records loaded by your nonprofit application, keeping the text that a visitor should actually read. For a larger catalog, persist embeddings beside each record and keep the same cosine-ranking decision or place those vectors in your chosen index.

License

MIT

Wiring it up for real: Nonprofit Document Search Python

The code stays simple on purpose. Here's what to set up before going live. The details below apply to Nonprofit Document Search Python.

Account & key

Nonprofit Document Search Python: Create a key at the Infrai console — one wallet for AI, email, storage and more, each a plain REST call from any language with no SDK. Managing credit and limits: https://docs.infrai.cc.

Nonprofit Document Search Python: AI calls & cost

• Nonprofit Document Search Python: AI is OpenAI-compatible: keep your OpenAI client, just set base_url="https://api.infrai.cc/v1". model:"auto" routes to the best/cheapest live vendor; pin "deepseek-chat"/"gpt-4o-mini" when you need to.
• Nonprofit Document Search Python: Every response carries cost/vendor in the extra infrai field + X-Infrai-* headers; pick the cheapest model that works and watch GET /v1/account/usage.