Graphon Docs

Overview

Graphon is smart blob storage that replaces your dumb object store. Store objects with the Graphon API, then search and query them with AI.

Make a working request

Graphon CLI
  1. 1Store a file

    CLI

    graphon objects put reports finance/q3-report.pdf \
      --file ./q3-report.pdf

    Graphon indexes each file you add.

  2. 2Search it

    CLI

    graphon search reports "quarterly revenue"

    One call matches the exact words and the meaning together.

  3. 3Ask it a question

    CLI

    graphon ask reports "How did revenue change in Q3?"

    One answer, with a citation for each source it used.

New here? Set up your environment to install the CLI, then create your first bucket. Every call here also works over HTTP: see Search your objects and Answer a question.

What is Graphon?

Graphon is smart blob storage. It replaces S3, R2, and GCS in your stack. Its object API is designed to feel like S3 — buckets, objects, and keys — so it is familiar. Graphon is different in one way: as you write data, it reads the data and understands it.

On top of storage, one search call matches the exact words and the meaning together, so you do not run a keyword index and a vector index and merge the two. Ask a question and Graphon answers it with a citation for each source. You drop your separate search stack and keep one dependency.

Why developers use Graphon

  • Familiar model. Buckets, objects, and keys, like S3. If you know S3, you know Graphon's shape.
  • Remove a dependency. Retire Elasticsearch, Pinecone, or LanceDB. Search and retrieval live in the storage layer.
  • Ask questions, not just fetch bytes. Query a bucket in natural language and get an answer with sources.
  • Isolate tenants. Partition data by your own customer with the X-Graphon-Tenant header.

What you can build with Graphon

Point Graphon at your files and ship a product on top. A few things teams build:

Was this page helpful?
View as Markdown