index4.ai Docs by

Appearance

Getting started ​

index4.ai is an end-to-end context engine: it runs a structure-aware ingestion pipeline (parse, chunk, embed) and persists the result in a managed retrieval layer, so you ingest documents into a project once and then query it. Search is hybrid (dense plus BM25) and the response is prompt-ready context in XML or Markdown rather than raw ranked hits. You run no vector store, reranker or chunking pipeline of your own.

Before you start ​

  • An account in the index4.ai console. See pricing for plans and free-tier limits.
  • A project API key (prefix poma_proj_gr_…), which the SDK reads from INDEX4AI_API_KEY. Each project has its own key. Account-level credentials also work on the REST API when you send an X-Project-ID header (see Authentication).
  • Any HTTP client for the REST API at https://api.index4.ai/v1. Or the Python SDK: pip install index4ai.

The three steps ​

  1. Authenticate — create a project in the console and put its key in your environment.
  2. Create a project — a project is a namespace for one corpus, optionally assigned to an organisation; ingest and search calls are scoped to it.
  3. Run the quickstart — ingest one document, wait for the job to finish, run a hybrid search, and drop the returned context into an LLM prompt.

After that, the concepts section explains ingestion, retrieval and its tiers, the returned context format, and document management, and the API reference lists every endpoint and field.