Overview

Introduction to the Indexing Service

Welcome to the Ejento Indexing Service. This service provides a simple and reliable way to upload documents into a specific corpus. Once uploaded, the system automatically handles all the processing in the background, no additional steps are required from your side.

The Indexing Service focuses on a single customer-facing capability: uploading a document to a corpus.

Behind the scenes, the service takes care of:

Extraction

Enrichment

Chunking

Embeddings

Indexing

This means you only perform one upload action, and the rest is handled by our scalable processing pipeline.

Key Benefits

Single, simple integration – Upload once, and all downstream processing happens automatically.

Scalable and reliable – Built on a resilient background pipeline for high-volume workloads.

Content-aware – Includes optional PII redaction, PDF-aware handling, and structured corpus support.

Future-proof – Backed by modern architecture, continuously maintained, and ready for evolving use cases.

Suitable For

New client uploads into corpora

Automated ingestion from back-office systems

Mixed content types including files, plain text, and URLs

What Happens After You Upload (At a Glance)

Validation – File type and size checks; structured corpora enforce content rules.

Optional PII Redaction – Configurable removal or redaction of sensitive data.

Storage & Registration – Content stored securely and assigned a document ID.

Background Processing – Extraction, chunking, embeddings, and indexing queued automatically.

Notifications/Tracking – Use the returned document ID to check processing status.

Base URL for Indexing Service APIs

All Indexing Service APIs must be called using the following base URL:
https://{your-server-name}/indexing-service

When making API calls, replace the {your-server-name} variable with this base URL.

You must include /indexing-service at the end of your server name; otherwise, the Indexing Service APIs will not run.

⚠️ Important: If the base URL is missing or incorrect, your API calls will not work.

Getting Your API Key

To run Indexing Service APIs, you must first generate an API Key.

Steps to Generate an API Key:

Go to Ejento App – API Keys.

Follow the step-by-step guide: How to Create an API Key.

While creating your key:

You can create a general-purpose key for All services, OR

Restrict your key specifically for the Indexing Service.

For best practice, restrict your key by setting:

Other Categories: None for all other categories

Indexing Service: Write

This ensures your API Key is only used for Indexing APIs, keeping your access secure and limited to the required scope.

How to Get Started

Obtain access: Generate your API Key (and Authorization token for user-context actions)

Choose a corpus: Identify the corpus_id you want to upload documents into.

Upload: Send your file, text, or URL via the upload API. You’ll receive a document_id for tracking.

That’s it, your document will now be processed automatically by Ejento’s Indexing Service.

If you need help with onboarding, best practices for preparing content, or tracking uploads, please reach out to the Ejento team.

Overview

Introduction to the Indexing Service#

Overview#

Key Benefits#

Suitable For#

What Happens After You Upload (At a Glance)#

Base URL for Indexing Service APIs#

Getting Your API Key#

Steps to Generate an API Key:#

How to Get Started#

Introduction to the Indexing Service

Overview

Key Benefits

Suitable For

What Happens After You Upload (At a Glance)

Base URL for Indexing Service APIs

Getting Your API Key

Steps to Generate an API Key:

How to Get Started