Skip to main content

How to setup collections in PhariaSearch

Introduction​

This guide explains how to set up the foundational components needed for document collections in PhariaSearch. You'll learn how to create namespaces, collections, and configure indexes.

Prerequisites​

Before starting, ensure you have:

  • PhariaSearch (Document Index) deployed - https://document-index.{ingressDomain}
  • Access to PhariaStudio - https://pharia-studio.{ingressDomain}
  • Basic familiarity with REST APIs

Get your authorization token​

To use the API, you need access to the PhariaStudio token. Follow these steps to retrieve it:

  1. Go to the PhariaStudio page and log in if necessary.
  2. In the upper-right corner, click on your profile.
  3. In the popup, click on Copy Bearer Token.

copy-bearer-token

Setting up your environment​

The PhariaSearch API provides an interface for creating and managing document collections. Access the API documentation at https://document-index.{ingressDomain}/openapi.yaml.

Step 1: Create a namespace​

A namespace is like a project space that helps organize your collections:

curl -X PUT \
  'https://document-index.{ingressDomain}/namespaces/{namespace}' \
  -H 'Authorization: Bearer {your-token}'

Step 2: Create a collection​

Collections store your documents within a namespace:

curl -X PUT \
  'https://document-index.{ingressDomain}/collections/{namespace}/{collection}' \
  -H 'Authorization: Bearer {your-token}'

Step 3: Configure an index​

Indexes determine how your documents are processed and searched:

curl -X PUT \
  'https://document-index.{ingressDomain}/indexes/{namespace}/{index}' \
  -H 'Authorization: Bearer {your-token}' \
  -H 'Content-Type: application/json' \
  -d '{
    "chunk_size": 384,
    "chunk_overlap": 0,
    "embedding_type": "asymmetric"
  }'

For hybrid search capabilities, include "hybrid_index": "bm25" in the configuration.

For more guidance on selecting the optimal index settings for your use case, see recommended index configuration.

Step 4: Assign index to collection​

Connect your index configuration to your collection:

curl -X PUT \
  'https://document-index.{ingressDomain}/collections/{namespace}/{collection}/indexes/{index}' \
  -H 'Authorization: Bearer {your-token}'

Validation​

Verify your setup using:

curl -X GET \
  'https://document-index.{ingressDomain}/namespaces/{namespace}/collections' \
  -H 'Authorization: Bearer {your-token}'

Extra Configuration - PhariaAssistant​

For setting up collections for PhariaAssistant Chat, follow the guide in Configuring which collections are visible to PhariaAssistant.

Troubleshooting​

Common setup issues:

Authorization Errors​

  • Error: 401 Unauthorized
    • Solution: Verify token is current and properly formatted

Next Steps​

Now that your collection is set up, learn how to: