Google Drive Collection

SearchBlox has a crawler that can index documents from a Google Drive account, and you can create a Google Drive Collection using the steps given below.

🚧

Prerequisites

• Create a Project in Google Account to get KEY File, ServiceAccount ID, Application Name and ServiceAccount User.
• Provide the Required Permissions to ServiceAccount User to access the files/folders of Google Drive.
• Share the files/folders with ServiceAccount User.
• Guidelines to create an ServiceAccount

Creating Google Drive Collection

You can create a Google Drive Collection using these steps:

• Log in to the Admin Console, go to the Collections tab, and click Create a New Collection or the "+" icon.
• Select Google Drive Collection as the Collection Type.
• Enter a unique collection name (example: Drive).
• Enable or disable RAG (enable if using ChatBot or Hybrid RAG search).
• Choose Private/Public access and set Collection Encryption as needed.
• Select the content language (if not English).
• Click Save to create the collection.
• After creating the Google Drive collection, you will be taken to the Authentication tab.

Settings Tab

Upload the KEY File and enter the ServiceAccount ID, Application Name, and ServiceAccount User. You can find all these details in the ServiceAccount section of the Google Cloud Console.

• Choose the settings for Generate Using LLM and Hybrid Search.

Detailed Logging

Enable Detailed Log — Turns on detailed indexing logs for debugging. Off (NO) by default.

RAG

Enable RAG — Builds a retrieval index (vector embeddings) for this collection so it can be used for RAG, hybrid search, and AI answers. Currently YES. Applies at the next index — you need to re-index to build/rebuild the RAG index.

RAG Chunking
Controls how documents are split into chunks for the RAG vector index:

Chunking Strategy — How documents are split (e.g., recursive). Set to Global Default, which suits most content.
Size Unit — Measure chunk size/overlap in Tokens or Characters. Currently Global Default.
Chunk Size — Size of each chunk; blank inherits the global default (300 tokens).
Overlap — Overlap between adjacent chunks, must be less than chunk size; blank inherits global default (30).
Chunking settings apply at indexing time — set them before the first index. Changing them later requires re-indexing the whole collection.

• Click on Save button and Click on Test Connection.

Synonyms

Synonyms help the search show relevant documents even when the exact search word is not used.
For example, if someone searches for “global,” the results can also include documents that use “world” or “international.”
We have an option to load Synonyms from the existing documents.

Stopwords

Stopwords are common, high-frequency words that carry minimal semantic value and are typically excluded during text processing, indexing, or search operations. Examples include articles (a, an, the), conjunctions (and, but, or), prepositions (in, on, about), and auxiliary verbs (is, was, would, had).

Purpose:

Reduce noise in search indexing and text analysis
Improve processing efficiency by excluding low-value tokens
Enhance search relevance by prioritizing meaningful keywords

Schedule and Index

Google Drive collections should only index files or folders that are shared. You can set how often and when the collection should be indexed. SearchBlox supports the following schedule options:

• Once
• Hourly
• Daily
• Every 48 Hours
• Every 96 Hours
• Weekly
• Monthly

The following operation can be performed in Google Drive collections

Manage Documents Tab

• In the Manage Documents tab, you can do these actions:

  1. Filter – Find specific documents.
  2. View content – See the document’s text.
  3. View metadata – Check details about the document.
  4. Refresh – Update the document list.
  5. Delete – Remove documents.

• To delete a file, type the file path and click Delete.

• To check the status of an indexed file, click View Metadata.

Data Fields Tab

In the Data Fields tab, you can create custom fields for search and view the default fields in a non-encrypted collection. SearchBlox supports 4 types of Data Fields:

After configuring Data Fields, the collection must be cleared and re-indexed to apply the changes.

To know more about Data Fields please refer to Data Fields Tab

Prompts

• When LLM/RAG is enabled, you can edit AI-based prompts for Title, Description, Topic, Image Description, and Smart FAQs.
• You can customize these prompts anytime, and use Restore Default to reset them back to the original SearchBlox settings.

Models

The Models section lets you override the global embedding, reranking, and LLM settings for this specific collection. Changes made here apply only to the current collection and do not affect other collections.

Embedding

• Provider specifies the embedding provider used to generate vector representations of documents.
• Model defines the embedding model used to convert document content into vectors for semantic search.

Reranker

• Provider specifies the reranker provider used for improving search result relevance.
• Model defines the reranker model used to re-score and reorder search results based on relevance.

LLM

• Provider specifies the Large Language Model provider used for AI-powered features.

• Model defines the LLM used for tasks such as document enrichment, summaries, and SmartFAQs.

• These settings override global configurations and apply only to the current collection.