Google Drive Text Embedding (v1) 📄

This example embeds text files from Google Drive, stores chunk embeddings in Postgres (pgvector), and includes a simple query demo.

Prerequisites

• A running Postgres with the pgvector extension available
• A Google Cloud service account with Drive access
• Environment variables:

export POSTGRES_URL="postgres://cocoindex:cocoindex@localhost/cocoindex"
export GOOGLE_SERVICE_ACCOUNT_CREDENTIAL="/path/to/service-account.json"
export GOOGLE_DRIVE_ROOT_FOLDER_IDS="folder_id_1,folder_id_2"

Run

Install deps:

pip install -e .

Build/update the index:

cocoindex update main.py

Query:

python main.py query "what is self-attention?"

Note: this example does not create a vector index; queries do a sequential scan.