OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Vectordb Gsc

Vectordb Gsc is a self-hosted Python CLI that extracts Google Search Console performance data, embeds query–page records in local ChromaDB with Gemini, and uses retrieval-augmented generation for analysis.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Vectordb Gsc — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a CLI-based way to turn Search Console records into a local semantic-retrieval collection and investigate them with AI, or to add a page-level content comparison.

Who it is for

  • Site owners and SEO practitioners with access to Google Search Console data.
  • Technical users comfortable configuring a Python project, cloud service-account credentials and API keys.

Documented uses

  • Retrieve up to 16 months of Search Console queries, pages, dates, countries and devices.
  • Ask semantic questions about stored search performance, including query trends and possible cannibalization.
  • Audit an individual page against its GSC queries and competing pages using optional Parallel.ai research.
Before you choose

Requirements & limits

The project is a public GitHub repository intended for local setup. It requires a Gemini API key and Google service-account access to a Search Console property. The README lists Gemini's free tier, pay-per-use options for Grok and Claude, and pay-per-use Parallel.ai research; actual costs depend on provider use.

  • The primary workflow is a Python CLI, not a hosted web dashboard.
  • Google Search Console access and a service-account JSON key are required for data extraction.
  • Gemini embeddings are required; Grok and Claude are alternative analysis providers with separate credentials.
  • Page audits and competitor analysis depend on an optional Parallel.ai key.
  • ChromaDB stores the vector collection locally, while model analysis and optional web research use external providers.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Vectordb Gsc and configure Google access

Prepare the project and credentials needed for its documented Search Console workflow.

Before you start

  • Python and the ability to install the repository's requirements.
  • A Google Cloud service account, enabled Search Console API, and permission to access the target Search Console property.
  • A Gemini API key.

Steps

  1. Clone the repository and install dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  2. Place the service-account JSON key file in the project root, enable the Search Console API, and add the service-account email to the property's Search Console users.

  3. Copy .env.example to .env and set SERVICE_ACCOUNT_FILE and GEMINI_API_KEY; set GSC_PROPERTY or leave it blank for the property picker.

Expected outcome

The project has its documented dependencies and Google and Gemini credentials configured for subsequent commands.

Guide limitations

  • This setup guide does not establish that extraction or analysis has been run.
  • The documented setup requires credentials and access to a Search Console property.
Documentation 1 ↗
Source-based practical guide

Extract, embed and query Search Console records

Use the documented CLI stages to prepare GSC records for semantic analysis.

Before you start

  • A configured project with Search Console property access and Gemini API key.
  • The repository's Python dependencies installed.

Steps

  1. Run the command below to retrieve the documented 16-month range of GSC performance data.

    Documented command
    python main.py extract

  2. Run the command below to aggregate rows into query–page documents, calculate metrics and embed records in ChromaDB.

    Documented command
    python main.py process

  3. Run the command below for the interactive analyses, or use the command below for a one-shot question.

    Documented command
    python main.py analyze
    Documented command
    python main.py ask "which queries are rising fastest?"

Expected outcome

The documented workflow extracts and embeds GSC records locally, then retrieves relevant records to support AI analysis.

Guide limitations

  • Gemini is required for embeddings; Grok and Claude require their own keys when selected.
  • The README describes a local ChromaDB store and external model providers; it does not describe this as a hosted dashboard.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Vectordb GscRetrieve up to 16 months of Search Console queries, pages, dates, countries and devices.CLI, Self-hostedThe project is a public GitHub repository intended for local setup. It requires a Gemini API key and Google service-account access to a Search Console property. The README lists Gemini's free tier, pay-per-use options for Grok and Claude, and pay-per-use Parallel.ai research; actual costs depend on provider use.
Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And PdfsRetrieve relevant passages from web and PDF content to answer a question.Web
LangChain in Supabase Edge FunctionsInitialize and start a Supabase project locally.Cloud, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
metehan777/vectordb-gsc · Official homepage title · retained in its source language
How we review sourcesSuggest a correction