Gerev is an AI-powered enterprise search engine designed to help organizations quickly find information across various internal platforms. It targets technical users, help desk staff, and developers, enabling them to locate conversations, documents, and internal pages using natural language queries, thereby improving efficiency and knowledge retrieval.

How It Works

Gerev leverages natural language processing to understand user queries, translating them into effective searches across integrated data sources. Its architecture supports both cloud-hosted and self-hosted deployments, with a focus on providing a unified search experience for disparate internal tools.

Quick Start & Requirements

• Self-Hosted (Docker): Requires Docker and the NVIDIA Container Toolkit for GPU acceleration.
  • Install NVIDIA Container Toolkit: Follow instructions for your distribution.
  • Run container: docker run --gpus all --name=gerev -p 80:80 -v ~/.gerev/storage:/opt/storage gerev/gerev (for GPU) or docker run --name=gerev -p 80:80 -v ~/.gerev/storage:/opt/storage gerev/gerev (for CPU).
• Cloud: Managed cloud version available with sign-up.
• Source: Development setup instructions are available in ADDING-A-DATA-SOURCE.md.

Highlighted Details

• Supports natural language search queries (e.g., "How to do X").
• Extensive integrations with Slack, Jira, Google Drive, Confluence, GitLab Issues, Mattermost, Rocket.Chat, and Bookstack, with more in progress.
• Offers both a managed cloud version and a self-hostable community edition.
• Requires NVIDIA hardware for optimal performance in GPU-accelerated deployments.

Maintenance & Community

The project is community-driven with contributions from various individuals. A Discord server is available for early access codes and community interaction.

Licensing & Compatibility

The README does not explicitly state the license type. Compatibility for commercial use or closed-source linking is not specified.

Limitations & Caveats

The project is actively under development, with several integrations listed as "In PR" or "In Progress." Specific hardware requirements (NVIDIA GPU) are necessary for the GPU-accelerated version. The license is not clearly stated, which may impact commercial adoption.