Ocular provides an open-core, enterprise-grade platform for building AI-powered search and chat experiences tailored to organizational data. It aims to simplify the deployment of custom internal search solutions, enabling companies to integrate generative AI capabilities with their existing data sources and workflows.

How It Works

Ocular offers a modular infrastructure that allows users to integrate their own LLMs and vector databases. It features a Google-like search interface and an app marketplace for connecting to various services, with support for custom connectors to proprietary data. A governance engine provides role-based access control and audit logs for enterprise readiness.

Quick Start & Requirements

• Install: Clone the repository and set up Docker.
• Prerequisites: Docker, OpenAI API keys (required for default LLM provider), and optional API keys for specific app integrations (e.g., Gmail, Google Drive).
• Run: docker compose -f docker-compose.local.yml up --build --force-recreate
• Access: http://localhost:3001/create-account
• Resources: Docs, Slack

Highlighted Details

• AI-powered search and chat for organizations.
• Connectors for popular apps (Gmail, Google Drive, Asana, GitHub).
• Customizable modular infrastructure for custom LLMs and vector databases.
• Governance Engine with RBAC and audit logs.

Maintenance & Community

The project encourages contributions and provides a Slack channel for community discussion and support.

Licensing & Compatibility

The repository is licensed under the Elastic License 2.0 (ELv2).

Limitations & Caveats

Support for LLM providers other than OpenAI is listed as "coming soon."