AI Powered Search and Chat for Companies – Think ChatGPT meets Google Search but powered by your data.

Introduction

Ocular is a set of modules and tools that allow you to build rich, reliable, and performant Generative AI-Powered Search Platforms without the need to reinvent Search Architecture. We help you build your customized internal search in days, not months.

Features

• Google Like Search Interface – Find what you need effortlessly.
• App MarketPlace – Connect to all of your favorite Apps.
• Custom Connectors – Build your own connectors to proprietary data sources.
• Customizable Modular Infrastructure – Bring your own custom LLMs, Vector DB, and more into Ocular.
• Governance Engine – Provides Role-Based Access Control and Audit Logs.

Open-source vs Paid

The repository is under Elastic License 2.0 (ELv2). If you are interested in managed Ocular Cloud or self-hosted Enterprise Offering, book a meeting with us.

Getting Started

Running Ocular in Docker

To run Ocular locally, you’ll need to set up Docker in addition to Ocular. Below are the steps to guide you through the process.

Prerequisites

First, make sure you have Docker installed on your device. You can download and install it from here.

Steps to Run Ocular

1. Clone the Ocular directory:

   git clone https://github.com/OcularEngineering/ocular.git
   cd ocular

2. Configure your environment: In the home directory, open env.local and add the required OpenAI environment variables.
3. Required Keys:
   • OpenAI Keys – To run Ocular, a Language Model (LLM) provider must be set up in the backend. By default, OpenAI is the LLM provider for Ocular, so please add the OpenAI keys in env.local.
   • Support for other LLM providers is coming soon!
4. Optional Keys:
   • Apps (Gmail, Google Drive, Asana, GitHub, etc.) – To index documents from apps, the API keys have to be set up in env.local according to the specific app. Please refer to our documentation for details.
5. Run Docker:

   docker compose -f docker-compose.local.yml up --build --force-recreate

   This command initializes the containers specified in the docker-compose.local.yml file. It might take a few moments to complete, depending on your computer and internet connection. Once the docker compose process completes, you should have your local version of Ocular up and running within Docker containers. You can access it at localhost:3001/create-account.

Remember to keep the Docker application open as long as you’re working with your local Ocular instance!

Contributing

We love contributions! Check out our guide to see how to get started. Not sure where to get started? You can join our Slack and ask us any questions there.

Troubleshooting

If you encounter any issues while setting up Ocular or running Docker, here are some troubleshooting tips:

• Docker not starting: Ensure that Docker is correctly installed and running on your machine. Restarting Docker can often resolve initialization issues.
• Access Denied errors: Double-check your environment variables in env.local to ensure all necessary keys are set correctly.
• Slow performance: If Ocular runs slowly, check your system resources and ensure that sufficient CPU and memory are allocated to Docker.

For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.