Feature Breakdown

Explore our advanced features designed to deliver state-of-the-art RAG on-premise

For Everyone

Operate entirely within your own infrastructure.

Dabarqus runs entirely on your own hardware—be it a PC, laptop, server, or owned-cloud infrastructure. Your data never leaves your control, ensuring maximum privacy and security for your sensitive information.

Standalone C++ application with everything built-in.

Dabarqus is engineered as a standalone C++ application with everything built-in. No need for additional software or libraries—just install and run.

All-in-one package for advanced RAG capabilities.

An all-in-one package that streamlines the entire RAG process by integrating four essential components into a single, powerful solution.

  • Vector database: for efficient storage and retrieval
  • Embedding model: for converting text to vector representations
  • Ingestion and retrieval utilities: for seamless data management
  • Built-in chatbot: accessible via browser
Runs as an OS service across Windows, Linux, and macOS.

Supports Windows, Linux, and macOS as an OS service, ensuring seamless operation across Windows, Linux, and macOS.

Receive relevant documents ranked by input relevance.

Retrieves and ranks documents based on their relevance to user inputs, facilitating more accurate and efficient searches.

Easy integration with various AI models.

The search results can be easily used with various AI models to generate more informed responses.

For Developers

🌐

Modern REST API for Seamless Integration

Dabarqus comes with a fully documented, modern REST API, providing developers with a straightforward way to integrate advanced RAG capabilities into their existing applications. The API allows for efficient querying, data management, and interaction with the Dabarqus engine, ensuring smooth integration with LLMs and other AI systems.

Key Features of the Dabarqus REST API

  • Simple Querying: Send HTTP requests to retrieve relevant documents with ease.
  • Data Ingestion Made Easy: Upload and manage large volumes of documents using the API’s ingestion endpoints.
  • Flexible AI Integration: The API provides structured JSON outputs that can easily be fed into AI models for more context-aware responses.

Using the API

Example

curl http://localhost:6568/api/silk/query?q=Tell%20me%20about%20the%20documents&limit=3&memorybank=docs

This sends a GET request to the Dabarqus API to perform a semantic search in the “docs” memory bank, returning up to three relevant documents.

Scalable and Cross-Platform

Whether you’re building a web app, mobile app, or a backend service, the Dabarqus REST API is designed to be cross-platform and highly adaptable. It works across different environments like Windows, Linux, and macOS, giving you the flexibility to develop on your preferred platform. This API-driven architecture allows for scalable deployments, making it easy to expand and customize your RAG system as your needs grow.

🚀

Developer-Friendly CLI Integration

For developers looking to harness the full potential of Dabarqus, we offer a powerful command-line interface (CLI) called barq. This CLI allows for seamless interaction with the Dabarqus engine via the REST API, making it easy to manage data ingestion and retrieval processes directly from the terminal.

Key Capabilities of barq

  • Simple Setup: Installing the CLI is as easy as running barq service install, and you’re ready to start managing your RAG implementation.
  • Effortless Data Management: Use the barq store command to upload your documents to a memory bank with ease.
  • Advanced Document Retrieval: Developers can retrieve data from a specific memory bank by querying directly through the CLI.

Example Usage

Storing Documents

barq store --input-path /path/to/documents --memory-bank "my_memory_bank"

This command ingests all documents in the specified folder into the “my_memory_bank,” making them readily available for querying.

Retrieving Documents

barq retrieve --memory-bank "my_memory_bank" --query "Find the latest update"

This enables targeted document search with results ranked by relevance, ready for use in AI models or other applications.

Flexible & Efficient

Whether you’re working locally or on a remote server, barq streamlines interaction with Dabarqus, providing a familiar and efficient toolset for data handling, retrieval, and integration. Its simplicity allows developers to focus on building AI-driven applications without worrying about complex setups or external dependencies.

🔌

Python and JavaScript SDKs

To make integration with Dabarqus even more accessible, we’ve developed SDKs for both Python and JavaScript. These SDKs provide a straightforward way for developers to interact with Dabarqus, offering pre-built methods and utilities for common tasks.

Python SDK

The Dabarqus Python SDK simplifies interactions with the REST API by offering a Pythonic interface. It abstracts the complexities of direct API calls, allowing you to integrate RAG capabilities into your Python applications with ease. With this SDK, you can seamlessly perform operations like querying and data storage, handle responses, and manage configurations—all through familiar Python code.

Key Features:

JavaScript SDK

For web and Node.js applications, the Dabarqus JavaScript SDK offers a convenient way to interact with the REST API. This SDK enables smooth integration into both client-side and server-side JavaScript environments, allowing you to utilize Dabarqus’s full capabilities in your JavaScript projects. Whether you’re building a dynamic web application or a backend service, the SDK ensures you can handle queries and manage data effortlessly.

Key Features:

Getting Started

Python

pip install dabarqus

To get started with the Python SDK, install it using the command above and refer to the documentation for code examples and setup instructions.

JavaScript

npm install dabarqus

For the JavaScript SDK, install it with the command above and follow the provided guides to integrate it into your project.

Both SDKs are designed to make your development process smoother and more efficient, enabling you to leverage Dabarqus’s powerful RAG capabilities with minimal effort.

Dabarqus Command Center – Optimized Version

For Everyone

Local and Private

Operate entirely within your own infrastructure.

Local and Private

Dabarqus runs entirely on your own hardware – be it a PC, laptop, server, or owned-cloud infrastructure. Your data never leaves your control, ensuring maximum privacy and security for your sensitive information.

Zero Dependencies

Standalone C++ application with everything built-in.

Zero Dependencies

Dabarqus is engineered as a standalone C++ application with everything built-in. No need for additional software or libraries – just install and run.

Comprehensive Solution

All-in-one package for advanced RAG capabilities.

Comprehensive Solution

An all-in-one package that streamlines the entire RAG process by integrating four essential components into a single, powerful solution.

  • Vector database: for efficient storage and retrieval
  • Embedding model: for converting text to vector representations
  • Ingestion and retrieval utilities: for seamless data management
  • Built-in chatbot: accessible via browser

Cross-Platform Compatibility

Runs as an OS service across Windows, Linux, and macOS.

Cross-Platform Compatibility

Supports Windows, Linux, and macOS as an OS service, ensuring seamless operation across Windows, Linux, and macOS.

Intelligent Querying

Receive relevant documents ranked by input relevance.

Intelligent Querying

Retrieves and ranks documents based on their relevance to user inputs, facilitating more accurate and efficient searches.

Enhanced AI Compatibility

Easy integration with various AI models.

Enhanced AI Compatibility

Seamlessly integrates with various AI models and systems, expanding its applicability across different AI use cases.

For Developers

Modern REST API

REST API with JSON output for seamless integration.

🌐

Modern REST API for Seamless Integration

Dabarqus comes with a fully documented, modern REST API, providing developers with a straightforward way to integrate advanced RAG capabilities into their existing applications. The API allows for efficient querying, data management, and interaction with the Dabarqus engine, ensuring smooth integration with LLMs and other AI systems.

Key Features of the Dabarqus REST API

  • Simple Querying: Send HTTP requests to retrieve relevant documents with ease.
  • Data Ingestion Made Easy: Upload and manage large volumes of documents using the API’s ingestion endpoints.
  • Flexible AI Integration: The API provides structured JSON outputs that can easily be fed into AI models for more context-aware responses.

Using the API

Example

curl http://localhost:6568/api/silk/query?q=Tell%20me%20about%20the%20documents&limit=3&memorybank=docs

This sends a GET request to the Dabarqus API to perform a semantic search in the “docs” memory bank, returning up to three relevant documents.

Scalable and Cross-Platform

Whether you’re building a web app, mobile app, or a backend service, the Dabarqus REST API is designed to be cross-platform and highly adaptable. It works across different environments like Windows, Linux, and macOS, giving you the flexibility to develop on your preferred platform. This API-driven architecture allows for scalable deployments, making it easy to expand and customize your RAG system as your needs grow.

CLI Tool – barq

Command-line interface for Dabarqus management.

🚀

Developer-Friendly CLI Integration

For developers looking to harness the full potential of Dabarqus, we offer a powerful command-line interface (CLI) called barq. This CLI allows for seamless interaction with the Dabarqus engine via the REST API, making it easy to manage data ingestion and retrieval processes directly from the terminal.

Key Capabilities of barq

  • Simple Setup: Installing the CLI is as easy as running barq service install, and you’re ready to start managing your RAG implementation.
  • Effortless Data Management: Use the barq store command to upload your documents to a memory bank with ease.
  • Advanced Document Retrieval: Developers can retrieve data from a specific memory bank by querying directly through the CLI.

Example Usage

Storing Documents

barq store --input-path /path/to/documents --memory-bank "my_memory_bank"

This command ingests all documents in the specified folder into the “my_memory_bank,” making them readily available for querying.

Retrieving Documents

barq retrieve --memory-bank "my_memory_bank" --query "Find the latest update"

This enables targeted document search with results ranked by relevance, ready for use in AI models or other applications.

Flexible & Efficient

Whether you’re working locally or on a remote server, barq streamlines interaction with Dabarqus, providing a familiar and efficient toolset for data handling, retrieval, and integration. Its simplicity allows developers to focus on building AI-driven applications without worrying about complex setups or external dependencies.

Python and JavaScript SDKs

Official SDKs for easy integration in Python and JavaScript projects.

🔌

Python and JavaScript SDKs

To make integration with Dabarqus even more accessible, we’ve developed SDKs for both Python and JavaScript. These SDKs provide a straightforward way for developers to interact with Dabarqus, offering pre-built methods and utilities for common tasks.

Python SDK

The Dabarqus Python SDK simplifies interactions with the REST API by offering a Pythonic interface. It abstracts the complexities of direct API calls, allowing you to integrate RAG capabilities into your Python applications with ease. With this SDK, you can seamlessly perform operations like querying and data storage, handle responses, and manage configurations—all through familiar Python code.

Key Features:

JavaScript SDK

For web and Node.js applications, the Dabarqus JavaScript SDK offers a convenient way to interact with the REST API. This SDK enables smooth integration into both client-side and server-side JavaScript environments, allowing you to utilize Dabarqus’s full capabilities in your JavaScript projects. Whether you’re building a dynamic web application or a backend service, the SDK ensures you can handle queries and manage data effortlessly.

Key Features:

Getting Started

Python

pip install dabarqus

To get started with the Python SDK, install it using the command above and refer to the documentation for code examples and setup instructions.

JavaScript

npm install dabarqus

For the JavaScript SDK, install it with the command above and follow the provided guide to integrate it into your project.

Both SDKs are designed to make your development process smoother and more efficient, enabling you to leverage Dabarqus’s powerful RAG capabilities with minimal effort.

Sign up below to be the first to know when Dabarqus is ready:

* indicates required