We solved RAG.

A dash of genius for your LLM.

Download now!

We solved RAG.

Responsive Smooth Text Slider with Animation

A dash of genius for your LLM.

Download now!

What is RAG?

RAG is short for Retrieval Augmented Generation, which is a framework for making private data available to AI large language models in real time.

What is Dabarqus?

📥

Ingest documents, databases and APIs

Ingest diverse data-sources like PDFs*, emails, and raw data.

No matter where your data resides, Dabarqus can make it available to your LLM.

*check here for available file types in Dabarqus editions.

💬

LLM-Style Prompting

Use simple, LLM-style prompts when speaking to your memory banks.

Dabarqus will retrieve relevant data using the same prompt that you give your LLM. No need to construct special queries or learn a new query language.

⚡️

REST API

Comprehensive control interface for downloading models, prompting semantic indexes and even LLM inference.

REST is a standard interface that enjoys wide adoption, so your team doesn’t learn a new, complex system. It allows comprehensive integration with existing development tools for easy adoption.

🧠

Multiple Semantic Indexes (Memory Banks)

Group your data into separate semantic indexes (memory banks).

Keep your data organized by subject matter, category, or whatever grouping you like. Memory banks are portable, so you can create and use them wherever you like.

🛠️

SDKs

Native SDKs in Python and Javascript.

Easily integrates with Python and Javascript projects.

Python SDK↗︎

Javascript SDK↗︎

🔗

LLM-Friendly Output

Produces LLM-ready output that works with ChatGPT, Ollama and any other LLM provider.

Works seamlessly with the LLM of your choice.

How Dabarqus Works

Our all-in-one RAG solution is so simple that we can explain it in three steps:

Dabarqus Tabs

Store Retrieve Integrate

Effortlessly Ingest diverse data sources (PDFs*, emails, raw data, etc) in semantic indexes called memory banks.

cURL

                        
 # Store documents in a memory bank 
curl -X GET "${DABARQUS_SERVER}/api/silk/store" \
-H "Content-Type: application/json" \
--data-urlencode "input-path=/path/to/your/documents" \
--data-urlencode "memory-bank=my_documents"

CLI

                        
# Store documents in a memory bank
barq store --input-path="/path/to/your/documents" --memory-bank=my_documents

*check here for available file types in Dabarqus editions.

Retrieve the most relevant information from your memory banks using LLM-Style Prompting.

No need to construct special queries — Dabarqus’s advanced query processing ensures you get precise, context-aware results every time.

cURL

                        
 # Retrieve information from the memory bank 
curl -X GET "${DABARQUS_SERVER}/api/silk/query" \
-H "Content-Type: application/json" \
--data-urlencode "q=Tell me about the documents" \
--data-urlencode "limit=3" \
--data-urlencode "memorybank=my_documents"

CLI

                        
 # Retrieve information from the memory bank 
barq retrieve --memory-bank=my_documents --query "When did I travel to Florida?"

Dabarqus gets you from zero to RAG in minutes and our REST API, SDKs, and CLI tool make integration simple across various platforms and languages.

Here’s an example of how easy it is with a Python-based chatbot we’ve put together using Dabarqus.

Dabarqus is now available on Linux, macOS, and Windows!

Download now!