Feature Breakdown

Diverse document ingestion, LLM flexibility, and more.

For Everyone

Ingest documents, databases and APIs

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

*check here for available file types in Dabarqus editions.

Ingest documents, databases and APIs

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

LLM-Style Prompting

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

LLM-Style Prompting

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.

Multiple Semantic Indexes (Memory Banks)

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

Multiple 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.

LLM-Friendly Output

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

LLM-Friendly Output

Works seamlessly with the LLM of your choice.

Admin Dashboard

Monitor performance, test memory banks and make changes in an easy-to-use UI.

Admin Dashboard

Easy access to Dabarqus features. Monitor app performance with real-time graphs.

Mac, Linux and Windows Support

Runs natively with zero dependencies on all platforms: MacOS (Intel or Metal), Linux, and Windows (CPU or GPU).

Mac, Linux and Windows Support

Runs on whatever platform you use.

For Developers

REST API

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

REST API

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

SDKs

Native SDKs in Python and Javascript.

SDKs

Easily integrates with Python and Javascript projects.

LLM Inference

Chat with LLM models right through the Dabarqus API/SDKs.

LLM Inference

Built-in chatbot capabilities for use in your applications.

Dabarqus Editions

Community Edition Features

  • Ingest PDFs only
  • Up to three results per prompt
  • One, preset embedding model (512 token context, lacking in the latest and greatest functionality like reranking)

Premium Edition Features

  • Full complement of ingestions options
  • Can specify an unlimited number of results per prompt
  • Supports multiple different embedding models, including models with additional context and features.

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

* indicates required