Be the first to try a brand new demo of DeepPavlov Library!
DEEPPAVLOV PRODUCTS
 
DeepPavlov Dream is an open-source Multi-Skill AI Assistant Platform. With it, you will be able to build simple and sophisticated AI Assistants. It is built on top of the DeepPavlov Conversational AI Stack:
  • Agent to orchestrate skills; Agent is the heart of Dream as it is a foundation of its multi-skill architecture;
  • Dialog Flow Framework to run individual skills; it was born during Amazon Alexa Prize Socialbot Grand Challenge 4 and it makes it super easy to build your own scenario-driven skills for Dream.
Start your discovery towards the future of Conversational AI

Learn more about open-source DeepPavlov Dream Platform in our announcement.


This is the most simple example of an end-to-end AI Assistant derived from DeepPavlov Dream.


We thrive for building a platform that will make it easy for you to develop sophisticated AI Assistants. Let us know what you need!
DEEPPAVLOV DREAM ARCHITECTURE
DeepPavlov Dream uses ML & DL models packaged as "Annotators" to extract various features like entities, emotions, sentiment from user utterances

With DeepPavlov Dream, you can build your very own AI Assistant, like Amazon™ Alexa™, Google Assistant™, or Apple's Siri™.

You can learn more about Dream from Dilyara Baymurzina's talks at DeepPavlov Community Call #14 and AI Journey 2021:
DeepPavlov Community Call #14
AI Journey 2021
If you want to try out the entire Dream on your PC beware it's quite resource-hungry.
1 replica eats through:
  • 4 NVIDIA GTX 1080 Ti GPUs
    to run ML & DL models (Annotators)
  • ~40GB RAM
    mostly used by running the light version of the up-to-date Wikidata in memory
  • ~100GB storage
    mostly used to store an up-to-date light replica of Wikidata

DREAM SOCIALBOT DEPLOYMENT IN THE CLOUD AS AN EXAMPLE OF DREAM Platform
DREAM TEAM IN ACTION
Amazon Alexa Prize Socialbot Grand Challenges 3 & 4
In 2019-2020, our DREAM Team was selected by Amazon for Alexa Prize Socialbot Grand Challenge 3. In 2020-2021, our DREAM Team was selected secondly by Amazon to participate in Alexa Prize Socialbot Grand Challenge 4. DREAM Socialbot filled the gap between production-ready agents and state-of-the-art NLP research.
Read our Alexa Prize Technical Reports to learn more how we used DeepPavlov Dream approach for our Socialbot during Alexa Prize Challenge 3 &4!
WHAT'S NEXT?
In the coming months, we will continue releasing more and more sophisticated versions and distributions of the experimental AI Assistant, with more and more Tutorials & Online Courses. We also plan to migrate to the professional-looking Read-The-Docs website. And many more things!

Stay tuned and subscribe to our blog!
COMMUNITY
Join the DeepPavlov community and help grow the conversational AI ecosystem
COMMUNITY
Join the DeepPavlov community and help grow the conversational AI ecosystem