Be the first to try a brand new demo of DeepPavlov Library!
Let's try
DEEPPAVLOV PRODUCTS
 
 

DeepPavlov

An open source conversational AI framework
DeepPavlov makes it easy for beginners and experts to create dialogue systems.
See the sections below to get started.
For beginners
The best place to start is with the user-friendly tutorials. They provide quick and convenient introduction on how to use DeepPavlov with complete, end-to-end examples. No installation needed.
For experts
Guides explain the concepts and components of DeepPavlov. Follow step by step instructions to install, configure and extend DeepPavlov framework for your use case.

For beginners
The best place to start is with the user-friendly tutorials. They provide quick and convenient introduction on how to use DeepPavlov with complete, end-to-end examples. No installation needed.
For experts
Guides explain the concepts and components of DeepPavlov. Follow step by step instructions to install, configure and extend DeepPavlov framework for your use case.
RUN CODE NOW
RUN CODE NOW
Why DeepPavlov
DeepPavlov is an open source framework for chatbots and virtual assistants development. It has comprehensive and flexible tools that let developers and NLP researchers create production ready conversational skills and complex multi-skill conversational assistants.
Latest deep learning models
Use BERT and other state-of-the-art deep learning models to solve classification, NER, Q&A and other NLP tasks.
Multi-skill dialog management
DeepPavlov Agent allows to build industrial solutions with
multi-skill integration via API services.
Easy to use
Run pretrained or your own NLP components and conversational skills from Python code, command line interface, API or Docker.
Try DEMO
Through the Internet
We write for the popular IT and ML blogs and have our own blog on Medium.
Find Out More News
Community
Join the DeepPavlov community and help grow the conversational AI ecosystem
DeepPavlov Forum
  • Automatic Dataset Generation Tool
    by Eugene
    Go-Bot is a framework for building simple goal-oriented bots in DeepPavlov. Originally it supported training only with the DSTC2 Schema format. While it is quite rich and powerful, converting your data into DSTC-2 Schema might be a challenging task. Fortunately, one of our Open Source community members, Eugene, stepped in and built his own DSTC2-compliant dataset generation tool. After internal analysis and code review, we've been happy to release it as a part of our v0.11 release!
  • Top N Answers In ODQA Model
    by Mapryl
    ODQA (open-domain question-answering) is one of the most popular components of DeepPavlov. It allows the computer to find answers directly in the raw text. However, initially you could only use this model to get the best answer from the candidates found . This made usage of the model rather limited . Thanks to Mapryl's Top N Answers PR to the ODQA model, now you can get N candidate answers with scores . It was shipped as part of our v0.12 release.
Dream Team
DeepPavlov has a Dream Team. Welcome
and keep in touch with team of Alexa Prize Socialbot Grand Challenge 2019!
Official Site
Dream Team
DeepPavlov has a Dream Team. Welcome and keep in touch with team of Alexa Prize Socialbot Grand Challenge 2019!
Official Site