Draft:Rasa (software)
 | Review waiting, please be patient.
This may take 3 months or more, since drafts are reviewed in no specific order. There are 3,878 pending submissions waiting for review.
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
Reviewer tools
|
| Rasa | |
|---|---|
| Developer | Rasa Technologies |
| Release | 2016 |
| Written in | Python |
| Type | Conversational AI, natural language processing |
| Website | rasa |
Rasa is a software framework for building text- and voice-based chatbots and AI agents. It is written in Python and developed by Rasa Technologies.[1]
Rasa's earlier versions used intent-based machine-learning models, including the DIET architecture introduced in 2020,[2] while later versions adopted approaches based on large language models.[3] The framework is offered under both open-source and commercial enterprise licenses.[3]
Architecture
[edit]The framework was introduced in a paper presented at the NeurIPS (formerly NIPS) 2017 Workshop on Conversational AI.[4]
DIET
[edit]DIET (Dual Intent and Entity Transformer) is a transformer-based architecture used in Rasa for joint intent classification and entity extraction, introduced in 2020.[5] According to a study published in IEEE Access, the architecture can incorporate embeddings from pretrained language models such as BERT, and has been adapted for tasks beyond dialogue, including sentiment analysis.[2]
Use of large language models
[edit]Later versions of the framework shifted from intent-based natural language understanding toward approaches based on large language models and in-context learning.[6]
Use in research
[edit]Rasa has been used and evaluated in academic research on conversational AI. A study published in IEEE Transactions on Software Engineering compared natural language understanding platforms including IBM Watson, Google Dialogflow, Rasa and Microsoft LUIS for intent and entity recognition.[7] Researchers have used the framework to build chatbots in domains such as student services[8] and other domain-specific applications.[9]
History
[edit]Rasa Technologies was founded in 2016 by Alan Nichol and Alex Weidauer, and the framework was first released the same year.[1] The company raised US$1.1 million in 2018,[10] US$13 million in a 2019 Series A led by Accel,[11] US$26 million in 2021,[12] and US$30 million in a 2024 Series C.[3][13] Investors have included Accel, Andreessen Horowitz, StepStone Group and PayPal Ventures.[3]
Editions
[edit]Rasa is available as open-source software and as a commercial product, Rasa Pro, which includes a free developer edition.[14] The company also offers a graphical building interface, Rasa Studio.[3]
Further reading
[edit]- Kong, Xiaoquan; Wang, Guan (2021). Conversational AI with Rasa. Packt Publishing. ISBN 978-1-80107-705-7.
- Vajjala, Sowmya; Majumder, Bodhisattwa; Gupta, Anuj; Surana, Harshit (2020). Practical Natural Language Processing: A Comprehensive Guide to Building Real-World NLP Systems. O'Reilly Media. ISBN 978-1-492-05404-7.
References
[edit]- ^ a b Lardinois, Frederic (December 16, 2016). "Rasa NLU gives developers an open-source solution for natural language understanding". TechCrunch. Retrieved June 18, 2026.
- ^ a b Arevalillo-Herráez, Miguel; Arnau-González, Pablo; Ramzan, Naeem (2022). "On Adapting the DIET Architecture and the Rasa Conversational Toolkit for the Sentiment Analysis Task". IEEE Access. 10: 107477–107487. doi:10.1109/ACCESS.2022.3213061.
- ^ a b c d e "Rasa, an enterprise-focused dev platform for conversational GenAI, raises $30M". TechCrunch. February 14, 2024. Retrieved June 18, 2026.
- ^ Bocklisch, Tom; Faulkner, Joey; Pawlowski, Nick; Nichol, Alan (2017). Rasa: Open Source Language Understanding and Dialogue Management. NIPS 2017 Workshop on Conversational AI. arXiv:1712.05181.
- ^ Bunk, Tanja; Varshneya, Daksh; Vlasov, Vladimir; Nichol, Alan (2020). "DIET: Lightweight Language Understanding for Dialogue Systems". arXiv:2004.09936 [cs.CL].
- ^ Bocklisch, Tom; Werkmeister, Thomas; Varshneya, Daksh; Nichol, Alan (2024). "Task-Oriented Dialogue with In-Context Learning". arXiv:2402.12234 [cs.CL].
- ^ Abdellatif, Ahmad; Badran, Khaled; Costa, Diego Elias; Shihab, Emad (2022). "A Comparison of Natural Language Understanding Platforms for Chatbots in Software Engineering". IEEE Transactions on Software Engineering. 48 (8): 3087–3102. doi:10.1109/TSE.2021.3078384.
- ^ Rodrigues, Fátima; Fonseca, João (2026). "ChatBot for student service based on RASA framework". Knowledge and Information Systems. 68. doi:10.1007/s10115-025-02655-4.
- ^ Kumari, Vijay; Gosavi, Chinmay; Sharma, Yashvardhan; Goel, Lavika (2022). "Domain-Specific Chatbot Development Using the Deep Learning-Based RASA Framework". Communication and Intelligent Systems. Lecture Notes in Networks and Systems. Springer. pp. 883–896. doi:10.1007/978-981-19-2130-8_69.
- ^ "Rasa raises $1.1 million to grow its natural language understanding for businesses". VentureBeat. 2018. Retrieved June 18, 2026.
- ^ "Rasa raises $13M led by Accel for its developer-friendly open-source approach to chatbots". TechCrunch. April 11, 2019. Retrieved June 18, 2026.
- ^ "Conversational AI startup Rasa shows steady growth with fresh $26 million". VentureBeat. 2021. Retrieved June 18, 2026.
- ^ "Rasa lands $30M to supercharge customer service with generative AI assistants". VentureBeat. February 2024. Retrieved June 18, 2026.
- ^ "Rasa Pro Developer Edition". Rasa. Retrieved June 18, 2026.
Category:2016 software Category:Natural language processing software Category:Chatbots Category:Artificial intelligence Category:Python (programming language) software