Hello Charalampos, First of all, thank you for your interest in our proposal! Regarding your questions, automating the creation of the intent examples is a rather challenging task. It can indeed be accomplished using NLP techniques, such as parsing as you are suggesting, or by using language models. In the first case, a clever post-processing algorithm is needed to use the parsed description to create the sentences, as for the second, LMs can be used in a few-shot or zero-shot manner. In all cases, this NLP process will need a text or words to work on, which can either be the API description or a set of keywords given at model definition time. The OpenAPI-to-dFlow M2M transformation can be developed using textX ( https://textx.github.io/textX/3.1/) which is used to define and create dFlow as well. Hence, the input data will be in a structured format based on OpenAPI spec, which you will design, while the output (the generated model) can be a dFlow model which already has a specific structure. Finally, the aim of the final model will be to map an OpenAPI to an end-to-end assistant scenario, meaning the intents, services and responses. In case the different API paths lead to different assistant scenarios, the metamodel you will design should support it. This will be the case when each API path has an entirely different semantic meaning and hence intent and intent examples. Otherwise, you may use an "if-else" logic (a feature we will develop for dFlow in the near future), so that if let's say a specific entity exists, the assistant scenario should trigger one path or if there is no entity the other. This is the most complex mapping strategy I can think of. However, we are open to other suggestions regarding this part. Feel free to contact us for further information! Best, Manos On Sun, Mar 12, 2023 at 5:58 PM babis Metaxas <babismetaxas000 [ at ] gmail [ dot ] com> wrote: > Hello, > I hope this email finds you well, i'm following up on my previous email, > regarding my interest in contributing to OpenAPI integration in dFlow DSL. > I understand that you may be busy, and I just wanted to check in and see if > there is any updates or suggestions you had for me. > > I'm still very interested in contributing to the project and would > appreciate any guidance or advice you may have. > > Thank you for your time and consideration. > > Best regards, > Charalampos Metaxas > ---- > Λαμβάνετε αυτό το μήνυμα απο την λίστα: Λίστα αλληλογραφίας και συζητήσεων > που απευθύνεται σε φοιτητές developers \& mentors έργων του Google Summer > of Code - A discussion list for student developers and mentors of Google > Summer of Code projects., > https://lists.ellak.gr/gsoc-developers/listinfo.html > Μπορείτε να απεγγραφείτε από τη λίστα στέλνοντας κενό μήνυμα ηλ. > ταχυδρομείου στη διεύθυνση <gsoc-developers+unsubscribe [ at ] ellak [ dot ] gr>. > -- Emmanouil G. Tsardoulias PhD, Electrical Engineer Aristotle University of Thessaloniki, Faculty of Engineering School of Electrical and Computer Engineering 54124 Thessaloniki, GREECE Tel.: +302310995922 http://users.auth.gr/etsardou/ http://r4a.issel.ee.auth.gr/
---- Λαμβάνετε αυτό το μήνυμα απο την λίστα: Λίστα αλληλογραφίας και συζητήσεων που απευθύνεται σε φοιτητές developers \& mentors έργων του Google Summer of Code - A discussion list for student developers and mentors of Google Summer of Code projects., https://lists.ellak.gr/gsoc-developers/listinfo.html Μπορείτε να απεγγραφείτε από τη λίστα στέλνοντας κενό μήνυμα ηλ. ταχυδρομείου στη διεύθυνση <gsoc-developers+unsubscribe [ at ] ellak [ dot ] gr>.