Rebbix has a brand new look! Learn more about our updates in an article

what we offercase studiesaboutcareersbloglife
contact us
get team and budget estimates

let's talk

engukr
contact us

all cases

building an AI-powered search chatbot for a cruise travel company

scroll down

AI tech

AI tech

What’s a Rich Text element?

The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.

Static and dynamic content editing

A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel.

  1. my first listA rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel.
  2. my first
  3. item
  4. asfsdf
  5. fweg
  6. we
  • Voila!
  • ‍
  • my first listA rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel.
  • ‍

How to customize formatting for each rich text

Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of" nested selector system.

teast

long story short 

The customer is a global travel company that offers cruises worldwide. Our idea was to create an intelligent AI-powered search chatbot to help users find the right cruise with a few simple clicks.

Our Rebbix team did extensive R&D work to implement an idea. The main task was to use different prompt techniques of a Large Language Model (LLM) to identify keywords in user messages and suggest the most relevant travel options. We created and embedded the list of presumed user intentions and programmed a format for the answer. We also implemented data sorting to narrow the search.

As a result, we got a chatbot that determines users' intents in real-time conversation. The chatbot asks specific questions related to destination, trip duration, budgets, and more. Users can communicate with the chatbot in natural language. 

The chatbot also understands natural language time queries (like fall, winter, tomorrow, next week, first week of September, and so on). It automatically detects the current date and converts user text into a standard date object that can be used in search queries. ‍

tools & technologies

Python, JavaScript, LLM, Elasticsearch

key outcomes

99.9%

The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.

‍

improved User Experience

the chatbot engages in a conversation and asks questions like an actual human

‍

personalization

chatbot provides personalized offers based on the specific user`s needs

timesaving

search with the AI chatbot is faster and more automatized, allowing users to receive the needed information in a second

‍

the successful POC

AI solutions that understand user text queries show significant potential. with sufficient parameters to guide the mapping, AI features can seamlessly be integrated within many existing solutions, even large legacy systems

‍

client testimonial

team setup

2

afasfa

3

Software Engineers

‍

‍

1

QA

‍

‍

meet the team

No items found.

what we did 

  • AI prompt engineering to minimize AI hallucinations
  • transform user input to parameters that can be used in existing search API, like "I want to see penguins in May" is transformed to region: Antarctica, time: 01-31 May 2025, person: 1 
  • use the model to convert natural language time queries into the required dates
  • automatically detect what data is still needed to narrow the search and ask a user to provide it as a plain text input or as a batch of dynamic filters

see how it works

need help with your AI-powered solution?

continue reading:
No items found.

book a free consultation

Set up a quick call with Taras Kunch, Rebbix's Chief Technology Officer, to discuss the challenges you're facing and get a timeline and budget estimates.

book a 30-min Calendly call

other case studies

get team and budget estimates

let's talk

language
approachapproach
socials

By clicking “Accept All Cookies”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. View our Privacy Policy for more information.

Accept