Coder Social home page Coder Social logo

safouat / travelapi Goto Github PK

View Code? Open in Web Editor NEW
2.0 2.0 0.0 17.97 MB

TravelAPI is a Django Rest API designed to enhance travel recommendations for trajects and planning using retrieval-augmented generation (RAG) to refine the OpenAI model GPT-3.5-turbo, facilitated by the Langchain framework.

Python 98.78% Dockerfile 1.22%

travelapi's Introduction

Welcome to TravelAPI!

TravelAPI is a Django server API specifically designed to enhance travel recommendations for trajects and plannings using advanced techniques like retrieval-augmented generation RAG. The primary goal of TravelAPI is to refine the language model (LLM), particularly leveraging OpenAI in our case, to provide users with highly specific and accurate recommendations for restaurants and hotels and activities to do in Morocco. check now Rihla

Data:

We utilized two datasets:

Front End:

Rihla FrontEnd

How It Works

  • Real-World Data: TravelAPI relies on official data provided by the Minister of Tourism and Agriculture for restaurants and hotels. This data is transformed into a chroma format, creating a vector database using encoding techniques provided by OpenAI. This enables TravelAPI to effectively represent textual information numerically.

  • User Preferences: Users provide their preferences such as budget, number of travelers, time constraints, and objectives to guide the recommendation process.

  • AI-Powered Framework: TravelAPI leverages Langchain to provide the search response, which is then given to the OpenAI model GPT-3.5 Turbo to process the result with other fields in a JSON format such as activities, description, and food.

  • Enriched Responses: The responses generated by TravelAPI are enriched with additional activities and detailed descriptions, enhancing the overall travel planning experience for users. this picture explain the process: OPENAI

Getting Started

To get started with TravelAPI, simply follow these steps:

  1. Installation: Install TravelAPI by following the installation instructions on the docker file.

  2. Set Preferences: Provide your travel preferences, including budget, number of travelers, time constraints, and objectives.

  3. Explore Recommendations: Explore the tailored recommendations provided by TravelAPI based on your preferences. ##Other Interested Features:

Other Interested Features:

In addition to travel recommendations, TravelAPI offers the following features:

  • Guides Assistance: We provide users with personalized guides to help them navigate their travel experiences in Morocco.
  • Match Information: Users can access information about matches happening in Morocco during their travel period.

About

TravelAPI aims to deliver tailored recommendations aligned closely with users' preferences and requirements, all powered by real data and cutting-edge AI technology.


Feel free to contribute, suggest improvements, or report issues by creating an issue or submitting a pull request.

travelapi's People

Contributors

safouat avatar moropopi avatar

Stargazers

 avatar Ayman Boufarhi avatar

Watchers

Kostas Georgiou avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.