Aurora
Precision given to chat gpt
The problem Aurora solves
The name of the hackathon is Stranger hacks chat gpt era.
That made us think about what if we create our own chat gpt 😉Aurora
Aurora is a project that aims to create a chatbot using the GPT-3.5 language model architecture, which is designed to mimic human language patterns and generate natural-sounding responses to user input.
The project would require suitable API keys to access the GPT-3.5 model, which would enable the chatbot to understand and respond to a wide range of user queries, including answering questions, providing recommendations, and engaging in conversation.
The project would be built using Flutter, a popular open-source UI toolkit for building high-quality mobile, web, and desktop applications. This would enable the chatbot to run on multiple platforms, including iOS and Android devices, as well as web browsers.
Overall, the Aurora project has the potential to create a powerful and versatile chatbot that can help users with a wide range of tasks and questions, using advanced machine learning and natural language processing technologies.
Challenges we ran into
When using API keys to access the ChatGPT model for a project like Aurora, it is possible to encounter a range of errors that can cause delays or difficulties in development. Here are some of the potential issues that may have been faced during this project:
API limitations: Depending on the API provider, there may be limitations on the number of requests that can be made within a certain time frame or restrictions on the types of requests that can be made. These limitations can cause errors if they are not properly accounted for in the code or if the API is being used in a way that violates the provider's terms of service.
Inconsistent response times: Because ChatGPT is a language model that relies on complex algorithms, response times can vary significantly depending on the complexity of the input and the current workload of the API servers. Inconsistencies in response times can cause errors if they are not properly accounted for in the code or if they cause delays that impact the user experience.
Compatibility issues: Depending on the programming language and environment being used for the project, there may be compatibility issues with the ChatGPT API that can cause errors. For example, some APIs may only work with specific versions of certain libraries or may require certain configurations that are not present in the development environment.
Data pre-processing: Before sending input to the ChatGPT model, it may be necessary to perform pre-processing to clean and normalize the input data. This can be a complex task depending on the types of input data being used and can require additional coding and testing to ensure that the data is properly formatted and compatible with the ChatGPT API.
Technologies used