Project Info
This project did not submit a demo video on Devpost.
Inspiration
We just thought about our own situation because it is always difficult to understand legal texts, then imagine when English is not even your first language. On top of that, having a conversation would help for user experience, sort of a consultation.
What it does
Focusing on immigrants in the US for whom English is not their native language, they could ask questions in their native language to understand how leasing agreements work in San Diego (for ex.) through a conversation with Legal AI. On top of that, Legal AI could recommend based on the topic of the conversation, different lawyers that are specialised in this topic and who are located in the area of the user.
How we built it
We built this project using Next.js for the frontend and flask and chroma for the backend. Gemini API was used for transcription and analysis while Cartesia API was used as a text-to-speech model. The project was deployed on Vercel.
Challenges we ran into
Coding because the documentation from the sponsors had some errors... :// Business model because right now we are just guessing based on what would make sense but actually we should talk to the different customer segments to receive feedback and decide upon the business model.
Accomplishments we're proud of
Mainly solving the errors in the documentation because this took a lot of time.
What we learned
We learned more about the API's of Gemini and Cartesia, most specifically how Cartesia AI does multilingual text-to-speech. Furthermore, this involved integrating AI and text models in a way we we haven't before, all before hosting with a service most of us have no familiarity with.
What's next
Talk to the different customer segments and get feedback!
This project did not link a GitHub repository.
Analysis
No indexed repository for this project, so there are no commit stats to show.
Technology
- CSSUnchecked
- FlaskUnchecked
- Google GeminiUnchecked
- JavaScriptUnchecked
- Next.jsUnchecked
- PythonUnchecked
- ReactUnchecked
- TypeScriptUnchecked
No repository was indexed for this project, so these Devpost claims have not been checked against code.
AI coding agents
No repository was indexed, so agent usage could not be checked.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
No repository was indexed, so there is no codebase to measure.
This project did not link a GitHub repository, so there is nothing to diagram.
This project did not link a GitHub repository, so its feature claims have not been checked against code.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.