Inspiration
In today's fast-paced educational environment, students often struggle to navigate through vast amounts of study materials effectively. They spend countless hours searching for relevant information, trying to assimilate lengthy study materials, solving practice questions, and ensuring their essays are well-structured and plagiarism-free. This lack of efficient study tools not only hampers academic performance but also adds unnecessary stress to students' lives.
What it does
Semantic Search in 100+ languages: Our service enables students to perform searches across a pre-indexed library of study materials in their native language. This saves valuable time and ensures they have access to the information they need quickly and efficiently.
Summarization: Generate concise and coherent summaries, capturing the essence of the original study text. This enables students to grasp key concepts and information more effectively, making their study sessions more efficient.
Practice Question Generation: Students can reinforce their understanding, test their knowledge, and prepare for exams by practising with relevant and tailored questions.
Paraphrasing Assistance: Students can rephrase their sentences while maintaining the intended meaning. This can enhance the quality of essays, avoid plagiarism, and improve writing skills.
Challenges we ran into
We encountered several challenges throughout the project. Initially, we opted for qdrant as our vector database solution, but we faced difficulties during the deployment phase. As a result, we had to make a last-minute switch to pinecone. However, our transition to pinecone wasn't smooth either, as we were initially placed on a waitlist. Fortunately, just in time, we received approval to utilize the free tier of pinecone.
Accomplishments that we're proud of
We are proud of the multiple features we were able to incorporate into our app. This accomplishment was made possible thanks to the seamless integration of Cohere's user-friendly APIs. Their accessible and well-documented APIs enabled us to efficiently implement a wide range of functionalities, enhancing the overall capabilities of our application. We are grateful for Cohere's support, which significantly contributed to the success of our project.
What we learned
During the hackathon, we encountered the need to work with new tools specifically designed for Language Models (LLMs), such as pinecone and langchain. These tools were unfamiliar to us initially, but we quickly adapted and familiarized ourselves with them within a few days. This allowed us to effectively leverage their capabilities and integrate them into our project within the limited time frame of the hackathon.
What's next for Òmòwé.ai
Language Support Expansion: Expand language support beyond English to cater to a global user base. Incorporate additional languages, starting with widely spoken ones, to ensure inclusivity and accessibility for students worldwide.
Integration with Online Libraries and Databases: Partner with reputable online libraries, scholarly databases, and educational content providers to expand the range of study materials available within Omowe.ai. This integration will enrich the content repository and provide students with a more comprehensive and diverse knowledge base.
Adaptive Assessments: Introduce adaptive assessment modules that dynamically adjust the difficulty and content of practice questions based on students' performance. This adaptive approach will personalize the assessment process, providing targeted practice and identifying areas for improvement.
Built With
- cohere
- langchain
- pinecone
- python
Log in or sign up for Devpost to join the conversation.