Inspiration
Our inspiration for this project came from simplifying data analysis in the competitive esports scene. With so much data available, we wanted to create a tool that would make it easier for coaches, analysts, and fans to access actionable insights quickly and effectively.
What it does
VCT Team Builder provides an AI-powered chatbot interface that allows users to ask questions about VCT players, teams, and tournaments. The chatbot uses linked data to provide detailed insights into player statistics, team compositions, and more, helping users make informed decisions.
How we built it
We built VCT Team Builder using Amazon Bedrock for AI capabilities, LangChain to manage the LLM-powered chains, and Streamlit for the user interface. Python served as the core programming language, and Boto3 was used to interact with AWS services. The project integrates various data sources related to VCT players, teams, and tournaments to provide up-to-date insights.
Challenges we ran into
One of the main challenges we faced was managing large amounts of data related to players and teams, which often led to exceeding the input limits of our AI model. We also had to handle API rate limits and ensure that our chatbot responses remained relevant and concise.
Accomplishments that we're proud of
We are proud to have created a functional prototype that demonstrates the potential of AI in enhancing esports data analysis. The integration of Amazon Bedrock and the ability to handle real-world data queries are significant accomplishments for our team.
What we learned
Throughout the project, we learned a lot about working with AI models, managing large datasets, and building interactive web applications. We also gained valuable experience in troubleshooting API limitations and refining our chatbot's responses to improve user experience.
What's next for VCT-Team-Builder
The next steps for VCT Team Builder include improving the accuracy and efficiency of the chatbot, expanding the data sources to include more tournaments, and adding more features such as predictive analytics to assist in team-building strategies. We also plan to enhance the UI to make it more user-friendly.
Built With
- amazon-web-services
- bedrock
- boto3
- langchain
- python
- s3
- streamlit
