Inspiration
Oreally was inspired by the need to address the isolation and constant propaganda that people face, which promotes cruelty and glorifies violence. Recognizing the lack of opportunities for self-reflection, we aimed to create a tool that encourages deep, meaningful conversations and introspection.
What it Does
Oreally is a chatbot that asks users thought-provoking questions about their beliefs, guiding them to uncover their own answers and understand their thoughts more deeply. It also provides candidate voting records and election information in an easily accessible format, helping users make informed decisions.
How We Built It
We built Oreally using a RAG system to facilitate meaningful conversations. The chatbot integrates LangChain and OpenAi LLM and a comprehensive database of voting records and election information, ensuring user-friendly interactions.
Challenges We Ran Into
One major challenge was integrating a RAG system capable of understanding complex human thoughts and asking contextually appropriate questions. Additionally, integrating extensive voting and election data into a user-friendly format required significant technical effort.
Accomplishments That We're Proud Of
We are proud of creating a chatbot that fosters self-reflection and provides valuable election information in an accessible way. Successfully integrating a large amount of voting data into the chatbot's responses is a significant achievement.
What We Learned
We learned the importance of tools that encourage genuine human interaction and self-reflection. Additionally, we gained valuable insights into the technical challenges of building sophisticated NLP models and integrating large datasets.
What's Next for Oreally
Next, we plan to expand Oreally's capabilities to cover more topics and provide more personalized insights. We also aim to continuously update the voting records and election data to ensure users have access to the most current information.
Built With
- langchain
- openai
- python
- streamlit

Log in or sign up for Devpost to join the conversation.