🤝 Top Collabolators
.png&w=640&q=75)
🤓 Submissions
.png&w=828&q=75)
Wikipedia Buddy
A Chat bot that helps people rapidly create Wikipedia articles powered by Cohere's large language model and their retriever. This chat bot helps condense information into Wikipedia articles which can be used for Humans or AI. With this chat bot, you can get the most up to date information and highly verifiable information on topics and people without human labor of maintaining pages. However, This is not the remove the human. This is a chatbot because now a person creating articles, can pick apart the results and ask the chatbot to verify the results. This also solves the problem of dealing with 404 urls to references.
Open Interpreter Tool-kit
One of the most groundbreaking features of large language models are their ability use code to accomplish task. This is a library that leverages Open Interpreter to create and use scripts (tools) for solving problems. The scripts generated are designed to be reused and expanded upon. In addition, each script is well documented for agents to be able to determine if that script can provide the user with the desired answer or accomplish the desired goal. Being able to save code for feature use help minimize the cost of generating code for common task. It also allows for more robust scripts to be able to achieve more. Furthermore, the human, if so desired, can work with the agent to improve or build upon existing tools to account for the agent's shortcomings. Now any user can have an AI generated code base with code that works for their personal machine.
.png&w=828&q=75)
RAG Assistant Agent
One of the difficulties of adopting RAG to a mass audience is lack of understanding of the underline NLP techniques required to produce good queries. With this tool, there is an AI agent that looks at the query and the results to help the user make better queries in the future. For example, If the user never used RAG before, they may ask a vague question. The agent will pick up on this and inform the user. In addition, it will provide suggestion of how to query for better results. This tool is general enough to be easy to adapt with already established RAG pipelines, in addition it is agnostic to data meaning it could be adopted to many fields.
