Areesa Ashfaq@Areesa

DiscernAI is designed to tell you whether a text is misinformation or benign

Our goal is to develop a system that can take documents in any language and allow users from different parts of the world with different languages to interact with those documents. This can help spread knowledge without any language barrier. We are first testing it out with Quranic text, which is in Arabic, and building a chatGPT-style bot for question answering. In future, we would like to expand it to additional documents in any language. We first perform embedding of the text using Cohere's multilingual embed model and save those embeddings in a vector database, Pinecone DB in our case. We then take user queries and also embed them and perform a similarity-based search to provide the most relevant results based on the query. The app is currently deployed and publicly available. Streamlit app link: https://taqihaider7-tafsir-quran-sementic-search-llm-app-fwh2if.streamlit.app/

ezAGI {easy Augmented Generative Intelligence} provides a comprehensive framework to develop modular, scalable and efficient AGI. Integrating multiple AI models ezAGI handles API management efficiently while managing memory effectively for continuous reasoning and interaction without user intervention. Components of ezAGI include SocraticReasoning, AGI, FundamentalAGI, LogicTables, OpenMind, memory management and API key management with multi-model support.ezAGI seamlessly integrates models from Together, Groq, and OpenAI to enhance any LLM with Continuous Autonomous Reasoning. ezAGI creates short term memory as an input/reponse constant. Leveraging internal reasoning and logic ezAGI will autonomously create decisions based on data inputs and predefined rules. ezAGI is a comprehensive framework for developing autonomous modular AGI systems. SocraticReasoning.py implements socratic reasoning to add premises and challenging them to draw_conclusion. agi.py handles learning from data to make_decision by initializing AGI as a chatter instance. memory provides the abiltity to learn from environmental data and store dialogue as history. automind.py manages environment interaction and response generation to . logic.py handles logical variables and expressions, generates truth tables, and validates truths, supporting ezAGI's reasoning. openmind.py provides an internal reasoning loop for continuous AGI operation, adding prompts reasoned from premise into processed conclusions while autonomously saving internal reasoning. memory.py manages memory storage, ensuring organized and persistent storage of short-term, long-term, and episodic memories. api.py uses the dotenv library for secure API key management, allowing dynamic integration with AI services. chatter.py provides input-response mechanisms for a multi-model environment including together, groq, and openAI ensuring robust and logical response. ezAGI augments the intelligence of large language models.