RAGApp is designed to simplify the entire RAG pipeline by providing out-of-the-box integrations with popular vector databases (FAISS, Pinecone, Chroma, Qdrant) and large language models (OpenAI, Anthropic, Hugging Face). It includes data ingestion tools to convert documents into embeddings, context-aware retrieval mechanisms for precise knowledge selection, and a built-in chat UI or REST API server for deployment. Developers can easily extend or replace any component—add custom preprocessors, integrate external APIs as tools, or swap LLM providers—while leveraging Docker and CLI tooling for rapid prototyping and production deployment.

Arenas is designed to streamline the development lifecycle of LLM-powered agents. Developers can define agent personas, integrate external APIs and tools as plugins, and compose multi-step workflows using a flexible DSL. The framework manages conversation memory, error handling, and logging, enabling robust RAG pipelines and multi-agent collaboration. With a command-line interface and REST API, teams can prototype agents locally and deploy them as microservices or containerized applications. Arenas supports popular LLM providers, offers monitoring dashboards, and includes built-in templates for common use cases. This flexible architecture reduces boilerplate code and accelerates time-to-market for AI-driven solutions across domains like customer engagement, research, and data processing.

Chat-With-CUHKSZ provides a streamlined pipeline for building a domain-specific chatbot over the CUHKSZ knowledge base. After cloning the repository, users configure their OpenAI API credentials and specify document sources, such as campus PDFs, website pages, and research papers. The tool uses LlamaIndex to preprocess and index documents, creating an efficient vectorized store. LangChain orchestrates the retrieval and prompts, delivering relevant answers in a conversational interface. The architecture supports adding custom documents, fine-tuning prompt strategies, and deploying via Streamlit or a Python server. It also integrates optional semantic search enhancements, supports logging queries for auditing, and can be extended to other universities with minimal configuration.