The Controllable RAG Agent framework provides a modular approach to building Retrieval-Augmented Generation systems. It allows you to configure and chain retrieval components, memory modules, and generation strategies. Developers can plug in different LLMs, vector databases, and policy controllers to adjust how documents are fetched and processed before generation. Built on Python, it includes utilities for indexing, querying, conversation history tracking, and action-based control flows, making it ideal for chatbots, knowledge assistants, and research tools.

LangChain Chatbot for Customer Support leverages the LangChain framework and large language models to provide an intelligent conversational agent tailored for support scenarios. It integrates a vector store for storing and retrieving company-specific documents, ensuring accurate context-driven responses. The chatbot maintains multi-turn memory to handle follow-up questions naturally, and supports customizable prompt templates to align with brand tone. With built-in routines for API integration, users can connect to external systems like CRMs or knowledge bases. This open-source solution simplifies deploying a self-hosted support bot, enabling teams to reduce response times, standardize answers, and scale support operations without extensive AI expertise.