lm-sys/FastChat
FastChat is an open platform for training, serving, and evaluating large language model based chatbots, featuring multi-model serving, extensive model support, and large-scale evaluation datasets.
Awesome AI Agents › Chatbot Platforms
The Data Questionnaire Agent Chatbot is a specialized reverse chatbot designed to assist users by asking them a series of questions about their data integration practices. Its primary function is to gather sufficient information from users to provide tailored advice based on a comprehensive body of knowledge related to data wellness and integration. Unlike traditional chatbots that respond to user queries, this agent proactively engages users with questions to better understand their data environment and challenges. The project includes a user interface (UI) that connects via a websocket, allowing interactive communication between the user and the chatbot. The UI requires building with Yarn and Node.js, and the backend server is implemented in Python, utilizing a Postgres database to store relevant data and knowledge base information. The knowledge base itself is composed of text documents that the chatbot references to generate advice. Setup involves creating a virtual environment using Conda, installing dependencies with Poetry, and configuring environment variables including API keys for OpenAI and Gemini services. The database setup requires creating a Postgres database and initializing it with predefined tables and data. The chatbot server can then be run, and users can interact with it through the web-based UI. This project is particularly useful for organizations or individuals looking to improve their data integration processes by receiving expert advice through an automated conversational agent. It leverages modern AI and database technologies to provide a dynamic and informative user experience. Additionally, the project includes testing capabilities to ensure reliability and correctness. Overall, the Data Questionnaire Agent Chatbot is a valuable tool for enhancing data wellness by guiding users through best practices and recommendations in data integration through an interactive question-and-answer format.
https://github.com/onepointconsulting/data-questionnaire-agent
FastChat is an open platform for training, serving, and evaluating large language model based chatbots, featuring multi-model serving, extensive model support, and large-scale evaluation datasets.
CopilotKit is a React-based framework for building deeply integrated AI assistants, chatbots, and in-app AI agents that enhance user interactions through natural language and contextual understanding.
TypeChat is a library that simplifies building natural language interfaces by using types to define intents and schemas, replacing traditional prompt engineering with schema engineering for improved validation and reliability.
RAGs is a Streamlit app that enables users to build and interact with personalized Retrieval-Augmented Generation pipelines over their own data using natural language instructions.
AdalFlow is a PyTorch-like library that enables building and auto-optimizing large language model applications, including chatbots, RAG, and agents, with a unified framework for prompt optimization and model-agnostic flexibility.
Open-source desktop client that runs an OpenClaw agent locally and bridges it into WeChat, Feishu, Slack and Discord through a graphical setup, with bring-your-own-key and OAuth model access.
LLPhant is a comprehensive PHP generative AI framework inspired by Langchain, supporting multiple LLMs and designed to simplify building powerful AI applications.
Reference implementations of various LangChain agents as interactive Streamlit applications demonstrating conversational AI capabilities and integrations.