chroma-core/chroma
Chroma is an open-source search and retrieval database specifically designed for AI applications, supporting document retrieval and vector embeddings.
Awesome AI Agents › RAG and Business Analytics
superagent-ai/super-rag
Super-Rag is a high-performance Retrieval-Augmented Generation (RAG) pipeline designed for AI applications, offering a comprehensive and efficient solution for document summarization, retrieval, reranking, and code interpretation through a unified API. It supports multiple document formats and integrates with various vector databases, making it versatile for different data storage and retrieval needs. The system is production-ready, providing a REST API built with FastAPI, which facilitates easy integration and deployment in real-world applications. Key features include customizable document splitting and chunking, support for different encoding models (both proprietary and open-source), and a built-in code interpreter mode that enables computational question and answer scenarios. This interpreter mode leverages E2B.dev's custom runtimes, allowing users to run code in a sandboxed cloud environment or set up their own runtime infrastructure. Super-Rag also supports session management through unique IDs, which helps in caching and maintaining state across interactions, enhancing performance and user experience. The project offers a cloud API for quick and easy access, with free usage within reasonable limits, making it accessible for developers to get started without complex setup. The ingestion process allows users to upload documents via URLs, specify document processing parameters such as encoding and splitting strategies, and configure vector database settings for indexing. Querying the indexed documents supports advanced filtering, exclusion of specific fields, and toggling the interpreter mode for computational queries. Additionally, documents can be deleted from the index through the API. Supported encoders include OpenAI, Cohere, HuggingFace, FastEmbed, with upcoming support for Mistral and Anthropic. Supported vector databases include Pinecone, Qdrant, Weaviate, Astra, PGVector, and soon Chroma. This extensive support ensures compatibility with popular AI and vector search technologies. Overall, Super-Rag is a robust, flexible, and scalable solution for building AI applications that require efficient document retrieval, summarization, and interactive computational capabilities.
https://github.com/superagent-ai/super-rag
Also in RAG and Business Analytics
vanna-ai/vanna
Vanna is an open-source Python framework that uses Retrieval-Augmented Generation and large language models to convert natural language questions into accurate SQL queries for various databases, simplifying data access and querying.
Canner/WrenAI
Wren AI is an open-source Generative Business Intelligence AI agent that enables data-driven teams to interact with their data using natural language to generate SQL queries, visualizations, and reports for smarter business insights.
import-ai/omnibox
Cross-platform self-hostable AI knowledge hub that collects web pages, files and voice notes, indexes them end to end, and answers questions or drafts text over the local and internet corpus.
apecloud/ApeRAG
Production-ready RAG platform combining graph, vector, and full-text retrieval with AI agents, multimodal document parsing, MCP support, and enterprise deployment features.
newrelic/newrelic-ruby-agent
The New Relic Ruby agent is a comprehensive performance monitoring tool for Ruby applications that helps identify issues, analyze business data, and improve customer experience.
zhongyu09/openchatbi
Open source chat-based business intelligence agent built on LangGraph and LangChain that converts natural language to SQL, runs Python analysis and returns plots, forecasts and anomaly explanations.
bagofwords1/bagofwords
Bag of Words is an open-source agentic analytics platform that connects any LLM to company data, giving each agent scoped data, tools, credentials and permissions for reports, dashboards and automations.