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
vanna-ai/vanna
Vanna is an open-source Python framework licensed under MIT that enables users to interact with SQL databases through natural language queries by leveraging Retrieval-Augmented Generation (RAG) techniques combined with large language models (LLMs). The core functionality of Vanna involves training a RAG model on your database schema, documentation, and existing SQL queries, which then allows users to ask questions in plain English. These questions are automatically converted into accurate SQL queries that can be executed on the connected database, returning results directly. This approach simplifies database querying for users who may not be proficient in SQL, making data access more intuitive and efficient. The framework supports a wide range of LLM providers including OpenAI, Anthropic, Google's Gemini, HuggingFace, AWS Bedrock, Ollama, Qianwen, Qianfan, and Zhipu, allowing flexibility in choosing the underlying language model. It also integrates with various vector stores such as AzureSearch, Opensearch, PgVector, PineCone, ChromaDB, FAISS, Marqo, Milvus, Qdrant, Weaviate, and Oracle, which are used for efficient retrieval in the RAG process. Vanna supports numerous popular databases including PostgreSQL, MySQL, PrestoDB, Apache Hive, ClickHouse, Snowflake, Oracle, Microsoft SQL Server, BigQuery, SQLite, and DuckDB, making it versatile for different data environments. The project provides multiple user interfaces like Jupyter Notebooks, Streamlit apps, Flask apps, and Slack integrations, which can be used out-of-the-box or customized. The training process involves feeding the model with database DDL statements, business documentation, and sample SQL queries to enhance the model's understanding of the data structure and business context. After training, users can ask natural language questions, and Vanna generates the corresponding SQL queries and optionally executes them to return results. Overall, Vanna is a powerful tool that bridges the gap between natural language and SQL databases, enabling more accessible and accurate data querying through advanced AI techniques.
https://github.com/vanna-ai/vanna
Also in RAG and Business Analytics
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.
superagent-ai/super-rag
Super-Rag is a high-performance RAG pipeline offering summarization, retrieval, reranking, and code interpretation for AI applications through a simple and production-ready REST API.