knowledge-intelligence
Knowledge Intelligence: a multi-tenant, permission-aware enterprise RAG platform. Grounded answers with citations over documents, databases and SaaS sources, pl
What is knowledge-intelligence?
Knowledge Intelligence: a multi-tenant, permission-aware enterprise RAG platform. Grounded answers with citations over documents, databases and SaaS sources, plus Text-to-SQL, agents and a live connections map. FastAPI, PostgreSQL/pgvector, Next.js.
Overview of knowledge-intelligence
What it is
CSV-AI is an open-source application for AI-powered CSV file analysis. It allows users to chat with, summarize, and analyze CSV data using large language models from OpenAI, Anthropic, or a local Ollama instance. The application is built with Streamlit and is designed for deployment on Streamlit Cloud, local machines, or via Docker.
Key features
- 💬 Chat: schema- and sample-aware Q&A with token streaming.- 📝 Summarize: single-call structured overview of CSV data.- 📊 Analyze: deterministic pandas statistics alongside LLM-generated narrative, with charts, missingness, and correlations.- 🔌 Multi-provider support: OpenAI, Anthropic Claude, or local Ollama.- 🎛️ Modern UI: sidebar navigation, chat messages, light/dark theme, custom CSS.- 🧱 Modular architecture: clean
app/package with no Streamlit imports in services, enabling future API split.
Use cases
CSV-AI is suitable for anyone who needs to quickly explore, summarize, or ask questions about data stored in CSV files. It can be used by data analysts, business users, or developers who want an interactive interface to understand their datasets without writing complex code.
Getting started
bashgit clone https://github.com/Safiullah-Rahu/CSV-AI.gitcd CSV-AIpython -m venv .venv && source .venv/bin/activate # Windows: .venv/Scripts/activatepip install -r requirements.txtcp .env.example .env # then add your API keysstreamlit run streamlit_app.py
License and pricing
CSV-AI is released under the MIT license. It is open-source and free to use. Users are responsible for their own API keys and any associated costs from OpenAI, Anthropic, or local Ollama.
Based on the project's public README and repository metadata.