datavane/tis

Support agile Ontology DataOps Based on Flink, DataX and Flink-CDC with Web-UI

What it solves

TIS addresses the complexity of traditional data engineering by using AI to automate the creation and management of data pipelines. It removes the need for manual configuration and complex SQL writing, allowing users to build data workflows and perform data analysis using natural language.

How it works

TIS integrates Large Language Models (LLMs) directly into the data lifecycle. It uses a Pipeline AI Agent to interpret natural language requests to automatically select plugins, configure parameters, and orchestrate tasks. For data analysis, it employs a ChatBI module that utilizes an Ontology layer and a Neo4j-based knowledge graph to understand business terminology. It then uses GraphRAG (Retrieval-Augmented Generation) to retrieve relevant data entities and generate insights without requiring the user to write SQL. Under the hood, it remains powered by proven data engines like DataX and Flink-CDC.

Who it’s for

TIS is designed for data engineers looking to simplify pipeline orchestration and business users who need to perform data analysis and gain insights without technical SQL expertise.

Highlights

  • Natural Language Pipelines: Create data pipelines by simply describing requirements in plain language.
  • ChatBI: Ask questions about your data in natural language and receive answers powered by GraphRAG and your business knowledge graph.
  • Knowledge Asset Management: Uses an Ontology layer and Neo4j to store and evolve business definitions, metrics, and entity relationships.
  • Proven Infrastructure: Built on top of reliable batch and stream processing engines like DataX and Flink-CDC.
  • Extensible Architecture: Features a plugin-based system inspired by Jenkins, allowing for easy expansion and custom development.

Related

  • Project
    DeepInsight-AI/DeepBI

    An AI-native data analysis platform that uses LLMs to allow users to explore, query, and visualize data from multiple sources via natural language conversations.

  • Project
    pipeshub-ai/pipeshub-ai

    PipesHub is an open‑source, self‑hostable platform that connects enterprise data sources (Slack, Google Drive, GitHub, etc.) to AI applications. It builds a permission‑aware knowledge graph, stores vector embeddings, and lets any LLM generate explainable answers with citations. The project includes Docker‑Compose deployment, a no‑code agent builder, MCP support, and SDKs for Python, TypeScript, and Go.

  • Project
    microsoft/Conversation-Knowledge-Mining-Solution-Accelerator

    An AI-powered pipeline and analysis platform that extracts insights from large volumes of conversational data, featuring an LLM-driven chat interface and automatically generated KPI dashboards.

  • Project
    dataease/SQLBot

    An intelligent data querying system based on LLMs and RAG that enables conversational data analysis (ChatBI) by converting natural language into SQL and visual charts.

  • Project
    GiovanniPasq/agentic-rag-for-dummies

    A tutorial‑style, open‑source Python project that shows how to build a modular, agent‑driven Retrieval‑Augmented Generation system with LangGraph, hierarchical chunking, conversation memory, query clarification, multi‑agent map‑reduce, self‑correction, and evaluation via RAGAS. Works with Ollama, OpenAI, Anthropic, Google Gemini, Qdrant vector store, and optional Langfuse observability.