Knowi's private AI service consists of two core components:
- A vector database (Milvus)
- LLM
Both components are fully hosted within Knowi’s infrastructure, ensuring that your data never leaves the environment. In addition to Knowi's built-in AI, you can configure external AI providers such as OpenAI or Anthropic (Claude) for enhanced capabilities. See AI Model Providers for setup details.
Knowi provides a suite of AI-powered tools that enable you to explore, analyze, and interact with your data securely and efficiently:
- Agentic BI: Agentic BI enables conversational analysis of your datasets and documents, allowing you to ask questions in natural language and receive insights, visualizations, and summaries directly within Knowi.
- AI Agents: Dashboard, widget, and query agents work within Knowi to take action on your behalf through natural language commands.
- AI Dashboards: Create full dashboards from your dataset with a single click, allowing you to quickly analyze your data.
- AI Model Providers: Configure external AI providers (OpenAI, Anthropic Claude) and select models per feature.
- Document AI: Document AI allows you to upload documents, ask natural language questions, and get precise answers directly from the content, all within Knowi.
- Embedding Agent Chat: Embed an AI-powered chat interface into external applications, enabling end users to interact with your Knowi data through natural language queries.
- InstantSights: InstantSights generates plain English insights and anomaly detection from your dashboards, enables you to create insight widgets for your dashboard, and allows you to send summary reports.
- Natural Language Processing (NLP): Knowi's NLP feature lets users ask questions in plain English to generate insights and visualizations directly from the data.
- OpenAI as a Datasource: Knowi provides built-in support to create a dataset with OpenAI as a datasource.
- Recommendation Widget: The Recommendation Widget provides automated, conversational analysis of your dataset using AI.