📄️ Agents
An Agent within the Denzing application is an entity that serves as a specialized expert in interacting with complex data. Users can send data-related queries to an Agent, and the Agent can retrieve, analyze, and respond based on its expertise in the data source it is bound to. Each Agent is connected to a specific data source (e.g., a database, CSV file, etc.), and it can help users interact with the data in a conversational manner.
📄️ Data Sources
Denzing empowers users to connect with their data—wherever it lives. Whether your files are stored in the cloud or locally, our platform supports seamless integration with a wide variety of data sources, enabling Agents to interact with your data in real time through natural, conversational queries.
📄️ Metadata
Metadata provides critical context and structure to data, enabling efficient querying and accurate responses. It is categorized into two types: Schema Metadata and Semantic Metadata. This documentation details these metadata types, along with examples in YAML format.
📄️ Chat with Agent
You can initiate a conversation with an agent either from the Chat Landing Page or the Agents Page. (Refer to Getting Started with Denzing for details on accessing the landing page.) To navigate to the list of available agents, click on Agents in the left sidebar of the Denzing interface. From there, you can select an existing agent shared with you or create a new one. Once an agent is selected, the chat interface will open, allowing you to begin interacting with it.
📄️ Create Agent
1. In the Denzing interface, locate the sidebar which contains key options for interacting with data.