Docs/Using Plugins/Dynamic Table

Dynamic Table

The Dynamic Table plugin gives your agent access to a managed, searchable data store. You define tables with typed columns, populate them with rows, and the agent can query that data using natural language — returning structured results directly in conversation.

Unlike static document uploads, data in a Dynamic Table can be added, edited, deleted, and bulk-imported at any time without redeploying or re-indexing the agent.


How It Works

When a user asks a question, the plugin:

  1. Receives the natural language query from the AI.
  2. Converts the query into a vector embedding.
  3. Runs a semantic similarity search against all rows in the configured table.
  4. Applies threshold and tolerance settings to control result quality.
  5. Optionally reranks results using an LLM for improved accuracy.
  6. Returns the matching rows as structured data for the AI to use in its response.

Key Features

FeatureDescription
Flexible schemaDefine typed columns per table: text, number, email, phone, date, boolean.
Semantic searchRows are indexed as vector embeddings and retrieved by semantic similarity.
Tolerance incrementAutomatically lowers the search threshold if not enough results are found.
LLM rerankingOptionally rerank search results using an AI model for better relevance.
Primary keysMark one column as a primary key to enforce uniqueness per table.
Search weightsAssign higher importance to specific columns in the search index.
Import and exportLoad rows from CSV or Excel files; export table data at any time.
Integration APIExternal systems can read and write rows using per-table API keys.

Setup Flow

Follow these steps in order to configure the plugin:

  1. Create a table — define columns, types, and search settings.
  2. Add and manage rows — populate the table and keep data up to date.
  3. Import and export data — bulk load from CSV or Excel, or export the full table.
  4. Configure search settings — tune similarity threshold, tolerance increment, and reranking.
  5. Configure function tool settings — define how the plugin appears and behaves for the AI.
  6. Test semantic search — verify search quality before publishing.
  7. Set up the Integration API — allow external systems to read and write rows programmatically.

Prerequisites

Before creating a plugin instance:

  1. Know what data the table will hold and what users will search for.
  2. Decide which columns should be searchable (included in the vector index).
  3. Determine whether any column needs to be a primary key.
  4. Have at least a small sample of real data ready to test search quality.