USER MANUALS

Denodo Assistant Chatbot for VQL Shell

The Denodo Assistant Chatbot is a fully interactive, AI-powered companion integrated directly into the VQL Shell to streamline your daily Design Studio tasks using natural language.

For the most accurate help, the Assistant is highly context-aware and can read the queries you select directly from the VQL shell. Additionally, the Assistant uses a variety of built-in tools to help you with the following tasks:

  • Explain, fix, and generate queries: Get assistance writing or troubleshooting VQL.

  • Search metadata: Search your catalog’s metadata (requires the vector integration to be enabled).

  • Explore databases and views: List the views within a database, and inspect the schema and VQL definition of any specific view.

  • Generate commands: Quickly find and generate commands using the built-in HELP tool.

  • Analyze data: Run SELECT queries to inspect views and analyze your data (requires the Execute Query tool to be enabled in the Chatbot Configuration).

To use the Assistant, simply type your request into the chat panel. The Assistant will analyze your input and automatically invoke the appropriate tools to provide the best solution.

Interaction with the Denodo Assistant in the VQL Shell

Interaction with the Denodo Assistant in the VQL Shell

Alternatively, you can explicitly trigger its specialized features using the following commands:

Within the Denodo Assistant panel, you can also perform the following actions:

  • Add user level custom instructions: Click the gear icon to define specific instructions that will automatically apply to all your interactions with the Assistant in the VQL Shell.

  • Filter by database: Select a subset of databases to limit the scope of your requests. When one or more databases are selected, the Assistant will only consider views from those specific databases (this applies to the /generate and /metadata features).

  • Clear chat history: Click the clear icon to reset your current conversation with the Assistant.

To modify the configuration of the chatbot, please refer to the Chatbot Configuration section.

Explain Query

The feature Explain query offers comprehensive explanations for VQL queries.

Explain query result

Explain query result

Diagnose Query

The feature Diagnose query analyzes a given query, providing both a corrected version and an explanation of the modifications made.

Diagnose query result

Diagnose query result

Metadata Query

The feature Metadata Query analyzes a natural language input to provide a list of the most relevant views, presenting an explanation for the selection along with a table with links for easy access.

Metadata query result

Metadata query result

Generate Query From Natural Language

The feature Generate query from natural language analyzes a plain language query written by the user and provides a corresponding VQL query along with an explanation of what the query does.

Generate query result

Generate query result

Improving Query Accuracy

Here are some considerations to take into account to improve the accuracy of the generated query and explanation:

Sample Data

To generate accurate VQL, the Denodo Assistant can analyze a small sample of a view’s actual data alongside its metadata. This helps the AI resolve format ambiguities that aren’t defined in the field descriptions.

For example, if you ask the Denodo Assistant “generate a query that lists all employees from California”, the AI must decide if the filter should be WHERE state = 'California' or WHERE state = 'CA'. By checking a data sample, the AI can see the actual format used and generate the correct clause immediately.

This data sampling also resolves other common ambiguities:

  • Date formats: Differentiating between 2025-09-02 and 09/02/2025.

  • Categorical Codes: Determining if a status is a string ‘Shipped’ or a numerical code like 3.

Enabling sample data ensures more reliable and precise VQL queries on the first attempt. You can activate this feature by enabling the Use sample data option in the Denodo Assistant configuration.

Descriptions

Descriptions for views, fields, and tags provide the essential business context the AI needs. While the Denodo Assistant is powerful, it does not inherently know your organization’s specific terminology.

Clear, human-readable descriptions are critical for accuracy when technical names are not self-explanatory (e.g., c_bal, ord_dt, or is_act). For instance, a field named status is ambiguous, but a description like “Customer account status: A for Active, I for Inactive, S for Suspended” provides the precise detail the AI needs to answer questions correctly.

By providing this precise detail, you directly improve the AI’s ability to interpret your data and generate more intelligent, accurate VQL.

Add feedback