Conversational Analytics API known limitations

This product or feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms. Pre-GA products and features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

Conversational Analytics API has the following known limitations on the number of data sources, style of visualizations, and size of datasets.

Data source limitations

• You can query only one Looker Explore at a time.

Visualization limitations

• These visualization types are fully supported: Line chart, area chart, bar (horizontal, vertical, stacked) chart, scatterplots, pie chart
• These visualization types are partially supported and may exhibit unexpected behavior: Maps, heatmaps, charts with tooltips

Data processing limitations

• For Looker data sources, the Conversational Analytics API can return a maximum of 5,000 rows per query.
• For BigQuery data sources, the Conversational Analytics API limits data queries to 500 GB of bytes processed.
• The Conversational Analytics API's Python-based reasoning and content retrieval capabilities can accommodate time complexities of up to O(100k) rows.
• Querying large amounts of data can cause reduced reasoning accuracy in data agents.
• The Conversational Analytics API has a maximum token output length of 8,192 tokens. Querying large amounts of data can return a MAX_TOKENS error.

Query limitations

• BigQuery's flexible column names feature is not supported.
• Structs in BigQuery are supported but may sometimes fail.
• For Looker data sources, the API cannot set the value of a filter-only field that is defined by using the LookML parameter parameter.
• Using the Conversational Analytics API to connect to a private IP Looker (Google Cloud core) instance using Looker Studio Pro when that Looker (Google Cloud core) instance is inside a VPC Service Controls perimeter is not a supported configuration and does not meet VPC Service Controls compliance requirements.
• For connections to Looker (Google Cloud core) instances with private IP configurations, Conversational Analytics API does not support Looker (Google Cloud core) instances that are configured to use CMEK or VPC Service Controls.
• Conversational Analytics API doesn't work well with Looker Studio data sources that have field editing in reports disabled in because this setting prevents Conversational Analytics from creating calculated fields.

• When a failure occurs during query validation or execution, the Conversation Analytics API may automatically retry the operation by generating a corrected query. This kind of retry will be attempted a maximum of three times per request.

  If a query fails because of permission or authentication issues, the Conversational Analytics API won't retry the query. Retries are non-deterministic; if the error message suggests that a query is unrecoverable, then the API won't try the query again, even if it is still below the limit of three errors per request.

Question types limitations

• Conversational Analytics API supports questions that can be answered by a single visualization, for example:

  • Metric trends over time
  • Breakdown or distribution of a metric by dimension
  • Unique values for one or more dimensions
  • Single metric values
  • The top dimension values by metric

• Conversational Analytics API doesn't yet support questions that can only be answered with the following types of complicated visualizations:

  • Prediction and forecasting
  • Advanced statistical analysis, including correlation and anomaly detection