GenaiDocumentQuery
The class inherits from the
GenaiVectorQuery class. It enables an API caller to perform a vector query that is
filtered to include chunks from a single document. The Content Platform Engine server verifies
whether the call has VIEW_CONTENT access for the underlying document. The set of
document chunks that closely match the input prompt are then returned. For more information, see
GenaiDocumentQuery class in the FNCM documentation.
| Property | Data type | Description |
|---|---|---|
GenaiLLMPrompt |
String | The input prompt from the user. The maximum length for the value is 4000 characters. |
GenaiLLMModelName |
String | An optional watsonx LLM model name. The maximum length for the value is 256 characters. |
GenaiLLMResponse |
String | The response from the watsonx LLM. |
GenaiLLMMaxOutputTokens |
Integer | If you set this parameter, it overrides the LLM maximum output tokens parameter which has a default value of 512. You cannot set a value less than 10 or greater than 8192. |
GenaiVectorChunks |
String | A JSON value that contains the document chunks that the vector search returns. If
GenaiPerformLLMQuery is false, then this property holds all the vector query
results. If GenaiPerformLLMQuery is true, then this property holds the chunks that
were submitted to the LLM as context for the LLM query. |
GenaiPerformLLMQuery |
Boolean | If the value is true, the prompt is submitted to an LLM with the vector chunks as context. |
GenaiMaxDocumentChunks |
Integer | You can set the maximum number of document chunks that need to be returned in the
GenaiVectorChunks property. |
GenaiRelevancyScoreFilterLevel |
Float | When you set this parameter, it overrides the LLM relevancy score filter level which has a default value of 0.5. You can set a value between 0.0 and 1.0. |
GenaiContextDocument |
Object | The document that is used as context for the query. |