Page History
| Excerpt | ||
|---|---|---|
Connects directly to the Python Bridge, to send text or sections of the interpretation graph to be process processed by ML algorithms in Python. This recognizer is used when there is a need to classify an entire document for example. That is the difference when compared to the Python Model Recognizer which will be processing or running for each token or text block. Processing an entire document has its benefits, it may be the best way to classify a document as a whole. By running only once per document we get a boost in performance when compared to run the recognizer for each individual token or text block. The other benefit is that we could normalize the text before sending it to the python model and also specify dependent tags so it runs in the order we need in the processing pipeline.
|
Parameter summary Flag to trigger this recognizer. default EOF name Trigger Flag Parameter summary Desired protocol to connect to Python Bridge (HTTP / HTTPS) default HTTP name Service Protocol Parameter summary URL for Name of the host where Python Bridge is running. default localhost name Service Hostname required true Parameter summary Port where Python Bridge is running. default 5000 name Service Port required true Parameter summary Whether or not to use authentication for the python bridge default false name Authentication type boolean required true Parameter summary Model name registered in the python bridge. name Select Model required true Parameter summary Model version registered in the python wrapper to query. name Select Version Parameter summary Model method to call for the model. name Select Model Method required true
Configuration
Parameter summary Maximum number of connection retries Whether to send the Python Bridge.original text to Python or not default false name Send Original Text type boolean Parameter summary Splits the text in blocks according to the split pattern and sends the text block list default 3false name Number of retries required true
Configuration
Send As Text Blocks type boolean Parameter summary Sends the content as a collection of tokens. This setting interacts with the previous ones, the original text can be sent as a token list and both can be grouped in lists of tokens corresponding to text blocks default false name Send as Token Collection type boolean Parameter summary Includes text from vertex as new tokens. default false name Include Vertex Text as Token type boolean Parameter summary Tags (flagged as SEMANTIC_TAG) are normalized. default false name Normalize Tags type boolean Parameter summary List of tags to be dependent for the model. name Dependency tags type string array
General Settings
| Include Page | ||||
|---|---|---|---|---|
|
Overview
Content Tools