{ "componentChunkName": "component---src-templates-doc-page-js", "path": "/docs/en/classificator/connection_classificator/", "result": {"data":{"site":{"siteMetadata":{"title":"Gatsby-doc-engine"}},"markdownRemark":{"id":"7f7499dd-a722-53b5-8ed2-cacea2c5398a","excerpt":"!> Please note that the use of the classifier by examples has been deprecated since version . Learn more about migrating projects to CAILA. Do the following to…","html":"

Connecting the classifier to the bot Deprecated

\n
\n

Please note that the use of the classifier by examples has been deprecated since version 1.10.0. Learn more about migrating projects to CAILA.

\n

Do the following to connect the classifier to the bot:

\n
\n
    \n
  1. Specify parameters for the platform’s nlp functions in the configuration file of the chatbot.yaml bot:
    2. \n
\n
morphology
\n

Can be used to select the library for morphological analysis of words. Is used for pattern processing in ~, $lemma, $morph, and in the $nlp.parseMorph function.

\n

Specify one of the libraries:

\n\n
\n
tokenizer
\n

You can use the tokenizer to specify rules to be used to split the text into words.

\n

Supported tokenizer types

\n\n
\n
vocabulary
\n

Word weight dictionary for pattern ranking. Default: common-vocabulary.json.

\n
\n
lengthLimit, timeLimit
\n

Can be used to modify the limits on the incoming message size and the nlp module processing time.

\n

Default parameters:

\n
nlp:\n  lengthLimit:\n    enabled: true\n    symbols: 400\n    words: 100000\n  timeLimit:\n    enabled: true\n    timeout: 10000
\n

For lengthLimit:

\n\n

Please note when you set the limit that the words counter treats the !,.:;?\"'()*/[\\]{|} symbols as words.

\n

For timeLimit:

\n\n

Example of an nlp module:

\n
nlp:                                    // platform’s nlp function parameters\n  morphology: myStem                    // library for morphological analysis of words\n  tokenizer: myStem                     // tokenizer, specifies rules to be used to split the text into words\n  vocabulary: common-vocabulary.json    // word weight dictionary for pattern ranking\n  lengthLimit:\n    enabled: true\n    symbols: 400                        // limit on the number of symbols in an incoming message\n    words: 100000                       // limit on the number of words in an incoming message\n  timeLimit:\n    enabled: true\n    timeout: 10000                      // maximum request processing time (in milliseconds) for the nlp module
\n
\n
    \n
  1. Next, specify classification parameters:
    2. \n
\n
engine
\n

Classifier type (sts by default).

\n
\n
noMatchThreshold
\n

The lower similarity threshold under which phrases are to be considered different. It was determined empirically in the course of classifier development that the optimum value of this parameter is 0.2.

\n
\n
parameters: algorithm
\n

The type of the classification algorithm used. match-aligner is used, which is the primary type of an sts classifier. You can also use aligner and aligner2, which is an alternative implementation of the classification algorithm.

\n
\n
    \n
  1. Next, configure the classifier algorithm. All parameters are set to their default values. You only need to specify the weight dictionary which is identical to the dictionary specified in the nlp block. Default: common-vocabulary.json.
    2. \n
\n
\n

Here is an example of a chatbot.yaml configuration file with a classifier connected to it:

\n
name: demo\n\nentryPoint:\n  - main.sc\n\ntests:\n  exclude:\n    - tests.xml\n\nmessages:\n    onError: \n        defaultMessage: Oops, something has gone wrong. \n        locales: \n            ru: Oops, something has gone wrong.\n\nnlp:                                    // platform’s nlp function parameters\n  morphology: myStem                    // library for morphological analysis of words\n  tokenizer: myStem                     // tokenizer, specifies rules to be used to split the text into words\n  vocabulary: common-vocabulary.json    // word weight dictionary for pattern ranking\n  lengthLimit:\n    enabled: true\n    symbols: 400                        // limit on the number of symbols in an incoming message\n    words: 100000                       // limit on the number of words in an incoming message\n  timeLimit:\n    enabled: true\n    timeout: 10000                      // maximum request processing time (in milliseconds) for the nlp module\n\nclassifier:                             // classifier parameters\n  enable: true\n  engine: sts                           // classifier type\n  noMatchThreshold: 0.2\n  parameters:\n    algorithm: aligner2                 // classification algorithm\n\naligner:\n  vocabulary: common-vocabulary.json\n\nexampleGroups:\n    - src/dictionaries/examples.json    // is specified when a group of examples is used
","frontmatter":{"title":"","description":null},"headings":[{"value":"Connecting the classifier to the bot"}]}},"pageContext":{"slug":"/docs/en/classificator/connection_classificator/","previous":{"fields":{"slug":"/docs/en/classificator/e!/"},"frontmatter":{"title":"","description":null}},"next":{"fields":{"slug":"/docs/en/classificator/classificator_platform/"},"frontmatter":{"title":"","description":null}}}}, "staticQueryHashes": ["1209419333"]}