{ "componentChunkName": "component---src-templates-doc-page-js", "path": "/docs/en/NLU_core/project_migration/", "result": {"data":{"site":{"siteMetadata":{"title":"Gatsby-doc-engine"}},"markdownRemark":{"id":"1894f298-1b98-54ea-a937-b53147ad52c7","excerpt":"Migrating projects to CAILA?> Projects that were created based on patterns or phrase examples can be migrated to the CAILA NLU kernel. All the CAILA features…","html":"

Migrating projects to CAILA

\n
\n

Projects that were created based on patterns or phrase examples can be migrated to the CAILA NLU kernel.

\n

All the CAILA features will be available for the project: intent recognition, system and user-defined entities, slot markup and filling, CAILA API, etc.

\n

We will cover the process of migrating projects to CAILA in this article:

\n
    \n
  1. Editing the project configuration file.
    2. \n
  2. Migrating NLU settings.
    3. \n
  3. Configuring activation rules.
    4. \n
  4. Testing and updating the script.
    5. \n
\n
\n

Configuration file

\n

Specify the chatbot.yaml parameters in the configuration file:

\n
botEngine: v2\nlanguage: ru\n \nsts:\n    noMatchThreshold: 0.2\ncaila:\n    noMatchThreshold: 0.2
\n\n

Please note that we also set the noMatchThreshold value for the STS classifier. This is required for the project’s backward compatibility.

\n
\n

Migrating NLU settings

\n

Most NLU settings in chatbot.yaml become inactive when migrated to CAILA. Some of the settings can be defined when you configure the project in the NLU settings section.

\n

Let us have a look at the changes in a sample project with an STS classifier:

\n
nlp:\n  morphology: myStem\n  tokenizer: myStem\n \n  vocabulary: common-vocabulary.json\n  lengthLimit:\n    enabled: true\n    symbols: 400\n    words: 100000\n  timeLimit:\n    enabled: true\n    timeout: 10000\n  spellcheck:\n    enabled: true\n    dictionary: dict.txt\n    frequency: frequency.txt\n    minWordLengthForEditDistance: 3\n    maxWordEditDistance: 0\n  speller:\n    dictionary: speller.dict\n \nclassifier:\n  enable: true\n  engine: sts\n  noMatchThreshold: 0.2\n  parameters:\n    algorithm: aligner2
\n\n
\n
Spellchecker module
\n

The built-in spellchecker module can be used to correct spelling errors in client requests. If can be used in combination with a user-defined dictionary. This way, the project dictionary will be used to correct the words from the domain scope and the global module will be used for other words.

\n

If you used a .dict dictionary before, you can migrate it to your project using the CAILA API Direct.

\n
\n
Tokenization and lemmatization
\n

The udpipe tokenizer is used for projects in Russian by default. Tests have shown this is the best tokenization and lemmatization solution.

\n

If your project was created using patterns or an STS classifier, we recommend that you use the morphsrus or mystem tokenizer.

\n
\n
NLU advanced configuration parameters
\n

Switch to project editing. Specify advanced configuration parameters here: NLU language, classifier algorithm, timezone, NLU settings.

\n

Learn more about NLU settings

\n
\n

Configuring activation rules

\n

You can use patterns, phrase examples from an STS classifier and the CAILA classifier in combination to detect client intent. Specify the state triggering mechanism for the combined use of intents, patterns and example groups in the bot script.

\n

Learn more about the activation rule mechanism

\n
\n
Example dictionary
\n

If you used an STS classifier in your project, you can migrate your example dictionary to the updated project.

\n

Open the Intents page. Click Import at the top of the intents tree > upload the .json file.

\n
\n
CatchAll
\n

Note that if the NLU service is used in combination with patterns and classifier phrase examples, the following CatchAll is not used:

\n
    state: CatchAll\n        q!: *\n        a: I did not get it
\n

Use event: noMatch for user requests not processed by your script:

\n
    state: CatchAll\n        event: noMatch\n        a: You said: {{ $request.query }}\n
\n
\n

Testing and updating the script

\n

Use the test widget built in the script editor to debug your script.

\n

We recommend using the intent activation rule, system and custom entities, slot filling and other features of the CAILA NLU kernel to further update your script.

","frontmatter":{"title":"","description":null},"headings":[{"value":"Migrating projects to CAILA"}]}},"pageContext":{"slug":"/docs/en/NLU_core/project_migration/","previous":{"fields":{"slug":"/docs/en/NLU_core/rule_activation/"},"frontmatter":{"title":"","description":null}},"next":{"fields":{"slug":"/docs/en/NLU_core/nlu_core/"},"frontmatter":{"title":"","description":null}}}}, "staticQueryHashes": ["1209419333"]}