docs(turing): clean up administration guide - remove NLP, NER, Chatbot, Blazon

Alexandre Oliveira · claude · Alexandre Oliveira · commit 8e2637fb9b0e · 2026-03-20T07:59:12.000-03:00
- Remove old architecture diagram (superseded by architecture-overview.md)
- Remove NLP section (OpenNLP, OTCA, CoreNLP, SpaCy, Polyglot, GCP NLP) — NLP removed from Turing ES
- Remove Named Entity Recognition (NER) section
- Remove Chatbot section (Agent, Intent, Actions, Entity, Training, History)
- Remove OpenText Blazon Integration section
- Update intro paragraph to reflect current feature set (Semantic Navigation + GenAI)
- Add reference to architecture-overview.md
- Remove NLP Vendor and NLP Instance from SN Site settings tables
- Remove NLP/NER columns from Fields table
- Update Connectors section to reference Viglet Dumont DEP

Co-Authored-By: Claude Sonnet 4.6 &lt;noreply@anthropic.com&gt;
diff --git a/docs-turing/administration-guide.md b/docs-turing/administration-guide.md
@@ -6,105 +6,9 @@ description: Viglet Turing ES Administration Guide
 
 # Viglet Turing ES: Administration Guide
 
-Viglet Turing ES ([https://viglet.com/turing](https://viglet.com/turing)) is an open source solution ([https://github.com/openviglet](https://github.com/openviglet)), which has Semantic Navigation and Chatbot as its main features. You can choose from several NLPs to enrich the data. All content is indexed in Solr as search engine.
+Viglet Turing ES ([https://viglet.com/turing](https://viglet.com/turing)) is an open source enterprise search platform ([https://github.com/openviglet](https://github.com/openviglet)) with Semantic Navigation and Generative AI as its main features. All content is indexed in Apache Solr as the primary search engine.
 
-## Architecture
-
-![Turing ES Architecture](/img/turing-diagram.png)
-
-## NLP
-
-Turing support the following providers:
-
-### OpenNLP
-
-Apache OpenNLP is a machine learning based toolkit for the processing of natural language text.
-
-Website: [https://opennlp.apache.org/](https://opennlp.apache.org/)
-
-| Attribute | Description |
-|-----------|-------------|
-| Title | OpenNLP Title |
-| Description | Description of OpenNLP |
-| Vendor | Select OpenNLP |
-| Endpoint URL | This attribute is not used |
-| Key | This attribute is not used |
-| Enabled | If the OpenNLP is enabled |
-
-### OpenText Content Analytics
-
-It transforms data into insights for better decision-making and information management while freeing up resources and time.
-
-Website: [https://www.opentext.com/](https://www.opentext.com/)
-
-| Attribute | Description |
-|-----------|-------------|
-| Title | OTCA Title |
-| Description | Description of OTCA |
-| Vendor | Select OTCA |
-| Endpoint URL | Service URL, for example: `http://localhost:40000` |
-| Key | This attribute is not used |
-| Enabled | If the OTCA is enabled |
-
-### CoreNLP
-
-CoreNLP is your one stop shop for natural language processing in Java! CoreNLP enables users to derive linguistic annotations for text, including token and sentence boundaries, parts of speech, named entities, numeric and time values, dependency and constituency parses, coreference, sentiment, quote attributions, and relations. CoreNLP currently supports 6 languages: Arabic, Chinese, English, French, German, and Spanish.
-
-Website: [https://stanfordnlp.github.io/CoreNLP/](https://stanfordnlp.github.io/CoreNLP/)
-
-| Attribute | Description |
-|-----------|-------------|
-| Title | CoreNLP Title |
-| Description | Description of CoreNLP |
-| Vendor | Select CoreNLP |
-| Endpoint URL | Service URL, for example: `http://localhost:9001` |
-| Key | This attribute is not used |
-| Enabled | If the CoreNLP is enabled |
-
-### SpaCy
-
-It is a free open-source library for Natural Language Processing in Python. It features NER, POS tagging, dependency parsing, word vectors and more.
-
-Website: [https://spacy.io](https://spacy.io)
-
-| Attribute | Description |
-|-----------|-------------|
-| Title | SpaCy Title |
-| Description | Description of SpaCy |
-| Vendor | Select SpaCy |
-| Endpoint URL | Service URL, for example: `http://localhost:2800` |
-| Key | This attribute is not used |
-| Enabled | If the SpaCy is enabled |
-
-### Polyglot NLP
-
-Polyglot is a natural language pipeline that supports massive multilingual applications.
-
-Website: [https://polyglot.readthedocs.io](https://polyglot.readthedocs.io)
-
-| Attribute | Description |
-|-----------|-------------|
-| Title | Polyglot Title |
-| Description | Description of Polyglot |
-| Vendor | Select Polyglot |
-| Endpoint URL | Service URL, for example: `http://localhost:2810` |
-| Key | This attribute is not used |
-| Enabled | If the Polyglot is enabled |
-
-### Google Cloud Platform NLP
-
-Analyze text with ES using pre-trained API or custom AutoML machine learning models to extract relevant entities, understand sentiment, and more.
-
-Website: [https://cloud.google.com/natural-language](https://cloud.google.com/natural-language)
-
-| Attribute | Description |
-|-----------|-------------|
-| Title | GCP NLP Title |
-| Description | Description of GCP NLP |
-| Vendor | Select Google Cloud Platform NLP |
-| Endpoint URL | Service URL, for example: `https://language.googleapis.com/v1/documents:analyzeEntities` |
-| Key | Key of Google Cloud Platform NLP |
-| Enabled | If the GCP NLP is enabled |
+For an overview of the system architecture and component interactions, see [Architecture Overview](./architecture-overview.md).
 
 ## Documents and OCR
 
@@ -114,46 +18,7 @@ It can read PDFs and Documents and convert to plain text and also it uses OCR to
 
 ### Connectors
 
-Semantic Navigation uses Connectors to index the content from many sources.
-
-#### Apache Nutch
-
-Plugin for Apache Nutch to index content using crawler.
-
-Learn more at [Connectors](./connectors#apache-nutch)
-
-#### Database
-
-Command line that uses the same concept as sqoop ([https://sqoop.apache.org/](https://sqoop.apache.org/)), to create complex queries and map attributes to index based on the result.
-
-Learn more at [Connectors](./connectors#database)
-
-#### File System
-
-Command line to index files, extracting text from files such as Word, Excel, PDF, including images, through OCR.
-
-Learn more at [Connectors](./connectors#file-system)
-
-#### OpenText WEM Listener
-
-OpenText WEM Listener to publish content to Viglet Turing.
-
-#### Wordpress
-
-Wordpress plugin that allows you to index posts.
-
-Learn more at [Connectors](./connectors#wordpress)
-
-### Named Entity Recognition (NER)
-
-With NLP it is possible to detect entities such as:
-
-- People
-- Places
-- Organizations
-- Money
-- Time
-- Percentage
+Content is delivered to Turing ES by **Viglet Dumont DEP**, a separate application that manages connectors independently. Dumont DEP sends documents to Turing ES via the REST API. Available connectors include WebCrawler (Apache Nutch), Database, FileSystem, AEM/WEM, and WordPress. Refer to the [Dumont DEP documentation](/dumont) for connector configuration.
 
 ### Facets
 
@@ -167,41 +32,9 @@ Through attributes defined in the contents, it is possible to use them to restri
 
 Java API ([https://github.com/openviglet/turing-java-sdk](https://github.com/openviglet/turing-java-sdk)) facilitates the use and access to Viglet Turing ES, without the need for consumer search content with complex queries.
 
-## Chatbot
-
-Communicate with your client and elaborate complex intents, obtain reports and progressively evolve your interaction.
-
-### Agent
-
-Handles conversations with your end users. It is a natural language processing module that understands the nuances of human language.
-
-### Intent
-
-An intent categorizes an end user's intention for taking a conversation shift. For each agent, you define several intents, where your combined intents can handle a complete conversation.
-
-### Actions
-
-The field of action is a simple field of convenience that helps to execute logic in the service.
-
-### Entity
-
-Each intent parameter has a type, called an entity type, that dictates exactly how the data in an end user expression is extracted.
-
-### Training
-
-Defines and corrects intents.
-
-### History
-
-Shows the conversation history and reports.
-
-## OpenText Blazon Integration
-
-Turing ES detects Entities of OpenText Blazon Documents using OCR and NLP, generating Blazon XML to show the entities into document.
-
 ## Turing ES Console
 
-Turing ES has many components: Search Engine, NLP, Converse (Chatbot), Semantic Navigation.
+Turing ES has many components: Search Engine, Semantic Navigation, and Generative AI.
 
 ### Login
 
@@ -243,15 +76,13 @@ The Settings of Semantic Navigation Site contains the following attributes:
 | Name | Name of Semantic Navigation Site |
 | Description | Description of Semantic Navigation Site |
 | Search Engine | Select the Search Engine that was created in Search Engine Section |
-| NLP Vendor | NLP Vendor for this site |
 | Thesaurus | If will use Thesaurus |
 
 ##### Multi Languages Tab
 
 | Attribute | Description |
 |-----------|-------------|
 | Language | Language for Semantic Navigation Site |
-| NLP Instance | NLP Instance to detect entities during indexing |
 | Core | Solr Core Name to store and to search indexed content |
 
 ##### Behavior Tab
@@ -291,13 +122,11 @@ Fields Tab contains a table with the following columns:
 
 | Column Name | Description |
 |-------------|-------------|
-| Type | Type of Field: NER (Named Entity Recognition) or Search Engine (Solr) |
 | Field | Name of Field |
 | Enabled | If the field is enabled |
 | MLT | If this field will be used in MLT |
 | Facets | To use this field like a facet (filter) |
 | Highlighting | If this field will show highlighted lines |
-| NLP | If this field will be processed by NLP to detect Entities |
 
 When clicking a Field, a details page appears with:
 
@@ -314,7 +143,6 @@ When clicking a Field, a details page appears with:
 | Enabled | If the field is enabled |
 | Required | If the field is required |
 | Default Value | Default value if content is indexed without this field |
-| NLP | If this field will be processed by NLP |
 
 ##### Spotlight Details Tab
 
