# IBM's Watson - Natural Language

![](https://1031980850-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-MRKcZBCSfHjT8BRPnSe%2F-MezxlJxgi_ML_kWLmCb%2F-Mf-4yBjgzAxRe5tP1F-%2Fimage.png?alt=media\&token=6d34829e-4285-4e55-b93a-3fdc1f9e222e)

## Input 

| Field                  | Description                                                                                                                |
| ---------------------- | -------------------------------------------------------------------------------------------------------------------------- |
| Title                  | Component Title                                                                                                            |
| Object Name Identifier | Singular name for the object (Variable)                                                                                    |
| API Key                | API Key registered in the IBM's console                                                                                    |
| Service URL            | The API's registered URL in the IBM´s console                                                                              |
| Version                | Version used on service. Pattern  **2021-03-25**                                                                           |
| Language               | The language in which the text is written. Currently both English and Portuguese are available.                            |
| Comprehension Features | The comprehension features that will be persued in the entered text: Category, concepts, entities, keywords and sentiment. |
| Text                   | Text that will be analyzed by the artificial intelligence.                                                                 |

#### Comprehension Features

* **Categories:** Categorize your content using a five-level classification hierarchy.  
* **Concepts :** Identify high level concepts that do not necessarily have a direct text reference.
* **Entities :** Find people, places, events and other entities that are mencioned in your text content. 
* **Keywords:** Search for relevant keywords in your text. 
* **Sentiment:** Analyze the sentiment of specific sentences and the overall sentiment of the document. 

```css
 "sentiment": {
    "document": {
      "score": -0.925909,
      "label": "negative"
    }
  },
```

## Return 

| Field      | Type         | Description                                                                         |
| ---------- | ------------ | ----------------------------------------------------------------------------------- |
| Result     | WatsonEntity | Component title                                                                     |
| ResultRaw  | string       | Singular object name to extract text from image (variable)                          |
| ResultJson | dynamic      | Which provider will be used for content identification (Tesseract (free) / Google). |

### WatsonEntity

| Field      | Type                  |
| ---------- | --------------------- |
| Sentiment  | **Sentiment**         |
| Keywords   | **List\<Keywords>**   |
| Entities   | **List\<Entities>**   |
| Concepts   | **List\<Concepts>**   |
| Categories | **List\<Categories>** |

### Keywords

| Field     | Type          |
| --------- | ------------- |
| Type      | string        |
| Text      | string        |
| Sentiment | **Sentiment** |
| Relevance | decimal       |
| Count     | int           |
| Emotion   | **Emotion**   |

### Sentiment

| Field | Type    |
| ----- | ------- |
| Label | string  |
| Score | decimal |

### Emotion

| Field   | Type    |
| ------- | ------- |
| Sadness | decimal |
| Joy     | decimal |
| Fear    | decimal |
| Disgust | decimal |
| Anger   | decimal |

### Entities

| Field     | Type          |
| --------- | ------------- |
| Type      | string        |
| Text      | string        |
| Sentiment | **Sentiment** |
| Relevance | decimal       |
| Count     | int           |
| Emotion   | **Emotion**   |

### Concepts

| Field     | Type    |
| --------- | ------- |
| Text      | string  |
| Relevance | decimal |

### Categories

| Field       | Text            |
| ----------- | --------------- |
| Label       | string          |
| Score       | decimal         |
| Explanation | **Explanation** |

### Explanation

| Field        | Type                    |
| ------------ | ----------------------- |
| RelevantText | **List\<RelevantText>** |

### RelevantText

| Field | Text   |
| ----- | ------ |
| Text  | string |


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.roboteasy.tech/studio-en/studio/objetos/ia/ibm-watson-linguagem-natural.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.