PHPackages                             passionweb/ai-seo-helper - PHPackages - PHPackages  [Skip to content](#main-content)[PHPackages](/)[Directory](/)[Categories](/categories)[Trending](/trending)[Leaderboard](/leaderboard)[Changelog](/changelog)[Analyze](/analyze)[Collections](/collections)[Log in](/login)[Sign up](/register)

1. [Directory](/)
2. /
3. [Utility & Helpers](/categories/utility)
4. /
5. passionweb/ai-seo-helper

ActiveTypo3-cms-extension[Utility & Helpers](/categories/utility)

passionweb/ai-seo-helper
========================

Generates SEO metadata based on content using AI. Currently several metadata for pages and articles of EXT:news can be generated using an additional button next to the corresponding input fields.

0.7.1(8mo ago)1636.9k↓15.2%6[3 issues](https://github.com/passionweb-manuel-schnabel/ai-seo-helper/issues)GPL-3.0PHPPHP ^8.0

Since Feb 17Pushed 8mo ago1 watchersCompare

[ Source](https://github.com/passionweb-manuel-schnabel/ai-seo-helper)[ Packagist](https://packagist.org/packages/passionweb/ai-seo-helper)[ Docs](https://www.passionweb.de)[ RSS](/packages/passionweb-ai-seo-helper/feed)WikiDiscussions master Synced 1mo ago

READMEChangelog (10)Dependencies (2)Versions (20)Used By (0)

TYPO3 Extension `AI SEO Helper`
===============================

[](#typo3-extension-ai-seo-helper)

Important

This extension will only receive bug fix releases in the future. Please switch to the improved version and the more feature-rich extension ["ai\_suite"](https://github.com/autodudesde/ai-suite).

Generates SEO metadata based on page content using AI. Currently, meta description, keywords, page title, Open Graph and Twitter data (titles and descriptions) of the page properties can be generated. Based on page title and meta description you can fill Open Graph title, Twitter title, Open Graph description and Twitter description too.

Furthermore, alternative title suggestions, description suggestions and keywords can be generated for articles of EXT:news.

By using an additional button next to the corresponding input fields you can generate the specific suggestions/data.

Installation
------------

[](#installation)

### Add via composer:

[](#add-via-composer)

```
composer require "passionweb/ai-seo-helper"

```

- Install the extension via composer
- Flush TYPO3 and PHP Cache
- Add your OpenAI secret key to the extension configuration before using the extension

### Add via TER:

[](#add-via-ter)

If you want to install the extension via TER you can find detailed instructions [here](https://docs.typo3.org/m/typo3/guide-installation/10.4/en-us/ExtensionInstallation/Index.html).

- Install the extension via TER
- Flush TYPO3 and PHP Cache
- Add your OpenAI secret key to the extension configuration before using the extension

### Further information

[](#further-information)

The different ways to install an extension and additional detailed information can be found [here](https://docs.typo3.org/m/typo3/reference-coreapi/main/en-us/ExtensionArchitecture/HowTo/ExtensionManagement.html).

Requirements
------------

[](#requirements)

You need an OpenAI account and API key. If you have not yet created an account or key, you can do so using the following links.

Source: [Create OpenAI account](https://platform.openai.com/signup "Create OpenAI account")

Source: [Create API key](https://platform.openai.com/account/api-keys "Create API key")

General information on data generation
--------------------------------------

[](#general-information-on-data-generation)

The extension currently supports the [GPT-3.5 models](https://platform.openai.com/docs/models/gpt-3-5) and [GPT-4 models](https://platform.openai.com/docs/models/gpt-4). No snapshots of models are supported. Please also note possible restrictions when using the "GPT-4" models (see [Possible limitations when using the GPT-4 model](#possible-limitations-when-using-the-gpt-4-model)).

Based on your individual requirements, different models can lead to different results (also in terms of quality). In addition, other parameters can be modified to further specify the OpenAI requests. You have the possibility to adjust the different models as well as the most of the supported request parameters ([detailed explanation can be found here](https://platform.openai.com/docs/api-reference/completions/create)) in the extension settings.

Generate data for page properties
---------------------------------

[](#generate-data-for-page-properties)

### Generate meta description (suggestions)

[](#generate-meta-description-suggestions)

Added an additional button next to the meta description text field. When you click this button, the (text) content of the selected page is generated, and you get meta description suggestions with the help of the AI. By default, the extension prepares the meta description suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. If you set the option `showRawMetaDescriptionSuggestions` to true within the extension configuration you can output the raw content and select your favorite meta description via copy/paste.

[![Generate meta description suggestions](./Documentation/Editor/generate-meta-description.png)](./Documentation/Editor/generate-meta-description.png)

It can happen that the AI returns texts that exceed the maximum allowed length of the meta description. To additionally check the length of the meta description, the extension ["Yoast SEO for TYPO3"](https://extensions.typo3.org/extension/yoast_seo "Yoast SEO for TYPO3") can be used, for example, or various online tools.

### Generate keywords

[](#generate-keywords)

Added an additional button next to the keywords text field. When you click this button, the (text) content of the selected page is generated and keywords that is as suitable as possible is created with the help of the AI. Currently, the page must not be deactivated in the backend. Depending on the page size, the process may take a few seconds. However, notifications are used to display appropriate information.

[![Generate keywords](./Documentation/Editor/generate-keywords.png)](./Documentation/Editor/generate-keywords.png)

### Generate page title (suggestions)

[](#generate-page-title-suggestions)

Added an additional button next to the seo title text field. When you click this button, the (text) content of the selected page is generated, and you get page title suggestions with the help of the AI. By default, the extension prepares the page title suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. If you set the option `showRawPageTitleSuggestions` to true within the extension configuration you can output the raw content and select your favorite page title via copy/paste.

[![Generate page title suggestions](./Documentation/Editor/generate-page-title-suggestions.png)](./Documentation/Editor/generate-page-title-suggestions.png)

### Generate Open Graph title (suggestions)

[](#generate-open-graph-title-suggestions)

Added an additional button next to the Open Graph title text field. When you click this button, the (text) content of the selected page is generated, and you get Open Graph title suggestions with the help of the AI. By default, the extension prepares the Open Graph title suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. If you set the option `showRawOgTitleSuggestions` to true within the extension configuration you can output the raw content and select your favorite Open Graph title via copy/paste.

### Generate Open Graph description (suggestions)

[](#generate-open-graph-description-suggestions)

Added an additional button next to the Open Graph description text field. When you click this button, the (text) content of the selected page is generated, and you get Open Graph description suggestions with the help of the AI. By default, the extension prepares the Open Graph description suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. If you set the option `showRawOgDescriptionSuggestions` to true within the extension configuration you can output the raw content and select your favorite Open Graph description via copy/paste.

### Generate Twitter title (suggestions)

[](#generate-twitter-title-suggestions)

Added an additional button next to the Twitter title text field. When you click this button, the (text) content of the selected page is generated, and you get Twitter title suggestions with the help of the AI. By default, the extension prepares the Twitter title suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. If you set the option `showRawTwitterTitleSuggestions` to true within the extension configuration you can output the raw content and select your favorite Twitter title via copy/paste.

### Generate Twitter description (suggestions)

[](#generate-twitter-description-suggestions)

Added an additional button next to the Twitter description text field. When you click this button, the (text) content of the selected page is generated, and you get Twitter description suggestions with the help of the AI. By default, the extension prepares the Twitter description suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. If you set the option `showRawTwitterDescriptionSuggestions` to true within the extension configuration you can output the raw content and select your favorite Twitter description via copy/paste.

### Use page title suggestion for Open Graph and Twitter titles

[](#use-page-title-suggestion-for-open-graph-and-twitter-titles)

Since Version 0.5.0 you have the option to copy the selected page title suggestion to the fields for Open Graph and Twitter titles (can be found within the tab "Social media"). Therefore you must enable the option `pageTitleForOgAndTwitter` in the extension settings. If you select a page title the content will be copied to the fields `og_title`and `twitter_title` too.

### Use meta description suggestion for Open Graph and Twitter descriptions

[](#use-meta-description-suggestion-for-open-graph-and-twitter-descriptions)

Since Version 0.5.0 you have the option to copy the selected meta description suggestion to the fields for Open Graph and Twitter descriptions (can be found within the tab "Social media"). Therefore you must enable the option `metaDescriptionForOgAndTwitter` in the extension settings. If you select a meta description the content will be copied to the fields `og_description`and `twitter_description` too.

Generate data for articles of EXT:news
--------------------------------------

[](#generate-data-for-articles-of-extnews)

With version 0.6.0 the compatibility to EXT:news was added. Currently, the following metadata can be generated:

### Generate meta description (suggestions)

[](#generate-meta-description-suggestions-1)

Added an additional button next to the meta description text field. When you click this button, the (text) content of the selected news article is generated, and you get meta description suggestions with the help of the AI. By default, the extension prepares the meta description suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. If you set the option `showRawNewsMetaDescriptionSuggestions` to true within the extension configuration you can output the raw content and select your favorite meta description via copy/paste.

It can happen that the AI returns texts that exceed the maximum allowed length of the meta description. To additionally check the length of the meta description, the extension ["Yoast SEO for TYPO3"](https://extensions.typo3.org/extension/yoast_seo "Yoast SEO for TYPO3") can be used, for example, or various online tools.

### Generate keywords

[](#generate-keywords-1)

Added an additional button next to the keywords text field. When you click this button, the (text) content of the selected news article is generated and keywords that is as suitable as possible is created with the help of the AI. Currently, the page must not be deactivated in the backend. Depending on the page size, the process may take a few seconds. However, notifications are used to display appropriate information.

### Generate alternative title (suggestions)

[](#generate-alternative-title-suggestions)

Added an additional button next to the alternative title text field. When you click this button, the (text) content of the selected news article is generated, and you get alternative title suggestions with the help of the AI. By default, the extension prepares the alternative title suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. If you set the option `showRawNewsAlternativeTitleSuggestions` to true within the extension configuration you can output the raw content and select your favorite page title via copy/paste.

Getting results in two different ways
-------------------------------------

[](#getting-results-in-two-different-ways)

Since version 0.3.0 you have two different options to generate the desired data. Both variants adds a ["language suffix"](#how-is-the-language-suffix-determined) to get the response in the language of the analyzed page/content.

### Analyzing the page content based on the text

[](#analyzing-the-page-content-based-on-the-text)

As already mentioned, this option is primarily limited by the length of the allowed characters per OpenAI request. Furthermore, using this method requires the use of a comparatively large number of tokens.

The following settings are necessary:

- disable the `useUrlForRequest` option in the extension settings
- check if the ISO code(s) of the language configurations is/are present in the predefined fields (if not present, custom languages can be added, see ["Add custom languages"](#add-custom-languages)).
- Definition of the corresponding prompt in English.

The entire prompt is then assembled from the prompt prefix (from the extension settings), the page url and the language suffix (based on the language used on the page). An example of the generated prompt for page title suggestions would look like this (for a German language site):

```
1. Suggest page title ideas in bullet point list for the following text (content from extension setting `openAiPromptPrefixPageTitle`)
2. in German (language suffix based on the language used on the page)
3. Here comes the page content

Complete:

Suggest page title ideas in bullet point list for the following text in German:

Here comes the page content

```

### Analyzing the page content by URL

[](#analyzing-the-page-content-by-url)

In contrast to the text-based variant, this option uses the URL of the page to analyze the desired data. If you want to use this variant, the following settings are necessary:

- enable the `useUrlForRequest` option in the extension settings
- check if the ISO code(s) of the language configurations is/are present in the predefined fields (if not present, custom languages can be added, see ["Add custom languages"](#add-custom-languages)).
- Definition of the corresponding prompt in English.

The entire prompt is then assembled from the prompt prefix (from the extension settings), the page url and the language suffix (based on the language used on the page). An example of the generated prompt for page title suggestions would look like this (for a German language site):

```
1. Suggest page title ideas in bullet point list for (content from extension setting `openAiPromptPrefixPageTitle`)
2. https://www.example.de/ (page url)
3. in German (language suffix based on the language used on the page)

Complete:

Suggest page title ideas in bullet point list for https://www.example.de/ in German

```

Requirement is that the page is publicly accessible (hidden pages fail and pages in a local environment lead to poor results).

A major advantage is that this variant saves quite a lot of OpenAI tokens (and thus costs), since only the URL is sent to OpenAI instead of the entire page content

Extension settings
------------------

[](#extension-settings)

You can adapt the following parameters to your personal needs. After the first tests, the best results were achieved with the predefined values. However, this is no guarantee that these values will also achieve the best results for you.

### API Key

[](#api-key)

#### `openAiApiKey`

[](#openaiapikey)

```
# cat=API Key; type=string; label=OpenAI Secret Key
openAiApiKey = YOUR_API_KEY

```

Enter your generated OpenAI API key.

### Basic request settings

[](#basic-request-settings)

#### `openAiModel`

[](#openaimodel)

```
# cat=basic request settings; type=string; label=OpenAI Model
openAiModel = gpt-3.5-turbo

```

The id of the model which will generate the completion. See [models overview](https://platform.openai.com/docs/models/overview "models overview") for an overview of available models.

#### `openAiTemperature`

[](#openaitemperature)

```
# cat=basic request settings; type=double+; label=OpenAI Temperature
openAiTemperature = 0.5

```

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

#### `openAiMaxTokens`

[](#openaimaxtokens)

```
# cat=basic request settings; type=int+; label=OpenAI Max-Tokens
openAiMaxTokens = 275

```

The token ([what are tokens and how to count them](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them#:~:text=Tokens%20can%20be%20thought%20of,spaces%20and%20even%20sub%2Dwords.)) count of your prompt plus max\_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).

#### `openAiTopP`

[](#openaitopp)

```
# cat=basic request settings; type=int+; label=OpenAI Top-P
openAiTopP = 1

```

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top\_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

#### `openAiFrequencyPenalty`

[](#openaifrequencypenalty)

```
# cat=basic request settings; type=double; label=OpenAI Frequency Penalty
openAiFrequencyPenalty = 0.8

```

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

#### `openAiPresencePenalty`

[](#openaipresencepenalty)

```
# cat=basic request settings; type=double; label=OpenAI Presence Penalty
openAiPresencePenalty = 0

```

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

#### `useUrlForRequest`

[](#useurlforrequest)

```
# cat=basic request settings; type=boolean; label=Use always URL for requests
useUrlForRequest = 1

```

### Meta description

[](#meta-description)

#### `openAiPromptPrefixMetaDescription`

[](#openaipromptprefixmetadescription)

```
# cat=meta description; type=string; label=Prompt-Prefix for meta description suggestions generation
openAiPromptPrefixMetaDescription = Extract five seo meta descriptions in a bullet point list, each seo meta description in one short sentence and with a maximum of 150 characters or less, for the content of

```

Enter your instruction for generating meta description suggestions. Since OpenAI calculates the length of the content with tokens (an explanation of the conversion of tokens into characters and sentences can be found [here](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them#:~:text=Tokens%20can%20be%20thought%20of,spaces%20and%20even%20sub%2Dwords.)) by default, we have to explicitly tell the AI the desired total length and the type of expected creation

#### `showRawMetaDescriptionSuggestions`

[](#showrawmetadescriptionsuggestions)

```
#cat=page title; type=boolean; label=Show raw response content of meta description suggestions
showRawMetaDescriptionSuggestions = 0

```

By default, the extension prepares the meta description suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. With this option you can output the raw content and select your favorite meta description via copy/paste.

### Keywords

[](#keywords)

#### `openAiPromptPrefixKeywords`

[](#openaipromptprefixkeywords)

```
# cat=keywords; type=string; label=Prompt-Prefix for keywords generation
openAiPromptPrefixKeywords = Extract seo keywords from this text. Return the result in a comma separated list.

```

Enter your instruction for generating keywords.

#### `replaceTextKeywords`

[](#replacetextkeywords)

```
# cat=keywords; type=string; label=Replace first part of generated keywords
replaceTextKeywords = SEO keywords:

```

The content generated by OpenAI is usually supplemented with a short introduction. Here you can define the part of the generated content that should be removed.

### Page title

[](#page-title)

#### `openAiPromptPrefixPageTitle`

[](#openaipromptprefixpagetitle)

```
#cat=page title; type=string; label=Prompt-Prefix for page title suggestions generation
openAiPromptPrefixPageTitle = Suggest page title ideas in bullet point list for this text

```

Enter your instruction for generating page title suggestions (IMPORTANT: response must be a bullet point list as the return is processed that way).

#### `showRawPageTitleSuggestions`

[](#showrawpagetitlesuggestions)

```
#cat=page title; type=boolean; label=Show raw response content of page title suggestions
showRawPageTitleSuggestions = 0

```

By default, the extension prepares the page title suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. With this option you can output the raw content and select your favorite page title via copy/paste.

### Twitter and OpenGraph

[](#twitter-and-opengraph)

#### `openAiPromptPrefixOgTitle`

[](#openaipromptprefixogtitle)

```
#cat=open graph; type=string; label=Prompt-Prefix for Open Graph title suggestions generation
openAiPromptPrefixOgTitle = Suggest Open Graph title ideas in bullet point list for this text

```

Enter your instruction for generating Open Graph title suggestions (IMPORTANT: response must be a bullet point list as the return is processed that way).

#### `showRawOgTitleSuggestions`

[](#showrawogtitlesuggestions)

```
#cat=open graph; type=boolean; label=Show raw response content of Open Graph title suggestions
showRawOgTitleSuggestions = 0

```

By default, the extension prepares the Open Graph title suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. With this option you can output the raw content and select your favorite Open Graph title via copy/paste.

#### `openAiPromptPrefixOgDescription`

[](#openaipromptprefixogdescription)

```
# cat=open graph; type=string; label=Prompt-Prefix for Open Graph description suggestions generation
openAiPromptPrefixOgDescription = Extract five Open Graph descriptions in a bullet point list, each Open Graph description in one short sentence and with a maximum of 150 characters or less, for the content of

```

Enter your instruction for generating Open Graph description suggestions. Since OpenAI calculates the length of the content with tokens (an explanation of the conversion of tokens into characters and sentences can be found [here](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them#:~:text=Tokens%20can%20be%20thought%20of,spaces%20and%20even%20sub%2Dwords.)) by default, we have to explicitly tell the AI the desired total length and the type of expected creation

#### `showRawOgDescriptionSuggestions`

[](#showrawogdescriptionsuggestions)

```
#cat=open graph; type=boolean; label=Show raw response content of Open Graph description suggestions
showRawOgDescriptionSuggestions = 0

```

By default, the extension prepares the Open Graph description suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. With this option you can output the raw content and select your favorite Open Graph description via copy/paste.

#### `openAiPromptPrefixTwitterTitle`

[](#openaipromptprefixtwittertitle)

```
#cat=twitter; type=string; label=Prompt-Prefix for Twitter title suggestions generation
openAiPromptPrefixTwitterTitle = Suggest Twitter title ideas in bullet point list for this text

```

Enter your instruction for generating Twitter title suggestions (IMPORTANT: response must be a bullet point list as the return is processed that way).

#### `showRawTwitterTitleSuggestions`

[](#showrawtwittertitlesuggestions)

```
#cat=twitter; type=boolean; label=Show raw response content of Twitter title suggestions
showRawTwitterTitleSuggestions = 0

```

By default, the extension prepares the Twitter title suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. With this option you can output the raw content and select your favorite Twitter title via copy/paste.

#### `openAiPromptPrefixTwitterDescription`

[](#openaipromptprefixtwitterdescription)

```
# cat=twitter; type=string; label=Prompt-Prefix for Twitter description suggestions generation
openAiPromptPrefixTwitterDescription = Extract five Twitter descriptions in a bullet point list, each Twitter description in one short sentence and with a maximum of 150 characters or less, for the content of

```

Enter your instruction for generating Twitter description suggestions. Since OpenAI calculates the length of the content with tokens (an explanation of the conversion of tokens into characters and sentences can be found [here](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them#:~:text=Tokens%20can%20be%20thought%20of,spaces%20and%20even%20sub%2Dwords.)) by default, we have to explicitly tell the AI the desired total length and the type of expected creation

#### `showRawTwitterDescriptionSuggestions`

[](#showrawtwitterdescriptionsuggestions)

```
#cat=twitter; type=boolean; label=Show raw response content of Twitter description suggestions
showRawTwitterDescriptionSuggestions = 0

```

By default, the extension prepares the Twitter description suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. With this option you can output the raw content and select your favorite Twitter description via copy/paste.

#### `pageTitleForOgAndTwitter`

[](#pagetitleforogandtwitter)

```
#cat=open graph & twitter; type=boolean; label=Fill Open Graph and Twitter titles
pageTitleForOgAndTwitter = 0

```

Use selected page title suggestion for Open Graph and Twitter titles

#### `metaDescriptionForOgAndTwitter`

[](#metadescriptionforogandtwitter)

```
#cat=open graph & twitter; type=boolean; label=Fill Open Graph and Twitter descriptions
metaDescriptionForOgAndTwitter = 0

```

Use selected meta description suggestion for Open Graph and Twitter descriptions

### EXT:news metadata

[](#extnews-metadata)

#### `singleNewsDisplayPage`

[](#singlenewsdisplaypage)

```
# cat=news; type=string; label=Enter the ID of one page that is used as a detail view for news articles of the news extension
singleNewsDisplayPage =

```

Enter the ID of one page that is used as a detail view for news articles of EXT:news. This page will be used to generate the `BackendPreviewUrl`.

#### `openAiPromptPrefixNewsMetaDescription`

[](#openaipromptprefixnewsmetadescription)

```
# cat=news; type=string; label=Prompt-Prefix for meta description suggestions generation of news article
openAiPromptPrefixNewsMetaDescription = Extract five seo meta descriptions in a bullet point list, each seo meta description in one short sentence and with a maximum of 150 characters or less, for the content of

```

Enter your instruction for generating meta description suggestions. Since OpenAI calculates the length of the content with tokens (an explanation of the conversion of tokens into characters and sentences can be found [here](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them#:~:text=Tokens%20can%20be%20thought%20of,spaces%20and%20even%20sub%2Dwords.)) by default, we have to explicitly tell the AI the desired total length and the type of expected creation

#### `showRawNewsMetaDescriptionSuggestions`

[](#showrawnewsmetadescriptionsuggestions)

```
# cat=news; type=boolean; label=Show raw response content for meta description suggestions of news article
showRawNewsMetaDescriptionSuggestions = 0

```

By default, the extension prepares the meta description suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. With this option you can output the raw content and select your favorite meta description via copy/paste.

#### `openAiPromptPrefixNewsKeywords`

[](#openaipromptprefixnewskeywords)

```
# cat=news; type=string; label=Prompt-Prefix for keywords generation of news article
openAiPromptPrefixKeywords = Extract seo keywords from this news article. Return the result in a comma separated list.

```

Enter your instruction for generating keywords.

#### `replaceTextNewsKeywords`

[](#replacetextnewskeywords)

```
# cat=news; type=string; label=Replace first part of generated keywords of news article
replaceTextNewsKeywords = SEO keywords:

```

The content generated by OpenAI is usually supplemented with a short introduction. Here you can define the part of the generated content that should be removed.

#### `openAiPromptPrefixNewsAlternativeTitle`

[](#openaipromptprefixnewsalternativetitle)

```
# cat=news; type=string; label=Prompt-Prefix for alternative title suggestions generation
openAiPromptPrefixNewsAlternativeTitle = Suggest page title ideas in bullet point list for this text

```

Enter your instruction for generating alternative title suggestions (IMPORTANT: response must be a bullet point list as the return is processed that way).

#### `showRawNewsAlternativeTitleSuggestions`

[](#showrawnewsalternativetitlesuggestions)

```
# cat=news; type=boolean; label=Show raw response content of alternative title suggestions of news article
showRawNewsAlternativeTitleSuggestions = 0

```

By default, the extension prepares the alternative title suggestions in such a way that they can be selected via radio button. If you change the prompt prefix and no bullet point list is returned as a result, display problems can occur here. With this option you can output the raw content and select your favorite alternative title via copy/paste.

With this option you can use the corresponding URL of the page for all analyses. As a result, you have to use fewer tokens to carry out your corresponding analyses. IMPORTANT: The page must be publicly accessible (hidden pages fail and pages in a local environment lead to poor results)

How is the language suffix determined?
--------------------------------------

[](#how-is-the-language-suffix-determined)

The root page of the page to be analyzed is determined. Based on this, the ISO code used (the `iso-639-1` field of the corresponding language from `config.yaml) is determined. The corresponding language has already been created for the conventional ISO codes. The following ISO codes and languages are already stored:

- 'en' => 'English',
- 'us' => 'English',
- 'gb' => 'English',
- 'de' => 'German',
- 'at' => 'German',
- 'ch' => 'German',
- 'fr' => 'French',
- 'nl' => 'Dutch',
- 'be' => 'Belgian',
- 'es' => 'Spanish',
- 'pl' => 'Polish',
- 'cz' => 'Czech',
- 'sk' => 'Slovak',
- 'si' => 'Slovenian',
- 'ro' => 'Romanian',
- 'ua' => 'Ukrainian',
- 'it' => 'Italian',
- 'se' => 'Swedish',
- 'no' => 'Norwegian',
- 'fi' => 'Finnish',
- 'dk' => 'Danish',
- 'jp' => 'Japanese',
- 'cn' => 'Chinese'

Add custom languages
--------------------

[](#add-custom-languages)

If the desired ISO code and language is not contained, it can be created using a data record "Custom language". The user-defined languages are added automatically (already existing languages are replaced by user-defined languages).

Extend logic to other fields
----------------------------

[](#extend-logic-to-other-fields)

Of course, the functionality can also be transferred to other page properties that are not currently taken into account. The following procedure applies to all text input and textarea fields. Additional adjustments must be made for other fields (e.g. image fields) or fields within content elements.

Do not make the changes directly in the extension! Please create your own extension for individual adjustments or add the changes to your sitepackage extension and add/edit the following files:

The following placeholders were used:

- FIELD\_IDENTIFIER: identifier of the field (e.g. twitter\_title),
- FIELD\_IDENTIFIER\_UPPER\_CAMELCASE: identifier of the field in upper camel case (e.g. TwitterTitle),
- NODE\_IDENTIFIER: identifier of the field type of NodeFactory (e.g. aiSeoTwitterTitle)
- TIMESTAMP: current timestamp as a unique identifier
- \\Vendor\\Package: replace this with your own vendor and package name

### Add TCA configuration to Configuration/TCA/Overrides/pages.php

[](#add-tca-configuration-to-configurationtcaoverridespagesphp)

```
$GLOBALS['TCA']['pages']['columns']['FIELD_IDENTIFIER']['config'] = array_merge_recursive(
    $GLOBALS['TCA']['pages']['columns']['FIELD_IDENTIFIER']['config'],
    [
        'fieldControl' => [
            'importControl' => [
                'renderType' => 'NODE_IDENTIFIER'
            ]
        ]
    ]
);

```

### Add FormEngine fieldControl (e.g. to Classes/FormEngine/FieldControl/AiSeoFIELD\_IDENTIFIER\_UPPER\_CAMELCASE.php)

[](#add-formengine-fieldcontrol-eg-to-classesformenginefieldcontrolaiseofield_identifier_upper_camelcasephp)

```
class AiSeoFIELD_IDENTIFIER_UPPER_CAMELCASE extends AbstractNode
{
    public function render(): array
    {
        $resultArray = [
            'iconIdentifier' => 'actions-document-synchronize',
            'title' => 'Your custom title',
            'linkAttributes' => [
                'id' => 'FIELD_IDENTIFIER_generation',
                'class' => 'ai-seo-helper-suggestions-generation-btn',
                'data-page-id' => $this->data['databaseRow']['uid'],
                'data-field-name' => 'FIELD_IDENTIFIER'
            ]
        ];

        $javaScriptModuleService = GeneralUtility::makeInstance(JavaScriptModuleService::class);

        return array_merge($resultArray, $javaScriptModuleService->addModules());
    }
}

```

### Add registration in NodeFactory to ext\_localconf.php

[](#add-registration-in-nodefactory-to-ext_localconfphp)

```
$GLOBALS['TYPO3_CONF_VARS']['SYS']['formEngine']['nodeRegistry'][TIMESTAMP] = [
    'nodeName' => 'NODE_IDENTIFIER',
    'priority' => 30,
    'class' => \Vendor\Package\FormEngine\FieldControl\AiSeoFIELD_IDENTIFIER_UPPER_CAMELCASE::class
];

```

### Add further configuration settings to ext\_conf\_template.txt

[](#add-further-configuration-settings-to-ext_conf_templatetxt)

```
#cat=custom category; type=string; label=Your custom title
openAiPromptPrefixFIELD_IDENTIFIER_UPPER_CAMELCASE = Your custom prompt

```

### Add function to controller (e.g. to Classes/Controller/Ajax/AiController.php)

[](#add-function-to-controller-eg-to-classescontrollerajaxaicontrollerphp)

```
public function generateFIELD_IDENTIFIER_UPPER_CAMELCASEAction(ServerRequestInterface $request): ResponseInterface
{
    return $this->generateSuggestions($request, 'FIELD_IDENTIFIER_UPPER_CAMELCASE');
}

```

The function generateSuggestions() can be used from `\Passionweb\AiSeoHelper\Service\ContentService`

### Add ajax route to Configuration/Backend/AjaxRoutes.php

[](#add-ajax-route-to-configurationbackendajaxroutesphp)

```
return [
    'FIELD_IDENTIFIER_generation' => [
        'path' => 'CUSTOM_PATH',
        'target' => \Vendor\Package\Controller\Ajax\AiController::class . '::generateFIELD_IDENTIFIER_UPPER_CAMELCASEAction'
    ],
];

```

Once all adjustments have been made, flush the TYPO3 and PHP cache and test if everything works as desired.

Troubleshooting and logging
---------------------------

[](#troubleshooting-and-logging)

If something does not work as expected take a look at the log file first. Every problem is logged to the TYPO3 log (normally found in `var/log/typo3_*.log`)

Notices to keep in mind
-----------------------

[](#notices-to-keep-in-mind)

Just like this extension, OpenAI is still in development mode and not fully mature. For this reason, we urgently advise you to check all generated texts for correctness before saving them and to make any necessary adjustments!

### Restrictions on very large texts

[](#restrictions-on-very-large-texts)

The OpenAI API (currently) limits the maximum number of tokens per request depending on the model used (currently the maximum possible tokens are 32,768 by using the `gpt-4-32k` model). You can find a detailed overview of models and the maximum number of tokens here:

Based on the current status of the extension, it is unfortunately not yet possible to analyze larger texts.

### Possible limitations when using the GPT-4 model

[](#possible-limitations-when-using-the-gpt-4-model)

At the time of version 0.6.0 release, only people with a $1 or more successful payment on their account have access to the GPT-4 model. According to OpenAI, that should change soon.

If you try to use the GPT-4 model without access you currently get a 404 error message which is a bit confusing.

Achieving more together or Feedback, Feedback, Feedback
-------------------------------------------------------

[](#achieving-more-together-or-feedback-feedback-feedback)

I'm grateful for any feedback! Be it suggestions for improvement, extension requests or just a (constructive) feedback on how good or crappy the extension is.

Feel free to send me your feedback to [service@passionweb.de](mailto:service@passionweb.de "Send Feedback") or [contact me on Slack](https://typo3.slack.com/team/U02FG49J4TG "Contact me on Slack")

###  Health Score

43

—

FairBetter than 91% of packages

Maintenance56

Moderate activity, may be stable

Popularity39

Limited adoption so far

Community15

Small or concentrated contributor base

Maturity49

Maturing project, gaining track record

 Bus Factor1

Top contributor holds 74.8% of commits — single point of failure

How is this calculated?**Maintenance (25%)** — Last commit recency, latest release date, and issue-to-star ratio. Uses a 2-year decay window.

**Popularity (30%)** — Total and monthly downloads, GitHub stars, and forks. Logarithmic scaling prevents top-heavy scores.

**Community (15%)** — Contributors, dependents, forks, watchers, and maintainers. Measures real ecosystem engagement.

**Maturity (30%)** — Project age, version count, PHP version support, and release stability.

###  Release Activity

Cadence

Every ~52 days

Recently: every ~195 days

Total

19

Last Release

251d ago

### Community

Maintainers

![](https://www.gravatar.com/avatar/923e299d6dd525718884ab180dffde75ec28a9615c6f75479f1a037ec79083bf?d=identicon)[passionweb-manuel-schnabel](/maintainers/passionweb-manuel-schnabel)

---

Top Contributors

[![ManuS3009](https://avatars.githubusercontent.com/u/43109656?v=4)](https://github.com/ManuS3009 "ManuS3009 (95 commits)")[![passionweb-manuel-schnabel](https://avatars.githubusercontent.com/u/120183093?v=4)](https://github.com/passionweb-manuel-schnabel "passionweb-manuel-schnabel (27 commits)")[![SZChimp](https://avatars.githubusercontent.com/u/47443911?v=4)](https://github.com/SZChimp "SZChimp (3 commits)")[![chludwig](https://avatars.githubusercontent.com/u/5552548?v=4)](https://github.com/chludwig "chludwig (1 commits)")[![sebastianstein](https://avatars.githubusercontent.com/u/25500519?v=4)](https://github.com/sebastianstein "sebastianstein (1 commits)")

### Embed Badge

![Health badge](/badges/passionweb-ai-seo-helper/health.svg)

```
[![Health](https://phpackages.com/badges/passionweb-ai-seo-helper/health.svg)](https://phpackages.com/packages/passionweb-ai-seo-helper)
```

###  Alternatives

[fluidtypo3/flux

The flux package from FluidTYPO3

152982.2k20](/packages/fluidtypo3-flux)[friendsoftypo3/content-blocks

TYPO3 CMS Content Blocks - Content Types API | Define reusable components via YAML

96374.6k23](/packages/friendsoftypo3-content-blocks)[wazum/sluggi

TYPO3 extension for URL slug management with inline editing, auto-sync, locking, access control, and redirects

39488.5k](/packages/wazum-sluggi)[eliashaeussler/typo3-form-consent

Extension for TYPO3 CMS that adds double opt-in functionality to EXT:form

1481.0k](/packages/eliashaeussler-typo3-form-consent)[b13/assetcollector

Add CSS and SVG files and strings as inline style tag/inline svg to the html code.

10118.4k](/packages/b13-assetcollector)[mautic/mautic-typo3

Add-on TYPO3 extension that enhances the "EXT:marketing\_automation" TYPO3 extension by connecting it to the Mautic Marketing Automation platform: Determine "Persona" from Mautic segments. Also provides additional services e.g. language synchronisation between Mautic and TYPO3.

236.3k](/packages/mautic-mautic-typo3)

PHPackages © 2026

[Directory](/)[Categories](/categories)[Trending](/trending)[Changelog](/changelog)[Analyze](/analyze)