Get started with the TextCortex Enterprise API — the hemingwai

In order to access the API, you need an authentication key. You need to send this key whenever you are sending a request to our servers. After the signup, you can find your token under API menu.

‍

To get your API key and free trial credits, signup here: https://app.textcortex.com/user/signup

The authentication key looks like this:

API KEY: "gAAAAABgu6ycSzxAWqIeoR3y1yZ5EDrPkCEU6c6-0UNoOTf5CvwhSGOxln1g66BuOjckRuetjZhKYPKgUxWk_gsEhxbzS-yveg=="

Here is the full documentation of the TextCortex Hemingwai API can be found here.

There are different kinds of texts that you can generate using TextCortex AI. No matter if on our frontend products or as API the functionalities are the same.

Here is a list of categories you can use:

Auto Complete: Expands, continues and completes the instructed prompt

Blog Body: Generates blog articles on an instructed blog title and keywords.

Ads: Generates ads based on the product that you are selling. This model is instructed with a product and a target segment for generating texts.

Instagram Caption: Generates Instagram captions to promote a product from a perspective of a user.

Email Body: Generates email bodies. This model takes an email subject and a target segment for generating the main body text.

Email Subject: Generates email subjects. This model takes the keywords as an input and then generates an email subject.

Paraphrase: Paraphrases an instructed sentence and returns multiple variations of it

‍
You can find the complete documentation of TextCortex Hemingwai API under postman here.

Generating text content is as easy as making a POST request in your terminal to the Enterprise Text Generation API to this URL:

https://api.textcortex.com/hemingwai/generate_text_v3

In each request, you need to send your auth token inside the JSON.

An example POST request to generate youtube descriptions would look like this:

curl --location --request POST 'https://api.textcortex.com/hemingwai/generate_text_v3/' \
--data-raw '{
    "template_name": "youtube_description",
    "prompt": {
      "video_title": "How to teach math to five year old",
      "video_keywords": "education, kids, learning",
      "target_audience": "Young moms and dads"
    },
    "temperature": 0.65,
    "token_count": 200,
    "n_gen": 2,
    "source_language": "en",
    "api_key": "gAAAAABitbsJGBo4fSNhhhRCp-xQUsV-U8hMPj3ZHmKG6Wjy5EAaN3q-L0f720mqZf_cIqfFWvsReTDe94PG6FyYDO1pgawr5CQw5TIbhNKTINvo0dks9WqmRlxungPUkbFUMy6fao5y"

}'
 

One python package to rule all the text content challenges

‍

Generating content right inside your python project just takes 3 lines of code. To make things as easy as possible we have published a python package that you can install with the following command:

pip install textcortex

After installing the package, generating content gets very easy and pretty fast. There are different types of content that can be generated with TextCortex. These are:

• Blog Articles
• Paraphrasing
• Emails
• Product Descriptions
• Instagram Captions
• Ads
• Email body
• Email subject
• Autocompletion of instructed prompts

You can find the complete documentation of TextCortex Hemingwai API under postman here.

Here is an example using the TextCortex python package to generate blog articles:

from textcortex import TextCortex

# Create the hemingwai object and enter your API Key
hemingwai = TextCortex(api_key='YOUR_API_KEY')

# Generate Blog articles using Hemingwai
blog = hemingwai.generate_blog(blog_title='Why SEO is important for your Business?',
                               blog_keywords='SEO, Business',
                               source_language='en', token_count=20, temperature=0.7, n_gen=2)
for row in blog:
		print(row)

Text generation variables:

As you can see, there are some parameters that you can use to fine-tune the generated content. Here is the list of those parameters and what they do:

• prompt: Prompting is a way to instruct the Enterprise API to start writing on a specific subject
• parameters: Used for setting the tone of the generated copy text. It can be basically anything but please keep it plausible :)
• blog_categories: This defines which type of content needs to be generated.
• temperature: Floating number between 0-1. 0 being the lowest creativity and 1 being the highest. Default is 0.65
• word_count: Integer which defines the maximum amount of characters that can be produced.
• source_language: Language code of the source language of the written prompt. for example 'en' for English and 'de' for German. We support 72 languages. If you don't know the language code you can also use 'auto' for this field. Our system will recognize the language of the instructed prompt and follow through with it in its generation.

More usage examples can be found on the TextCortex text generation examples Github repo.

One NPM package to rule all the text content challenges.

‍

Generating content right inside your project just takes 3 lines of code. To make things as easy as possible we have published a NPM-JS package that you can install with the following command:

npm i textcortex-hemingwai-js

After installing the package, generating content gets very easy and pretty fast. There are different types of content that can be generated with TextCortex. These are:

• Blog Articles
• Product Descriptions
• Instagram Captions
• Ads
• Email body
• Email subject
• Autocompletion of instructed prompts

Here is an example using TextCortex JS package to generate blog articles:

const { TextCortex } = require("textcortex-hemingwai-js");

let hemingwai = new TextCortex(YOUR_API_KEY);

hemingwai
  .generateBlog({
    blog_title: "Why SEO is important for your Business?",
    blog_categories: ["SEO", "Business"],
    token_count: 300,
    creativity: 0.5,
    source_language: "en",
    n_gen: 2,
  })
  .then((res) => {
    console.log("res: ", res);
  })
  .catch((err) => {
    console.log("err", err);
  });

Text generation variables:

As you can see, there are some parameters that you can use to fine-tune the generated content. Here is the list of those parameters and what they do:

• prompt: Prompting is a way to instruct the Enterprise API to start writing on a specific subject
• parameters: Used for setting the tone of the generated copy text. It can be basically anything but please keep it plausible :)
• blog_categories: This defines which type of content needs to be generated.
• creativity: Floating number between 0-1. 0 being the lowest creativity and 1 being the highest. Default is 0.7
• character_length: Integer which defines the maximum amount of characters that can be produced.
• source_language: Language code of the source language of the written prompt. for example 'en' for English and 'de' for German. We support 72 languages. If you don't know the language code you can also use 'auto' for this field our system will recognize the language of the instructed prompt and follow through with it in its generation.

More examples can be found under the JS package repo of textcortex on github.

‍

Automate your ad creation with our text generation API

‍

Generating unique and creative ad copies is pretty simple. Just instruct the prompt with product to promote and the target audience. For example_

Product to promote: 'Vega

‍Audience: Young women
‍

Here is how the Post request looks like:

curl --location --request POST 'https://api.textcortex.com/hemingwai/generate_text_v3/' \
--data-raw '{
    "template_name": "ads_copy",
    "prompt": {
      "product_name": "Vegan face cream",
      "target_audience": "Mid aged women",
      "product_category": "Beauty",
      "product_description": "Vegan face cream is an amazing product that helps your skin to replenish its young look while making it shine.",
      "ad_keywords": "vegan, face cream, sustainable"
    },
    "temperature": 0.65,
    "token_count": 200,
    "n_gen": 5,
    "source_language": "en",
    "api_key": "gAAAAABitbsJGBo4fSNhhhRCp-xQUsV-U8hMPj3ZHmKG6Wjy5EAaN3q-L0f720mqZf_cIqfFWvsReTDe94PG6FyYDO1pgawr5CQw5TIbhNKTINvo0dks9WqmRlxungPUkbFUMy6fao5y"

}'

‍

Here is how the post request looks like using TextCortex JS library:

var axios = require('axios');
var data = JSON.stringify({
  "template_name": "ads_copy",
  "prompt": {
    "product_name": "Vegan face cream",
    "target_audience": "Mid aged women",
    "product_category": "Beauty",
    "product_description": "Vegan face cream is an amazing product that helps your skin to replenish its young look while making it shine.",
    "ad_keywords": "vegan, face cream, sustainable"
  },
  "temperature": 0.65,
  "token_count": 200,
  "n_gen": 5,
  "source_language": "en",
  "api_key": "YOUR_API_KEY"
});

var config = {
  method: 'post',
  url: 'https://api.textcortex.com/hemingwai/generate_text_v3/',
  headers: { 
    'Content-Type': 'application/json'
  },
  data : data
};

axios(config)
.then(function (response) {
  console.log(JSON.stringify(response.data));
})
.catch(function (error) {
  console.log(error);
});

Text generation variables:

As you can see, there are some parameters that you can use to fine-tune the generated content. Here is the list of those parameters and what they do:

• prompt: Prompting is a way to instruct the Enterprise API to start writing on a specific subject
• parameters: Used for setting the tone of the generated copy text. It can be basically anything but please keep it plausible.
• blog_categories: This defines which type of content needs to be generated.
• creativity: Floating number between 0-1. 0 being the lowest creativity and 1 being the highest. Default is 0.7
• character_length: Integer which defines the maximum amount of characters that can be produced.
• source_language: Language code of the source language of the written prompt. for example 'en' for English and 'de' for German. We support 72 languages. If you don't know the language code you can also use 'auto' for this field our system will recognize the language of the instructed prompt and follow through with it in its generation.

Besides reading this guide on how to implement the API for blog writing we recommend you to have a look at our article about long-form and blog writing is hard that's why we take away 70% of your work with TextCortex.

Starting to generate unique and creative blog articles programmatically with our API is pretty simple. Just instruct the title of the blog post you want to generate together with the keywords that are important. For example:

Blog Title: 'Why SEO is important for your Business?'
Keywords: 'SEO', 'Business'
‍

Here is the post request using cURL:

curl --location --request POST 'https://api.textcortex.com/hemingwai/generate_text_v3/' \
--data-raw '{
    "template_name": "blog_body",
    "prompt": {
        "blog_title": "Why Content is important for your SEO?",
        "blog_keywords": "ai, content generation tools, Search engine optimisation"
    },
    "temperature": 0.65,
    "token_count": 100,
    "n_gen": 2,
    "source_language": "en",
    "api_key": "gAAAAABitbsJGBo4fSNhhhRCp-xQUsV-U8hMPj3ZHmKG6Wjy5EAaN3q-L0f720mqZf_cIqfFWvsReTDe94PG6FyYDO1pgawr5CQw5TIbhNKTINvo0dks9WqmRlxungPUkbFUMy6fao5y"
}'

‍

Here is how the post request looks like using Axios NodeJS library:

var axios = require('axios');
var data = JSON.stringify({
  "template_name": "blog_body",
  "prompt": {
    "blog_title": "Why Content is important for your SEO?",
    "blog_keywords": "ai, content generation tools, Search engine optimisation"
  },
  "temperature": 0.65,
  "token_count": 100,
  "n_gen": 2,
  "source_language": "en",
  "api_key": "YOUR_API_KEY"
});

var config = {
  method: 'post',
  url: 'https://api.textcortex.com/hemingwai/generate_text_v3/',
  headers: { 
    'Content-Type': 'application/json'
  },
  data : data
};

axios(config)
.then(function (response) {
  console.log(JSON.stringify(response.data));
})
.catch(function (error) {
  console.log(error);
});

Text generation variables:

As you can see, there are some parameters that you can use to fine-tune the generated content. Here is the list of those parameters and what they do:

• prompt: Prompting is a way to instruct the Enterprise API to start writing on a specific subject
• parameters: Used for setting the tone of the generated copy text. It can be basically anything but please keep it plausible :)
• category: This defines which type of content needs to be generated.
• creativity: Floating number between 0-1. 0 being the lowest creativity and 1 being the highest. Default is 0.7
• character_length: Integer which defines the maximum amount of characters that can be produced.
• source_language: Language code of the source language of the written prompt. for example 'en' for English and 'de' for German. We support 72 languages. If you don't know the language code you can also use 'auto' for this field our system will recognize the language of the instructed prompt and follow through with it in its generation.

Pro advice:

As mentioned in the beginning of the article we recommend reading the long-form and blog writing is hard that's why we take away 70% of your work with TextCortex article.

1) Give clear instructions.

If you ever feel disappointed by the text our AI writers have written for you, ask yourself:

• What might be the pattern which the AI writers are following?
• Was my instruction unclear? Ask yourself would my friend understand the assignment?
• Did I leave out information that I wanted to have in there?
• Did I limit the creativity of the AI writers too much so they don’t dare to do something different?

Often, you can do the following:

• Does the creation look like a list of items? Were my instructions a list and it is just building on top of it?
• Try to change the instructions to something with more context.
• Add more information with the fitting context into your instructions

Learn more about how our AI writers think: [LINK TO THE HELP CENTER]

2) Divide & Conquer

Like with so many big problems it helps to divide the task into smaller bite-sized pieces.

So instead of expecting a 2000 word article right from the start, you can start with smaller problems. Think about it an article is often consisting of an intro, the main part, and a conclusion.

Think about a content brief before starting to create.

For example, if you want want to write a blog about "how SEO helps businesses grow organically" and in the best you want around 2000 words this is quite big of a task. Divide & conquer the challenge and break it down.

1. Intro: Why is SEO important for businesses?
2. -> POST request
3. Main part: How can you improve SEO with text content?
4. -> POST request
5. Conclusion: What is the first step to get into SEO?
6. -> POST request

Then bundle the responses together into a bigger piece of text content.

Besides reading this guide on how to implement the API for blog writing we recommend you to have a look at our article about how to use our TextCortex to create 1000s of selling descriptions for your Shopify, Amazon FBA or WooCommerce shop.

‍

Starting to generate unique and creative product descriptions programmatically with our API is pretty simple. Just instruct the name of the product, add the fitting product category to it together with some features or the brand. For example:

‍

Product Name: "Blue sports underwear"
Brand: Nike
Features: Ultra soft and super well wet absorbing,
Category: Clothing,

Here is the POST request

curl --location --request POST 'https://api.textcortex.com/hemingwai/generate_text_v3' \
--data-raw '{
    "template_name": "product_description",
    "prompt": {
        "product_name": "Blue sports underwear",
        "brand": "Nike",
        "product_category": "Clothing",
        "product_features": "Ultra soft and super well wet absorbing"
    },
    "temperature": 0.65,
    "token_count": 200,
    "n_gen": 2,
    "source_language": "en",
    "api_key": "gAAAAABiqHJzkJI0b10m3lb_IiopCkyOQ-T0olFimpMPfO6dnt8j6wUfxzrHgmTkH10sKz1QOfFYa9FNhGvgbmlhQWHBtaYNyPEqAvLbUl3UY7fviPpVke3yp5TNUNpuw2VYE2lyeJpg"
}'

‍

Here is how the post request looks like using TextCortex JS library:

import { TextCortex } from "textcortex-hemingwai-js";

const hemingwai = new TextCortex(YOUR_API_KEY);

hemingwai.generateProductDescriptions({
  product_title: "Headphone",
  product_brand: "JBL",
  product_features: ["Noise canceling", "Adjustable Fit"],
  product_category: ["Electronics"],
  source_language: "en",
});

‍

Here is how the post request looks like using Axios NodeJS library:

var axios = require('axios');
var data = JSON.stringify({
  "template_name": "product_description",
  "prompt": {
    "product_name": "Blue sports underwear",
    "brand": "Nike",
    "product_category": "Clothing",
    "product_features": "Ultra soft and super well wet absorbing"
  },
  "temperature": 0.65,
  "token_count": 200,
  "n_gen": 2,
  "source_language": "en",
  "api_key": "YOUR_API_KEY"
});

var config = {
  method: 'post',
  url: 'https://api.textcortex.com/hemingwai/generate_text_v3/',
  headers: { 
    'Content-Type': 'application/json'
  },
  data : data
};

axios(config)
.then(function (response) {
  console.log(JSON.stringify(response.data));
})
.catch(function (error) {
  console.log(error);
});

‍

Automate social media caption writing with our API.

‍

Generating multiple Instagram captions programmatically is pretty simple. Just give the name of the product that you want to promote and your audience as input like the following:

Product: "Blue shaded sunglasses with UV protection

Audience: University Students

‍

Here is the POST request

curl --location --request POST 'https://api.textcortex.com/hemingwai/generate_text_v3' \
--header 'Content-Type: application/json' \
--data-raw '{
    "template_name": "instagram_caption",
    "prompt": {
        "product": "Blue shaded sunglasses with UV protection",
        "target_audience": "University students"
    },
    "temperature": 0.65,
    "token_count": 200,
    "n_gen": 2,
    "source_language": "en",
    "api_key": "gAAAAABitbsJGBo4fSNhhhRCp-xQUsV-U8hMPj3ZHmKG6Wjy5EAaN3q-L0f720mqZf_cIqfFWvsReTDe94PG6FyYDO1pgawr5CQw5TIbhNKTINvo0dks9WqmRlxungPUkbFUMy6fao5y"

}'

‍

Here is how the post request looks like using Axios NodeJS library:

var axios = require('axios');
var data = JSON.stringify({
  "template_name": "instagram_caption",
  "prompt": {
    "product": "Blue shaded sunglasses with UV protection",
    "target_audience": "University students"
  },
  "temperature": 0.65,
  "token_count": 200,
  "n_gen": 2,
  "source_language": "en",
  "api_key": "YOUR_API_KEY"
});

var config = {
  method: 'post',
  url: 'https://api.textcortex.com/hemingwai/generate_text_v3/',
  headers: { 
    'Content-Type': 'application/json'
  },
  data : data
};

axios(config)
.then(function (response) {
  console.log(JSON.stringify(response.data));
})
.catch(function (error) {
  console.log(error);
});

Text generation variables:

As you can see, there are some parameters that you can use to fine-tune the generated content. Here is the list of those parameters and what they do:

• prompt: Prompting is a way to instruct the Enterprise API to start writing on a specific subject
• parameters: Used for setting the tone of the generated copy text. It can be basically anything but please keep it plausible. For the social media, captions use case your should definitely enter a certain type of target audience as parameter.
• category: This defines which type of content needs to be generated.
• creativity: Floating number between 0-1. 0 being the lowest creativity and 1 being the highest. Default is 0.7
• character_length: Integer which defines the maximum amount of characters that can be produced.
• source_language: Language code of the source language of the written prompt. for example 'en' for English and 'de' for German. We support 72 languages. If you don't know the language code you can also use 'auto' for this field our system will recognize the language of the instructed prompt and follow through with it in its generation.

Paraphrasing is as simple as a single POST request to TextCortex's API.

Sentence: Why search engine optimisation is important for your online business?

‍

If you are using TextCortex python library, you can paraphrase given sentence with 3 lines of code:

from textcortex import TextCortex

# Create the hemingwai object and enter your API Key
hemingwai = TextCortex(api_key='YOUR_API_KEY')

paraphrase = hemingwai.paraphrase(prompt='He also teaches architectural and urban design studios in several'
                                         ' universities as an adjunct professor.',
                                  source_language='en', token_count=200, temperature=1, n_gen=2)

for row in paraphrase:
    print(row)

‍

Here is how the post request looks like using Axios NodeJS library:

var axios = require('axios');
var data = JSON.stringify({
  "template_name": "paraphrase",
  "prompt": {
    "original_sentence": "It was a great day at cortex HQ."
  },
  "temperature": 1.3,
  "token_count": 20,
  "n_gen": 4,
  "language": "en",
  "api_key": "YOUR_API_KEY"
});

var config = {
  method: 'post',
  url: 'https://api.textcortex.com/hemingwai/generate_text_v3/',
  headers: { 
    'Content-Type': 'application/json'
  },
  data : data
};

axios(config)
.then(function (response) {
  console.log(JSON.stringify(response.data));
})
.catch(function (error) {
  console.log(error);
});

‍