Build powerful cognitive software
with Natural Language Understanding capabilities.

Titan API (Metis)

one API
"text-in," "text-out" 

The Titan API provides access to the Titan Cognitive Agent. You can apply natural language understanding (NLU) to your applications with the Titan API.

By receiving text through the Titan API, the Titan cognitive agent processes data . i.e., extracting entities and the relationships between them. 

After extracting the entities and relationships, the agent auto-generates a real-time cognitive model in the form of a dynamic knowledge graph and stores it into its memory.

Upon receiving queries or instructions, the agents navigate the knowledge graph to retrieve or act on newly structured information (answers are in the form text, and actions trigger code).

You don't need to label.
You don't need to annotate.
You don't need to train.
5 things you can quickly do with the API.


Simply by receiving text through the API, Titan agents can autonomously inject into and extract from its knowledge graph any type of concept; things like entities, objects, organizations, people, products, etc. 


Similarly, Titan agents have the ability to inject into and extract from the knowledge graph any type of relationship; things like spatial, temporal, causal, and correlational relations among others. 


Titan agents can understand and reason about information in their knowledge graph.  You can simply ask your questions in natural language and the agent will find the answer if there is one. 


Titan agents have the ability to observe, recognize, and intercept patterns and replace them with new patterns when instructed.  You do not need to train your agent, simply instruct them in natural language.


Titan agents and knowledge graph can be configured with permission to grant/deny users or users groups access based on policy.

Titan API reference guide (v1.0.1)

Table of Contents

1. Introduction

Titan comprises several integrated AI engines and algorithms that work together to deliver a simulated intelligent behavior through the Titan API.

The Titan API can be applied to any natural language task that involves learning, understanding or acting.

You can use the Titan API to build applications like knowledge mining, semantic search, question answering, conversational AI agents, digital workers, digital twins, intelligent automation, prediction engines, fraud detection engines, and much more.

2. Getting started

You can integrate the API into your environment and immediately endow your applications with the ability to learn, understand, and act on natural language queries and instructions.

Your app will need a valid key to make successful Titan API requests. To obtain a key, you must register for the API below.

3. Registration

Titan API is available in the form of a subscription service (Coming Soon). We selected RapidAPI (The leading API marketplace for software developers) as a service partner to help facilitate the implementation of the Titan API service with your software.

Please register (Coming Soon). to request your API key.

After completing the registration form, RapidAPI will provide you with an X-RapidAPI-Key. You will use the X-RapidAPI-Key to authenticate against our API.

Once you have received your key, you immediately start adding Titan cognitive services to your web, mobile, and desktop apps.

4. Documentation

4.1 Definition

The Titan API works simply by capturing the text you submit through the API and forwarding it to a Titan cognitive Agent for analysis. (figure 1)

Once the information is processed, you can either: (figure 2)
Scenario A- Ask the agent questions about the content of the text you submitted.
Scenario B- Instruct your agent to take action based on natural language-driven rules.

4.2 Request

4.2.1 Operation

Titan API is structured around REST principles. Data resources are accessed via standard HTTPS requests in UTF-8 format to an API endpoint. Where possible, Titan API uses appropriate HTTP verbs:

Retrieves Resources.
Creates Resources.
Changes and/or Replaces Resources.
Deletes Resouces.
4.2.2 Endpoints & SDKs

The Titan API endpoints always return a response in JSON metadata format at the base address: 


Based on your subscription plan (Coming Soon), the endpoints to access Titan cognitive services will vary. So please check that you are using the correct endpoints to communicate with our API. 


Regardless of what you prefer as a programing language, we have included a list of SDKs to get you started easily and quickly. You can just import the SDK of your choice by copying the provided code snippet into your application.


4.2.3 JSON Objects

In the API requests and responses, you will frequently encounter the following JSON objects:

Enter session identifier (x-rapidapi-key) 
Enter your content
"What color is the sun?"
4.2.4 Authentication

We use API keys as mean to authenticate your application. We expect developers to build internal applications that don’t need to access more than a single user’s data.

All requests to Titan API require authentication (your X-RapidAPI-key). This is achieved by sending a valid API key in the request header.
The API key assigned to you is in the form of:

"x-rapidapi-key”: “a8e009619xxxxxxxxxx4ea2840f9c19"

4.3 Response

Titan API returns all response data as a JSON object.

4.4 Response Status Codes

Titan API uses the following response status codes, as defined in the RFC 2616 and RFC 6585:

OK - The request has succeeded. The client can read the result of the request in the body and the headers of the response.
Bad Request - The request could not be understood by the server due to malformed syntax. The message body will contain more information; see Response Schema.
Unauthorized - The request requires user authentication or, if the request included authorization credentials, authorization has been refused for those credentials.
Forbidden - The server understood the request, but is refusing to fulfill it.
Not Found - The requested resource could not be found. This error can be due to a temporary or permanent condition.
Too Many Requests - Rate limiting has been applied.
Internal Server Error- When this happens try your request again at a later time or contact our support team to get assistance.
Bad Gateway - The server was acting as a gateway or proxy and received an invalid response from the upstream server.
Bad Gateway - The server was acting as a gateway or proxy and received an invalid response from the upstream server.

4.5 Rate Limiting

Rate Limiting enables Titan API to share access bandwidth to its resources equally across all users.

Rate limiting is applied as per application based on Client ID/API key, and regardless of the number of users who use the application simultaneously.

To reduce the amount of requests, fetch multiple entities in one request.
For example: You can ask multiple questions about your text at the same time in the same request and that will drastically reduce the amount of requests your application utilizes.

Note: If Titan API returns status code 429, it means that you have sent too many requests. When this happens try your request again at a later time or contact our support team to get assistance.

Getting Started

Welcome to the Titan API demo,

You have access to a cognitive agent with a pre-configured session timeout of 60 minutes. If you wish to continue testing after your session expires, you need to reload your web browser tab to access a new agent.

After your session expires or your browser is reset, we will automatically discard your previously loaded content.

Getting started with the Titan API Demo

Your agent does not have any information and does not know anything.

You can teach your agent by adding content (in the form of text) to its knowledge base.

Your agent will learn your content in real-time.

You can ask your agent questions regarding the content you provided.

  • If the answer is in the agent knowledge base, the agent will answer your question.
  • If the answer is not in the agent knowledge base, the agent will respond “I don’t know.”

The agent will continuously learn and answer more questions as you add content.

More Content –> Deeper Inference.


  • PoS:

Part-Of-Speech (PoS) tagger labels words as one of several categories to identify the word’s function in a given language.

  • Actions:

Titan Action System produces a table to identify the intents and actions in a given language.

  • Facts:

Titan Fact System produces a table to identify factual information in a given language.

  • Relations:

Titan graph Engine automatically constructs semantic representations from textual data sources.

  • Search:

Titan Cognitive Search Engine provides answers to inquiries about upload text. The questions should be in the form of: Who, What, When Where, and Why?

  • Instruct:

Titan Instruction System allows you to setup rules to govern and manage your Agent’s actions.

  • Insight:

Titan Insight System produces a report to identify knowledge either directly the provided text or inferred a combination of different content sources.