Skip to content
Text Generative AI
/
A classifier that measures the accuracy of the translated text.

MARCIE API (2025-08-18T18:01:56Z)

What's this?

Application APIs

Lets documents, content and metadata be stored in MARCIE for further API processing. To get this data into the MARCIE store, document decomposition and ingestion, as well as manual document/content submission APIs can be used. Once populated, application APIs provide semantic/syntactic analysis, semantic search and content related querying to be executed at scale. See APPS from the navigation panel for more details.

Content APIs

Content is submitted to endpoints with associated control attributes and results are synchronously returned. Primary examples of these APIs include: content comparison, enrichment, transformation, and analysis (spellcheck, grammar, sentiment, readability). See DOCUMENT and CONTENT from the navigation panel for more details. In this scenario, content is not stored or persisted.

Download OpenAPI description
openapi.json
openapi.yaml
Overview
MARCIE Support

info@messagepoint.com

Languages
Servers
Mock server

https://marcie.redocly.app/_mock/openapi/

https://w1waoh1clk.execute-api.us-east-1.amazonaws.com/{basePath}/

Text Generative AI

Text focused APIs utilizing generative large language models (LLMs)

Operations

Sentiment classification

Request

Multilingual sentiment classification using LLM models..

Security
api_key
Bodyapplication/jsonrequired
textstringnon-emptyrequired

The text content with UTF-8 text representation

ishtmlboolean

A boolean flag that should be set to true if text is in HTML markup.

Default false
randomnumber[ 0 .. 1 ]

Controls the amount of randomness in the generated text. Lowering this will result in the output to be more deterministic.

Default 0
modelstring

The generative model to use.

Default "gpt4-o"
Enum"gpt4-o""gpt4-o-mini""gpt4""gpt4-t""o1""o1-mini"
curl -i -X POST \
  https://marcie.redocly.app/_mock/openapi/text/enrichment/sentiment/llm \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: YOUR_API_KEY_HERE' \
  -d '{
    "text": "We'\''re so happy to see you, and we will be delighted to extend a warm welcome."
  }'

Responses

200 response

Headers
Access-Control-Allow-Originstring
Bodyapplication/json
object(Empty Schema)
Response
application/json
{}

A classifier that measures the accuracy of the translated text.

Request

Given a text pair [text1, text2], the classifier outputs 't' if the translation is faithful and accurate, 'f' otherwise.

Security
api_key
Bodyapplication/jsonrequired
text1stringnon-emptyrequired

The text content with UTF-8 text representation

text2stringnon-emptyrequired

The text content with UTF-8 text representation

lang1string[ 2 .. 5 ] characters

The language code for the text1.

lang2string[ 2 .. 5 ] characters

The language code for the text2.

domainstring

The content domain to be used for additional context.

Default "general"
Any of:

Predefined options for the domain.

string

Predefined options for the domain.

Default "general"
Enum"general""healthcare""banking""finance""retail""sports"
ishtmlboolean

A boolean flag that should be set to true if text is in HTML markup.

Default false
explainboolean

A boolean flag that should be set to true if an explanation for the label is required.

Default false
cacheboolean

A boolean flag that utilizes a simple caching scheme as an optimization for duplicates in input..

Default true
randomnumber[ 0 .. 1 ]

Controls the amount of randomness in the generated text. Lowering this will result in the output to be more deterministic.

Default 0
modelstring

The generative model to use.

Default "gpt4-o"
Enum"gpt4-o""gpt4-o-mini""gpt4""gpt4-t""o1""o1-mini"
curl -i -X POST \
  https://marcie.redocly.app/_mock/openapi/text/translate/accuracy \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: YOUR_API_KEY_HERE' \
  -d '{
    "text1": "You owe me 200 dollars, and I am here till today.",
    "text2": "Vous me devez 200 dollars, et je suis là jusqu'\''à aujourd'\''hui.",
    "explain": true
  }'

Responses

200 response

Headers
Access-Control-Allow-Originstring
Bodyapplication/json
object(Empty Schema)
Response
application/json
{}

Plain Language Rewrite (EXPERIMENTAL)

Request

Rewrite the given text to be more easier to read and comprehend.

Security
api_key
Bodyapplication/jsonrequired
textstringnon-emptyrequired

The text content with UTF-8 text representation

ishtmlboolean

A boolean flag that should be set to true if text is in HTML markup.

Default false
randomnumber[ 0 .. 1 ]

Controls the amount of randomness in the generated text. Lowering this will result in the output to be more deterministic.

Default 0
modelstring

The generative model to use.

Default "gpt4-o"
Enum"gpt4-o""gpt4-o-mini""gpt4""gpt4-t""o1""o1-mini"
curl -i -X POST \
  https://marcie.redocly.app/_mock/openapi/text/enrichment/plainlang/rewrite \
  -H 'Content-Type: application/json' \
  -H 'x-api-key: YOUR_API_KEY_HERE' \
  -d '{
    "text": "Quantum mechanics is a basic theory in physics that explains how things work at the tiny scale of atoms and subatomic particles. It is the basis for all quantum physics, like quantum chemistry, quantum field theory, quantum technology, and quantum information science."
  }'

Responses

200 response

Headers
Access-Control-Allow-Originstring
Bodyapplication/json
object(Empty Schema)
Response
application/json
{}

Text Similarity

Provides multiple text-based similarity algorithms to measure the similarity of input text pairs. The provided algorithms are tuned to measure similarity both in the representation (syntax) and the meaning (semantics) of the text content.

Operations

Text Summary

Generates a summary for the given text.

Operations

Natural Language Processing

MARCIE NLP operations' request on provided content

Operations

Enrichments/Classification

Text enrichment APIs offer various enrichment functions that take the raw text as its input and provides a specific enrichment/feature corresponding to the input text. An enrichment function is idempotent and its output is determined by the input text and the underlying predictive (deep learning based) linguistic model. Some examples of these include text based sentiment, readability calculation etc. Most of the underlying methods can be used either using a "GET" or a "POST" HTTP method. For smaller text, the GET method offers better performance and allows for network optimizations such as caching.

Operations

Text Transformers

MARCIE text transformers operations' request on provided content

Operations

Spelling & Grammar

MARCIE spell and grammar operations' request on provided content

Operations

Content Moderation

MARCIE API Content Moderation

Operations

Translation

MARCIE translation operations

Operations

Application

Root resource for all application APIs

Operations

Content

Root resource for all content APIs

Operations

Document

Root resource for all document APIs

Operations

PDF Document

PDF document parsing & processing APIs

Operations

Word Document

Microsoft Word document parsing.

Operations

XHTML Email

XHTML Email template parsing.

Operations

Self Service

MARCIE API Self Service

Operations