Content Insights
Content Insights works for both uploaded files or by referencing a completed translation.
Note
In order to use this feature you need to have it enabled on your account.
Create Content Insights for files
This call creates the Content insights by sending the input and the Multipart form data.
Linux
curl -XPOST \
-H "Content-Type:multipart/form-data" \
-H "Authorization:Bearer asd0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiIsI" \
-H "Trace-ID: 2c0c4dda-8333-4538-983e-e098de7cf555" \
-F "sourceLanguage=eng" \
-F "file=@\"./demo.txt\";filename=\"demo.txt\"" \
-F "file=@\"./demo2.txt\";filename=\"demo2.txt\"" \
'https://api.languageweaver.com/v4/content-insights'
Windows
curl -XPOST^
-H "Content-Type:multipart/form-data"^
-H "Authorization:Bearer asd0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiIsI"^
-H "Trace-ID: 2c0c4dda-8333-4538-983e-e098de7cf555"^
-F "sourceLanguage=eng"^
-F "input=@\"demo.txt\";filename=\"demo.txt\""^
-F "input=@\"demo2.txt\";filename=\"demo2.txt\""^
https://api.languageweaver.com/v4/content-insights
Access token type
User credentials - Allowed User Roles: Admin, Linguist, Translator
API credentials
HTTP Request
POST /v4/content-insights
Headers
Name | Value (example) | Description |
---|---|---|
Authorization | Bearer asd0eXAi... | Bearer token |
Trace-ID | 2c0c4dda-8333-4538-983e-e098de7cf555 | Optional unique request identifier (UUID) provided by client |
Request Body:
(Request Body)
--bmmy1qevxni7T7MwlQcBYI6EvBdjoQj
Content-Disposition: form-data; name="file"; filename="demo1.txt"
Content-Type: multipart/form-data
Content-Length: 11
--bmmy1qevxni7T7MwlQcBYI6EvBdjoQj
Content-Disposition: form-data; name="file"; filename="demo2.txt"
Content-Type: multipart/form-data
Content-Length: 50
--bmmy1qevxni7T7MwlQcBYI6EvBdjoQj
Content-Disposition: form-data; name="sourceLanguage"
Content-Type: text/plain;charset=UTF-8
Content-Length: 3
--bmmy1qevxni7T7MwlQcBYI6EvBdjoQj--
Request Parameters
Format
multipart/form-data
Name | Type | Mandatory | Default value | Description |
---|---|---|---|---|
sourceLanguage |
string | yes | Three letters language code of the source language | |
file |
file | yes | The binary content of the file |
Response JSON:
{
"contentInsightsId": "ec00a687-9a72-443a-b5cf-121da1c84789",
"documents":[
{
"fileId": "f8acc566-1b3b-4ebc-b40a-69c51568ef75",
"fileName": "demo1.txt"
},
{
"fileId": "f8acasd6-1b3b-4ebc-b40a-69c51568ef75",
"fileName": "demo2.txt"
}
]
}
Response
Headers
Name | Value (example) | Description |
---|---|---|
BeGlobal-Request-ID | dbbbc062-88a7-4783-8d52-dea795e517f4 | Unique request identifier (UUID) |
Trace-ID | 2c0c4dda-8333-4538-983e-e098de7cf555 | The identifier provided in the request (UUID) |
Format
JSON
Name | Type | Description |
---|---|---|
contentInsightsId |
string | The id of the content insights request. This has to be used for the subsequent calls |
fileId |
string | The id of each file sent for content insights. This has to be used for the subsequent calls |
fileName |
string | The name of each file sent for content insights |
{
"errors":[
{
"code":1047,
"description":"File demo1.txt is empty"
}
]
}
Error Response
Format
JSON
Name | Type | Description |
---|---|---|
errors |
list | A list with the errors that occurred |
code |
integer | The code of the error |
description |
string | The description of the error |
Returned HTTP Codes:
Http Code | Description |
---|---|
202 | When the content insights request is successfully initiated |
400 | When the input data is not valid |
401 | When the authentication process failed or the access token is not valid |
403 | Forbidden to access resource |
500 | Application internal error |
Note
The file limit is set to 100 MB.
Create Content Insights for existing translations
This call allows you to perform content insights for a file that was already translated.
Linux
curl -XPOST \
-H "Content-type: application/json" \
-H "Authorization:Bearer asd0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiIsI" \
-H 'Trace-ID: 2c0c4dda-8333-4538-983e-e098de7cf555' \
-d '{"translationIds": ["gfui83oah", "gfui83oah1"]}' \
https://api.languageweaver.com/v4/content-insights
Windows
curl -X POST -H "Content-type: application/json"^
-H "Authorization: Bearer asd0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiIsI"^
-H "Trace-ID: 2c0c4dda-8333-4538-983e-e098de7cf555" -d^
"{^
\"translationIds\": [\"gfui83oah\", \"gfui83oah1\"]^
}" https://api.languageweaver.com/v4/content-insights
Access token type
User credentials - Allowed User Roles: Admin, Linguist, Translator
API credentials
HTTP Request
POST /v4/content-insights
Headers
Name | Value (example) | Description |
---|---|---|
Authorization | Bearer asd0eXAi... | Bearer token |
Trace-ID | 2c0c4dda-8333-4538-983e-e098de7cf555 | Optional unique request identifier (UUID) provided by client |
Request Parameters
Format
JSON
Name | Type | Mandatory | Default value | Description |
---|---|---|---|---|
translationIds |
string array | no | empty | A string array containing translation ids |
Request JSON:
{
"translationIds": ["gfui83oah", "gfui83oah1"]
}
Note
The translation ids must reference translations that are still available in the system. This means that the translation was either not retrieved yet, or 'Content deletion' is disabled for this account
Response JSON:
{
"contentInsightsId": "ec00a687-9a72-443a-b5cf-121da1c84789",
"documents":[
{
"fileId": "f8acc566-1b3b-4ebc-b40a-69c51568ef75",
"fileName": "demo1.txt"
},
{
"fileId": "f8acasd6-1b3b-4ebc-b40a-69c51568ef75",
"fileName": "demo2.txt"
}
]
}
Response
Headers
Name | Value (example) | Description |
---|---|---|
BeGlobal-Request-ID | dbbbc062-88a7-4783-8d52-dea795e517f4 | Unique request identifier (UUID) |
Trace-ID | 2c0c4dda-8333-4538-983e-e098de7cf555 | The identifier provided in the request (UUID) |
Format
JSON
Name | Type | Description |
---|---|---|
contentInsightsId |
string | The id of the content insights request. This has to be used for the subsequent calls |
fileId |
string | The id of each file sent for content insights. This has to be used for the subsequent calls |
fileName |
string | The name of each file sent for content insights |
{
"errors":[
{
"code":1047,
"description":"File demo1.txt is empty"
}
]
}
Error Response
Format
JSON
Name | Type | Description |
---|---|---|
errors |
list | A list with the errors that occurred |
code |
integer | The code of the error |
description |
string | The description of the error |
Returned HTTP Codes:
Http Code | Description |
---|---|
202 | When the content insights request is successfully initiated |
400 | When the input data is not valid |
401 | When the authentication process failed or the access token is not valid |
403 | Forbidden to access resource |
500 | Application internal error |
Check the Content Insights status
This call will allow the user to check the status of a previously created content insights.
The status can be: INIT, ACCEPTED, IN_PROGRESS, DONE, FAILED.
If the status is INIT, ACCEPTED or IN_PROGRESS then the status call has to be triggered again. You
need to set a sleep time between the subsequent calls made to the status
endpoint /v4/content-insights/{contentInsightsId}
which should vary from 100 milliseconds for smaller inputs (up
to 500 characters)
to 500 milliseconds for larger inputs.
If the status is DONE the result of the content insights can
be retrieved.
If the status is FAILED this signals that we cannot run content insights. When this status is returned, the
Get Status calls must not be sent anymore.
Linux
curl -XGET -H 'Authorization: Bearer asd0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiIsI' -H 'Trace-ID: 2c0c4dda-8333-4538-983e-e098de7cf555' \
'https://api.languageweaver.com/v4/content-insights/ec00a687-9a72-443a-b5cf-121da1c84789'
Windows
curl -XGET -H "Authorization: Bearer asd0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiIsI" -H "Trace-ID: 2c0c4dda-8333-4538-983e-e098de7cf555" ^
https://api.languageweaver.com/v4/content-insights/ec00a687-9a72-443a-b5cf-121da1c84789
Access token type
User credentials - Allowed User Roles: Admin, Linguist, Translator
API credentials
HTTP Request
GET /v4/content-insights/{contentInsightsId}
Headers
Name | Value (example) | Description |
---|---|---|
Authorization | Bearer asd0eXAi... | Bearer token |
Trace-ID | 2c0c4dda-8333-4538-983e-e098de7cf555 | Optional unique request identifier (UUID) provided by client |
Response JSON:
{
"contentInsightsStatus":"INIT",
"documents":[
{
"fileId": "f8acc566-1b3b-4ebc-b40a-69c51568ef75",
"fileName": "demo2.txt",
"summarization": {
"status": "INIT"
}
},
{
"fileId": "f8acasd6-1b3b-4ebc-b40a-69c51568ef75",
"fileName": "demo.txt",
"summarization": {
"status": "INIT"
}
}
]
}
{
"contentInsightsStatus": "IN_PROGRESS",
"documents": [
{
"fileId": "f8acc566-1b3b-4ebc-b40a-69c51568ef75",
"fileName": "demo2.txt",
"summarization": {
"status": "IN_PROGRESS"
}
},
{
"fileId": "f8acasd6-1b3b-4ebc-b40a-69c51568ef75",
"fileName": "demo.txt",
"summarization":{
"status": "DONE"
}
}
]
}
{
"contentInsightsStatus":"DONE",
"documents":[
{
"fileId": "f8acc566-1b3b-4ebc-b40a-69c51568ef75",
"fileName": "demo2.txt",
"summarization": {
"status": "DONE"
}
},
{
"fileId": "f8acasd6-1b3b-4ebc-b40a-69c51568ef75",
"fileName":"demo.txt",
"summarization":{
"status": "DONE"
}
}
]
}
Response
Headers
Name | Value (example) | Description |
---|---|---|
BeGlobal-Request-ID | dbbbc062-88a7-4783-8d52-dea795e517f4 | Unique request identifier (UUID) |
Trace-ID | 2c0c4dda-8333-4538-983e-e098de7cf555 | The identifier provided in the request (UUID) |
Format
JSON
Name | Type | Description |
---|---|---|
contentInsightsStatus |
string | A string representing the status of the content insights process. Can be one of the following: INIT - source files were received by system and will be validated ACCEPTED - the files were validated by the system and content insights can be generated IN_PROGRESS - Content insights are being generated DONE - Content insights were generated for the given files. When this status is returned then the Retrieve Content Insights call should be triggered. FAILED - this state signals that we cannot run Content Insights. When this status is returned, the Get Status calls must stop because there is no way to recover from this state. |
documents |
string array | A string array with the list of files that were submitted for content insights |
fileId |
string | The id of the file |
fileName |
string | The name of the file |
summarization |
string | The content insights operation |
status |
string | The status of the content insights operation |
{
"errors":[
{
"code":43,
"description": "Unknown status for requestId {0}"
}
]
}
Error Response
Format
JSON
Name | Type | Description |
---|---|---|
errors |
list | A list with the errors that occurred |
code |
integer | The code of the error |
description |
string | The description of the error |
Returned HTTP Codes:
Http Code | Description |
---|---|
200 | When the content insights status is successfully returned |
400 | When the input data is not valid |
401 | When the authentication process failed or the access token is not valid |
403 | Forbidden to access resource |
500 | Application internal error |
Retrieve Content Insights Results
This call returns the result of the aggregated content insights. The sentences that are part of the summary come from all the files that were part of the input.
Linux
curl -XGET -H 'Authorization: Bearer asd0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiIsI' -H 'Trace-ID: 2c0c4dda-8333-4538-983e-e098de7cf555' \
'https://api.languageweaver.com/v4/content-insights/ec00a687-9a72-443a-b5cf-121da1c84789/result'
Windows
curl -XGET -H "Authorization: Bearer asd0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiIsI" -H "Trace-ID: 2c0c4dda-8333-4538-983e-e098de7cf555" ^
https://api.languageweaver.com/v4/content-insights/ec00a687-9a72-443a-b5cf-121da1c84789/result
Access token type
User credentials - Allowed User Roles: Admin, Linguist, Translator
API credentials
HTTP Request
GET v4/content-insights/{contentInsightsId}/result
Headers
Name | Value (example) | Description |
---|---|---|
Authorization | Bearer asd0eXAi... | Bearer token |
Trace-ID | 2c0c4dda-8333-4538-983e-e098de7cf555 | Optional unique request identifier (UUID) provided by client |
Response JSON:
{
"contentInsightsId":"ec00a687-9a72-443a-b5cf-121da1c84789",
"stats": {
"inputWordCount": 5,
"inputCharCount": 26
},
"sourceLanguage":"eng",
"summarization":{
"segments":[
{
"text":"The English word Alps derives from the Latin Alpes (through French).",
"lineNumber":3,
"score":0.5954782
},
{
"text":"The peaks in the easterly portion of the range, in Austria and Slovenia, are smaller than those in the central and western portions.",
"lineNumber":11,
"score":0.5050102
},
{
"text":"The countries with the greatest alpine territory are Switzerland, France (21.4%), Austria (28.7% of the total area) and Italy (27.2%).",
"lineNumber":12,
"score":0.4954782
}
]
}
}
Response
Headers
Name | Value (example) | Description |
---|---|---|
BeGlobal-Request-ID | dbbbc062-88a7-4783-8d52-dea795e517f4 | Unique request identifier (UUID) |
Trace-ID | 2c0c4dda-8333-4538-983e-e098de7cf555 | The identifier provided in the request (UUID) |
Format
JSON
Name | Type | Description |
---|---|---|
contentInsightsId |
string | The id of the content insights request |
stats |
object | Content insights statistics |
inputWordCount |
int | Number of input words in the source files |
inputCharCount |
int | Number of input characters in the source files |
sourceLanguage |
string | Three letters language code of the source language |
summarization |
object | Object containing the sentences from the input files that were selcted as part of the summary |
segments |
array | The array with the sentences from the input files that were selcted as part of the summary |
text |
string | A sentence from the input files that was selected to be part of the summary |
lineNumber |
int | The line number of the sentence in the input file |
score |
int | A score between 0 and 1. The higher the score, the more representative the sentence is for the summary |
{
"errors":[
{
"code":42,
"description": "Invalid requestId {0}"
}
]
}
Error Response
Format
JSON
Name | Type | Description |
---|---|---|
errors |
list | A list with the errors that occurred |
code |
integer | The code of the error |
description |
string | The description of the error |
Returned HTTP Codes:
Http Code | Description |
---|---|
200 | When the content insights content is successfully returned |
400 | When the input data is not valid |
401 | When the authentication process failed or the access token is not valid |
403 | Forbidden to access resource |
500 | Application internal error |
Retrieve Content Insights Results for one file
This call will allow the user to get the result of the content insights for a single file.
Linux
curl -XGET -H 'Authorization: Bearer asd0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiIsI' -H 'Trace-ID: 2c0c4dda-8333-4538-983e-e098de7cf555' \
'https://api.languageweaver.com/v4/content-insights/ec00a687-9a72-443a-b5cf-121da1c84789/file/f8acc566-1b3b-4ebc-b40a-69c51568ef75/result'
Windows
curl -XGET -H "Authorization: Bearer asd0eXAiOiJKV1QiLCJhbGciOiJSUzI1NiIsI" -H "Trace-ID: 2c0c4dda-8333-4538-983e-e098de7cf555" ^
https://api.languageweaver.com/v4/content-insights/ec00a687-9a72-443a-b5cf-121da1c84789/file/f8acc566-1b3b-4ebc-b40a-69c51568ef75/result
Access token type
User credentials - Allowed User Roles: Admin, Linguist, Translator
API credentials
HTTP Request
GET /v4/content-insights/{contentInsightsId}/file/{fileId}/result
Headers
Name | Value (example) | Description |
---|---|---|
Authorization | Bearer asd0eXAi... | Bearer token |
Trace-ID | 2c0c4dda-8333-4538-983e-e098de7cf555 | Optional unique request identifier (UUID) provided by client |
Response JSON:
{
"contentInsightsId":"ec00a687-9a72-443a-b5cf-121da1c84789",
"fileId":"f8acc566-1b3b-4ebc-b40a-69c51568ef75",
"fileName":"SDL.docx",
"stats": {
"inputWordCount": 5,
"inputCharCount": 26
},
"summarization":{
"segments":[
{
"text":"The English word Alps derives from the Latin Alpes (through French).",
"lineNumber":3,
"score":0.5954782
},
{
"text":"The peaks in the easterly portion of the range, in Austria and Slovenia, are smaller than those in the central and western portions.",
"lineNumber":11,
"score":0.5050102
},
{
"text":"The countries with the greatest alpine territory are Switzerland, France (21.4%), Austria (28.7% of the total area) and Italy (27.2%).",
"lineNumber":12,
"score":0.4954782
}
]
}
}
Response
Headers
Name | Value (example) | Description |
---|---|---|
BeGlobal-Request-ID | dbbbc062-88a7-4783-8d52-dea795e517f4 | Unique request identifier (UUID) |
Trace-ID | 2c0c4dda-8333-4538-983e-e098de7cf555 | The identifier provided in the request (UUID) |
Format
JSON
Name | Type | Description |
---|---|---|
contentInsightsId |
string | The id of the content insights request |
fileId |
string | The id of the file |
fileName |
string | The name of the file |
stats |
object | Content insights statistics |
inputWordCount |
int | Number of input words in the source files |
inputCharCount |
int | Number of input characters in the source files |
sourceLanguage |
string | Three letters language code of the source language |
summarization |
object | Object containing the sentences from the input files that were selcted as part of the summary |
segments |
array | The array with the sentences from the input files that were selcted as part of the summary |
text |
string | A sentence from the input files that was selected to be part of the summary |
lineNumber |
int | The line number of the sentence in the input file |
score |
int | A score between 0 and 1. The higher the score, the more representative the sentence is for the summary |
{
"errors":[
{
"code": 42,
"description": "Invalid requestId {0}"
}
]
}
Error Response
Format
JSON
Name | Type | Description |
---|---|---|
errors |
list | A list with the errors that occurred |
code |
integer | The code of the error |
description |
string | The description of the error |
Returned HTTP Codes:
Http Code | Description |
---|---|
200 | When the content insights content is successfully returned |
400 | When the input data is not valid |
401 | When the authentication process failed or the access token is not valid |
403 | Forbidden to access resource |
500 | Application internal error |