ixp
latest
false
- Introduction
- Setting up your account
- Balance
- Clusters
- Concept drift
- Coverage
- Datasets
- General fields
- Labels (predictions, confidence levels, label hierarchy, and label sentiment)
- Models
- Streams
- Model Rating
- Projects
- Precision
- Recall
- Annotated and unannotated messages
- Extraction Fields
- Sources
- Taxonomies
- Training
- True and false positive and negative predictions
- Validation
- Messages
- Access control and administration
- Manage sources and datasets
- Understanding the data structure and permissions
- Creating or deleting a data source in the GUI
- Uploading a CSV file into a source
- Preparing data for .CSV upload
- Creating a dataset
- Multilingual sources and datasets
- Enabling sentiment on a dataset
- Amending dataset settings
- Deleting a message
- Deleting a dataset
- Exporting a dataset
- Using Exchange integrations
- Model training and maintenance
- Understanding labels, general fields, and metadata
- Label hierarchy and best practices
- Comparing analytics and automation use cases
- Turning your objectives into labels
- Overview of the model training process
- Generative Annotation
- Dastaset status
- Model training and annotating best practice
- Training with label sentiment analysis enabled
- Training chat and calls data
- Understanding data requirements
- Train
- Introduction to Refine
- Precision and recall explained
- Precision and Recall
- How validation works
- Understanding and improving model performance
- Reasons for label low average precision
- Training using Check label and Missed label
- Training using Teach label (Refine)
- Training using Search (Refine)
- Understanding and increasing coverage
- Improving Balance and using Rebalance
- When to stop training your model
- Using general fields
- Generative extraction
- Using analytics and monitoring
- Automations and Communications Mining™
- Developer
- Using the API
- API tutorial
- Uploading data
- Downloading data
- Exchange Integration with Azure service user
- Exchange Integration with Azure Application Authentication
- Exchange Integration with Azure Application Authentication and Graph
- Fetching data for Tableau with Python
- Elasticsearch integration
- General field extraction
- Self-hosted Exchange integration
- UiPath® Automation Framework
- UiPath® official activities
- How machines learn to understand words: a guide to embeddings in NLP
- Prompt-based learning with Transformers
- Efficient Transformers II: knowledge distillation & fine-tuning
- Efficient Transformers I: attention mechanisms
- Deep hierarchical unsupervised intent modelling: getting value without training data
- Fixing annotating bias with Communications Mining™
- Active learning: better ML models in less time
- It's all in the numbers - assessing model performance with metrics
- Why model validation is important
- Comparing Communications Mining™ and Google AutoML for conversational data intelligence
- Licensing
- FAQs and more
Communications Mining user guide
Last updated Oct 7, 2025
Note: We strive to make the API predictable, as well as easy to use and
integrate. If you have any feedback that could help us improve it, or if you encounter any
issues or unexpected behavior, contact support. We will get back to
you as soon as possible.
All API requests are sent to Communications Mining™ as JSON objects to your tenant endpoint over HTTPS.
Note: You can view all available endpoints in the . Additionally, you
can check the API
Tutorial.
Tenants onboarded via UiPath®:
https://cloud.uipath.com/<my_uipath_organisation>/<my_uipath_tenant>/reinfer_/api/...https://cloud.uipath.com/<my_uipath_organisation>/<my_uipath_tenant>/reinfer_/api/...
Tenants onboarded via Communications Mining:
https://<mydomain>.reinfer.io/api/...https://<mydomain>.reinfer.io/api/...
Important: In Communications Mining™, development and production
data and workflows can be separated either by having separate tenants, or by placing them in
separate projects in the same tenant. In each case the data access is permissioned
separately , so that developers can have admin access to development data while stricter
controls can be placed on production. If using separate tenants then the API endpoint is
different for each of development and production data; if using separate projects in the
same tenant then that single tenant's endpoint is used for both.
All API requests require authentication to identify the user making the request. Authentication is provided through an access token.
To obtain the developer access token, proceed as follows:
- Access IXP from Automation Cloud.
- Go to the Administration page.
- Select My Account.
- Under API token, select the
Regenerate button, which will generate an access token.
Note: You can have only one API token active at a time.
Generating a new token will invalidate the previous one.
You need to include the
following HTTP header for every API call you make, where $REINFER_TOKEN is
your Communications Mining™ API
token.Authorization: Bearer $REINFER_TOKENAuthorization: Bearer $REINFER_TOKEN
The bash examples in the assume that you have
saved your token in an environment variable. The Python and Node examples in the assume
that the token has been stored in a local variable
REINFER_TOKEN via your
chosen config
solution.
Bash
curl -X GET 'https://<my_api_endpoint>/api/...' \
-H "Authorization: Bearer $REINFER_TOKEN"curl -X GET 'https://<my_api_endpoint>/api/...' \
-H "Authorization: Bearer $REINFER_TOKEN"Node
const request = require("request");
request.get(
{
url: "https://<my_api_endpoint>/api/...",
headers: {
Authorization: "Bearer " + process.env.REINFER_TOKEN,
},
},
function (error, response, json) {
// digest response
console.log(JSON.stringify(json, null, 2));
}
);const request = require("request");
request.get(
{
url: "https://<my_api_endpoint>/api/...",
headers: {
Authorization: "Bearer " + process.env.REINFER_TOKEN,
},
},
function (error, response, json) {
// digest response
console.log(JSON.stringify(json, null, 2));
}
);Python
import json
import os
import requests
response = requests.get(
"https://<my_api_endpoint>/api/...",
headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
)
print(json.dumps(response.json(), indent=2, sort_keys=True))import json
import os
import requests
response = requests.get(
"https://<my_api_endpoint>/api/...",
headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
)
print(json.dumps(response.json(), indent=2, sort_keys=True))
Response
{
"status": "ok"
}{
"status": "ok"
}Each API endpoint in the lists its required permissions. To view the permissions you have, go to the Manage Access tab on the Administration page. The tab shows the projects you have access to and the permissions you have in each project.
We use conventional HTTP response codes to indicate success or failure of an API request. In
general, codes in the
2xx range indicate success, codes in the
4xx range indicate an error that resulted from the provided request and
codes in the 5xx range indicate a problem with Communications Mining.
Requests that error will also return a body with a
status value of
error, instead of ok, and an error message describing
the error.
Bash
curl -X GET 'https://<my_api_endpoint>/api/v1/nonexistent_page' \
-H "Authorization: Bearer $REINFER_TOKEN"curl -X GET 'https://<my_api_endpoint>/api/v1/nonexistent_page' \
-H "Authorization: Bearer $REINFER_TOKEN"
Node
const request = require("request");
request.get(
{
url: "https://<my_api_endpoint>/api/v1/nonexistent_page",
headers: {
Authorization: "Bearer " + process.env.REINFER_TOKEN,
},
},
function (error, response, json) {
// digest response
console.log(JSON.stringify(json, null, 2));
}
);const request = require("request");
request.get(
{
url: "https://<my_api_endpoint>/api/v1/nonexistent_page",
headers: {
Authorization: "Bearer " + process.env.REINFER_TOKEN,
},
},
function (error, response, json) {
// digest response
console.log(JSON.stringify(json, null, 2));
}
);Python
import json
import os
import requests
response = requests.get(
"https://<my_api_endpoint>/api/v1/nonexistent_page",
headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
)
print(json.dumps(response.json(), indent=2, sort_keys=True))import json
import os
import requests
response = requests.get(
"https://<my_api_endpoint>/api/v1/nonexistent_page",
headers={"Authorization": "Bearer " + os.environ["REINFER_TOKEN"]},
)
print(json.dumps(response.json(), indent=2, sort_keys=True))
Response
{
"message": "404 Not Found",
"status": "error"
}{
"message": "404 Not Found",
"status": "error"
}Note: Your request can fail due to issues in your network before it reaches
Communications Mining. In such cases, the response you receive will look different from
the previously-described Communications Mining error response.
We use the Server-Timing HTTP header to communicate the time taken for requests to our API to be processed. We include a single metric,
total, which you can use to measure how long our platform took to process your request free from latency of the network request.
An example of the header as it shows in a response:
Server-Timing: total;dur=37.7Server-Timing: total;dur=37.7
Server-Timing values are always in milliseconds, so in this case the API request with this header value took 37.7 milliseconds to process
on our platform.
