ixp
latest
false
Communications Mining user guide
- 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
- Preparing data for .CSV upload
- Uploading a CSV file into a source
- Uploading a PST file
- 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
- Email transform tags
- 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
- 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
- Uploading data
- Downloading data
- Exchange Integration with Azure service user
- Exchange Integration with Azure Application Authentication
- Exchange Integration with Azure Application Authentication and Graph
- Migration Guide: Exchange Web Services (EWS) to Microsoft Graph API
- 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
Enabling Generative Extraction
Generative Extraction in IXP on Automation Cloud, including how it is activated, permission requirements, and behavior for previously annotated fields.
Note:
- You need Review and Label permissions to configure and validate any extractions.
- If you defined any extraction fields on any of your labels, you automatically have Generative Extraction (GenEx) enabled.
- If you have previously annotated general fields while GenEx was not enabled, you need to provide new annotations for extraction fields, so the model can recognize the relationship between your fields and labels.
- Avoid switching back and forth between the UiPath Helix Extractor 1.0 (IXP-Comms) LLM and the UiPath Helix Extractor 2.0 (IXP-Comms) LLM, as it can complicate tracking and managing the LLM version used for training each model. Find more information on the LLMs in the sections that follow.
To enable Generative Extraction, follow these steps:
- Configure at least one extraction field in the Taxonomy tab, under Settings.
- Depending on which LLM you want to use, UiPath Helix Extractor 1.0 or UiPath Helix Extractor 2.0, in the Dataset tab:
- To use UiPath Helix Extractor 1.0, disable the Use external generative AI features option.
- To use UiPath Helix Extractor 2.0, enable the Use external generative AI features option, and then enable Use V2 generative extraction model.
Regional availability
Generative Extraction is available in the following regions:
- US
- Europe
- Japan
- Canada
- Australia
- Singapore
- United Kingdom
- Switzerland
- EU GxP
- US GxP
Note:
- The UiPath Helix Extractor 1.0 (IXP-Comms) LLM has been retired in Singapore, United Kingdom, Switzerland, and EU GxP. In these regions, Generative Extraction is available exclusively through the UiPath Helix Extractor 2.0 (IXP-Comms) LLM, which relies on external LLM calls. This model can handle larger and more complex extractions than UiPath Helix Extractor 1.0. UiPath is evaluating additional options for the underlying extraction model in these regions. UiPath Helix Extractor 1.0 is also in the process of being retired in Japan, Canada, and Australia.
- Both UiPath Helix Extractor 1.0 and UiPath Helix Extractor 2.0 are available in US, US GxP, and Europe.
For more details on the differences between these models, check Comparing UiPath Helix Extractor (IXP-Comms) 1.0 and 2.0.