- 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
- Overview
- Comparing UiPath Helix Extractor (IXP-Comms) 1.0 and 2.0
- Configuring Fields
- Extraction field type filtering
- Generating your extractions
- Validating and annotating generated extractions
- Best practices and considerations
- Understanding validation on extractions and extraction performance
- Frequently asked questions (FAQs)
- 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
Comparing UiPath Helix Extractor (IXP-Comms) 1.0 and 2.0
Comparison of available LLM options for Communications Mining extractions, including UiPath Helix Extractor 1.0 (IXP-Comms) and UiPath Helix Extractor 2.0 (IXP-Comms), to help you choose the right model for your use case.
To generate your extractions, you can choose from the following different available LLMs:
- UiPath Helix Extractor 1.0 (IXP-Comms) LLM
- UiPath Helix Extractor 2.0 (IXP-Comms) LLM
The main difference is that UiPath Helix Extractor 2.0 relies on external LLM calls, while UiPath Helix Extractor 1.0 does not, but cannot support the same level of extractions. The following sections outline some of the considerations when deciding on an LLM to use. If your use case requires extracting more than 30 fields per message, we recommend using UiPath Helix Extractor 2.0.
UiPath Helix Extractor 1.0 (IXP-Comms) LLM
- Leverages the proprietary LLM of UiPath®, fine-tuned for Communications data.
- Does not rely on external LLM calls.
- Limited to extracting approximately 30 fields per message.
- Less latency than UiPath Helix Extractor 2.0.
- You can fine-tune it based on your data.
- Improving performance for UiPath Helix Extractor 1.0, both in terms of the number of fields, which can be extracted, and the inference speed for the model is a high priority.
- Provides specific occurrence confidences compared to UiPath Helix Extractor 2.0. For more details, check Automating with Generative Extraction.
UiPath Helix Extractor 1.0 (IXP-Comms) is retired in Singapore, United Kingdom, Switzerland, and EU GxP, where the model had no usage for a period of 3 to 6 months. The model is also in the process of being retired in Japan, Canada, and Australia. In the regions where it is retired, only the UiPath Helix Extractor 2.0 (IXP-Comms) LLM is available. For details, check Regional availability.
UiPath Helix Extractor 2.0 (IXP-Comms) LLM
- Relies on external LLM calls, using Azure OpenAI GPT model as the underlying LLM.
- UiPath® cannot guarantee uptime, as this is entirely dependent on the Azure OpenAI endpoints. If the endpoints are down or overloaded, UiPath cannot guarantee availability.
- You can extract more than 30 fields per message.
- Limited to in-context learning.
Note:
When using in-context learning, the platform can only learn from what you prompt it with. Communications Mining™ can automatically refine the prompt to an extent, but the model doesn't learn from any user-led validation.
Use the settings illustrated in the following images to select which LLM you want to use for the Generative Extraction.
UiPath Helix Extractor 1.0 is enabled by default. To enable UiPath Helix Extractor 2.0, make sure you enable Use generative AI features and Use V2 generative extraction model.
If the Use V2 generative extraction model toggle is turned off, it means that you are using UiPath Helix Extractor 1.0.
Having the Use generative AI features and Use V2 generative extraction model toggles turned on means the platform uses the UiPath Azure OpenAI endpoint in the extraction process.
Recommended approach
- Start training your extractions with UiPath Helix Extractor 1.0.
- If the extraction results are correct, continue to train the extractions using UiPath Helix Extractor 1.0. If not, due to high number of fields or large tables in each message, switch to UiPath Helix Extractor 2.0. To verify the extraction results, check the validation statistics in the Generative Extraction tab, on the Validation page. If the precision and recall of the extractions are appropriate for your use case, continue to use UiPath Helix Extractor 1.0. If any data points don't extract as expected with UiPath Helix Extractor 1.0:
- Publish the current model version by going to models and select publish on the most recent model version.
- Reach out to your UiPath® representative, making note of the model version where the extractions were not performing well on. The representative will work directly with the Communications Mining™ product team to investigate and implement improvements.
- If you use UiPath Helix Extractor 2.0, continue to train your model the same way you trained UiPath Helix Extractor 1.0. Go through it, and provide correct examples for each of your extractions.
Note:
When you select UiPath Helix Extractor 2.0, only that model will be trained for Generative Extraction, without simultaneously training a UiPath Helix Extractor 1.0 model. This results in faster training and validation for UiPath Helix Extractor 2.0 users. If you switch to UiPath Helix Extractor 1.0, predictions will continue to be provided by UiPath Helix Extractor 2.0 until a UiPath Helix Extractor 1.0 model version has been trained, and vice versa.