- 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
- 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
- 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 for Comms and Preview LLMs
- 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
Communications Mining user guide
Comparing UiPath Helix Extractor for Comms and Preview LLMs
To generate your extractions, you can choose from the following different available LLMs:
- UiPath Helix Extractor 1.0 (IXP-Comms) LLM
- Preview LLM
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, you are recommend to use the Preview LLM.
UiPath Helix Extractor 1.0 (IXP-Comms) LLM
- Leverages the proprietary LLM of UiPath®, fine-tuned for Communications data.
- Limited to extracting approximately 30 fields per message.
- Less latency than the Preview LLM.
- You can fine-tune it based on your data.
- Improving performance for UiPath Helix Extractor for Comms, 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 the Preview LLM. For more details, check Automating with Generative Extraction.
Preview LLM
- Leverages 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.
- Higher amount of latency compared to UiPath Helix Extractor for Comms LLM.
- 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 for Comms LLM is enabled by default. To enable the Preview LLM, make sure you enable Use generative AI features and Use preview generative extraction model.
If the Use preview generative extraction model toggle is turned off, it means that you are using the UiPath Helix Extractor for Comms LLM.
Having the Use generative AI features and Use preview 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 the UiPath Helix Extractor for Comms LLM.
- If the extractions extract correctly, continue to train the extractions using the UiPath Helix Extractor for Comms LLM. If not, due to high number of fields or large tables in each message, switch to the Preview LLM. To determine if your extractions predict correctly, 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 the UiPath Helix Extractor for Comms LLM. If any data points don't extract as expected with the UiPath Helix Extractor for Comms LLM:
- Pin the current model version by going to models and select pin 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. Your UiPath Representative will work directly with the Communications Mining™ product team to investigate and implement improvements.
- If you use the Preview LLM, continue to train your model the same way you trained the UiPath Helix Extractor for Comms LLM. Go through it, and provide correct examples for each of your extractions.
Note:
When you select the Preview model, only that model will be trained for Generative Extraction—without simultaneously training a UiPath Helix Extractor for Comms model. This results in faster training and validation for Preview model users. If you switch to UiPath Helix Extractor for Comms, predictions will continue to be provided by the Preview LLM until a UiPath Helix Extractor for Comms model version has been trained, and vice versa.