Skip to main content

Glossary

TermDescription
AI RecommendationA feature that suggests optimal settings for model compression or fine-tuning based on user requirements and model characteristics.
APIApplication Programming Interface; a set of protocols and tools for building software applications.
App DesignA no-code/low-code platform within LLMOps for creating LLM-powered workflows and applications.
Bias CheckA validator in the Monitoring feature that ensures LLM outputs do not contain biased language towards specific demographics.
CompressionThe process of reducing the size of an LLM while maintaining its performance capabilities.
Data Source ManagerA component in LLMOps for managing and organizing datasets used for fine-tuning.
Fine-TuningThe process of adapting a pre-trained language model to specific tasks or domains using additional training data.
Gibberish TextA validator that checks if the LLM-generated text is coherent and makes sense.
Governance ConfigurationSettings and rules applied to ensure LLM usage complies with organizational policies and regulations.
LLMLarge Language Model; an AI model trained on vast amounts of text data to understand and generate human-like text.
LLM TracingA feature that records and displays detailed information about each LLM interaction, including prompts, responses, and performance metrics.
LoRALow-Rank Adaptation; a fine-tuning technique that adapts only a small set of parameters, reducing computational requirements.
Model QuantizationA technique to reduce the precision of model weights, decreasing model size and potentially improving inference speed.
Monitoring DashboardA visual interface displaying real-time insights into LLM usage, performance, and trends.
PIIPersonally Identifiable Information; data that could potentially identify a specific individual.
PromptThe input text given to an LLM to elicit a specific type of response or completion.
QLoRAQuantized LoRA; a combination of quantization and LoRA techniques for efficient fine-tuning.
RAGRetrieval-Augmented Generation; a technique that combines information retrieval with text generation to produce more accurate and informative responses.
Response TimeThe time taken by an LLM to generate a response to a given prompt.
Saliency CheckA validator that ensures an LLM-generated summary covers the main topics present in the source document.
Sensitive TopicA validator that checks if the input or output contains potentially sensitive or controversial subjects.
TokenThe basic unit of text that an LLM processes. A token can be a word, part of a word, or a single character, depending on the model's tokenization scheme.
Validation FlowA customizable sequence of checks in the Monitoring feature to ensure LLM outputs meet safety, relevance, and quality standards.
Vector StoreA database optimized for storing and retrieving high-dimensional vectors, often used in RAG systems for efficient similarity search.
Wiki ProvenanceA validator that checks if LLM-generated text contains hallucinations by comparing it with relevant Wikipedia information.