Embedding Metrics
=================

These metrics are embedding-based that are used to evaluate the quality of the output of the LLM.
An embedding is a relatively low-dimensional space that captures the semantic meaning of the input text.
These embeddings are typically learned using unsupervised learning techniques such as Word2Vec, GloVe, or FastText.

As they embrace contextual information, embeddings are widely used in various NLP tasks such as text classification, sentiment analysis, and machine translation.
They can also be used to evaluate the quality of the output of the LLM, as they capture:

* The semantic meaning of the input text
* The relationships between words (grammar rules)

.. automodule:: saga_llm_evaluation.helpers.embedding_metrics
   :members:
   :undoc-members:
   :show-inheritance: