*[Tuning vector recall while generating query embeddings in the database](use-cases/embeddings/tuning-vector-recall-while-generating-query-embeddings-in-the-database.md)

*[Personalize embedding results with application data in your database](use-cases/embeddings/personalize-embedding-results-with-application-data-in-your-database.md)

*[Supervised Learning](use-cases/supervised-learning.md)

*[Natural Language Processing](use-cases/natural-language-processing/README.md)

*[Text Classification](use-cases/natural-language-processing/text-classification.md)

*[Zero-shot Classification](use-cases/natural-language-processing/zero-shot-classification.md)

*[Token Classification](use-cases/natural-language-processing/token-classification.md)

*[Question Answering](use-cases/natural-language-processing/question-answering.md)

*[Translation](use-cases/natural-language-processing/translation.md)

*[Summarization](use-cases/natural-language-processing/summarization.md)

*[Text Generation](use-cases/natural-language-processing/text-generation.md)

*[Text-to-Text Generation](use-cases/natural-language-processing/text-to-text-generation.md)

*[Fill Mask](use-cases/natural-language-processing/fill-mask.md)

*[Natural Language Processing](use-cases/natural-language-processing.md)

*[Fraud Detection](use-cases/fraud-detection.md)

*[Recommendation Engine](use-cases/recommendation-engine.md)

*[Time-series Forecasting](use-cases/time-series-forecasting.md)

* Access 1000s of state-of-the-art language models like GPT-2, GPT-J, GPT-Neo from:hugs: HuggingFace model hub

* Fine tune large language models (LLMs) on your own text data for different tasks

* Use your existing PostgreSQL database as a vector database by generating embeddings from text stored in the database.

See[pgml.transform](../introduction/apis/sql-extensions/pgml.transform/"mention") for examples of using transformers or[pgml.tune.md](../introduction/apis/sql-extensions/pgml.tune.md"mention") for fine tuning.