PostgresML provides a simple interface to generate embeddings from text in your database. You can use the[`pgml.embed`](https://postgresml.org/docs/guides/transformers/embeddings) function to generate embeddings for a column of text. The function takes a transformer name and a text value. The transformer will automatically be downloaded and cached on your connection process for reuse. You can see a list of potential good candidate models to generate embeddings on the[Massive Text Embedding Benchmark leaderboard](https://huggingface.co/spaces/mteb/leaderboard).

PostgresML provides a simple interface to generate embeddings from text in your database. You can use the[`pgml.embed`](https://postgresml.org/docs/open-source/pgml/guides/transformers/embeddings) function to generate embeddings for a column of text. The function takes a transformer name and a text value. The transformer will automatically be downloaded and cached on your connection process for reuse. You can see a list of potential good candidate models to generate embeddings on the[Massive Text Embedding Benchmark leaderboard](https://huggingface.co/spaces/mteb/leaderboard).

Since our corpus of documents (movie reviews) are all relatively short and similar in style, we don't need a large model.[`Alibaba-NLP/gte-base-en-v1.5`](https://huggingface.co/Alibaba-NLP/gte-base-en-v1.5) will be a good first attempt. The great thing about PostgresML is you can always regenerate your embeddings later to experiment with different embedding models.

!!!

We also have asynchronous versions of the create and`create_stream` functions relatively named`create_async` and`create_stream_async`. Checkout[our documentation](https://postgresml.org/docs/guides/opensourceai) for a complete guide of the open-source AI SDK including guides on how to specify custom models.

We also have asynchronous versions of the create and`create_stream` functions relatively named`create_async` and`create_stream_async`. Checkout[our documentation](https://postgresml.org/docs/open-source/pgml/guides/opensourceai) for a complete guide of the open-source AI SDK including guides on how to specify custom models.

PostgresML is free and open source. To run the above examples yourself[create an account](https://postgresml.org/signup), install korvus, and get running!

!!!

Other distance functions have similar formulas and provide convenient operators to use as well. It may be worth testing other operators and to see which performs better for your use case. For more information on the other distance functions, take a look at our[Embeddings guide](https://postgresml.org/docs/guides/embeddings/vector-similarity).

Other distance functions have similar formulas and provide convenient operators to use as well. It may be worth testing other operators and to see which performs better for your use case. For more information on the other distance functions, take a look at our[Embeddings guide](https://postgresml.org/docs/open-source/pgml/guides/embeddings/vector-similarity).

Going back to our search example, we can compute the cosine distance between our query embedding and our documents:

*[Embeddings](guides/embeddings/README.md)

*[In-database Generation](guides/embeddings/in-database-generation.md)

*[Dimensionality Reduction](guides/embeddings/dimensionality-reduction.md)

*[Aggregation](guides/embeddings/vector-aggregation.md)

*[Similarity](guides/embeddings/vector-similarity.md)

*[Normalization](guides/embeddings/vector-normalization.md)

*[Search](guides/improve-search-results-with-machine-learning.md)

*[Chatbots](guides/chatbots/README.md)

*[Embeddings](open-source/pgml/guides/embeddings/README.md)

*[In-database Generation](open-source/pgml/guides/embeddings/in-database-generation.md)

*[Dimensionality Reduction](open-source/pgml/guides/embeddings/dimensionality-reduction.md)

*[Aggregation](open-source/pgml/guides/embeddings/vector-aggregation.md)

*[Similarity](open-source/pgml/guides/embeddings/vector-similarity.md)

*[Normalization](open-source/pgml/guides/embeddings/vector-normalization.md)

*[Search](open-source/pgml/guides/improve-search-results-with-machine-learning.md)

*[Chatbots](open-source/pgml/guides/chatbots/README.md)

*[Example Application](use-cases/chatbots.md)

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

*[Unified RAG](guides/unified-rag.md)

*[OpenSourceAI](guides/opensourceai.md)

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

*[Vector database](guides/vector-database.md)

*[Supervised Learning](open-source/pgml/guides/supervised-learning.md)

*[Unified RAG](open-source/pgml/guides/unified-rag.md)

*[OpenSourceAI](open-source/pgml/guides/opensourceai.md)

*[Natural Language Processing](open-source/pgml/guides/natural-language-processing.md)

*[Vector database](open-source/pgml/guides/vector-database.md)

embedding_1= embed("King")# embed returns something like [0.11, -0.32, 0.46, ...]

<figure><imgsrc="../../.gitbook/assets/embedding_king.png"alt=""><figcaption><p>The flow of word -> token -> embedding</p></figcaption></figure>

<figure><imgsrc="../../../../.gitbook/assets/embedding_king.png"alt=""><figcaption><p>The flow of word -> token -> embedding</p></figcaption></figure>

`Embeddings` aren't limited to words, we have models that can embed entire sentences.

<figure><imgsrc="../../.gitbook/assets/embeddings_tokens.png"alt=""><figcaption><p>The flow of sentence -> tokens -> embedding</p></figcaption></figure>

<figure><imgsrc="../../../../.gitbook/assets/embeddings_tokens.png"alt=""><figcaption><p>The flow of sentence -> tokens -> embedding</p></figcaption></figure>

Why do we care about`embeddings`?`Embeddings` have a very interesting property. Words and sentences that have close[semantic similarity](https://en.wikipedia.org/wiki/Semantic\_similarity) sit closer to one another in vector space than words and sentences that do not have close semantic similarity.

Thereis a lot going onwith this, let's check out this diagram and step through it.

<figure><imgsrc="../../.gitbook/assets/chatbot_flow.png"alt=""><figcaption><p>The flow of taking a document, splitting it into chunks, embedding those chunks,and then retrieving a chunk based off of a users query</p></figcaption></figure>

<figure><imgsrc="../../../../.gitbook/assets/chatbot_flow.png"alt=""><figcaption><p>The flow of taking a document, splitting it into chunks, embedding those chunks,and then retrieving a chunk based off of a users query</p></figcaption></figure>

Step1: We take the documentand split it into chunks. Chunks are typically a paragraphor twoin size. There are many ways to split documents into chunks,for more information check out [this guide](https://www.pinecone.io/learn/chunking-strategies/).

!!! warning

Other cloud providers claim to offer embeddings "inside the database", but[benchmarks](../../resources/benchmarks/mindsdb-vs-postgresml.md) show that they are orders of magnitude slower than PostgresML. The reason is they don't actually run inside the database with hardware acceleration. They are thin wrapper functions that make network calls to remote service providers. PostgresML is the only cloud that puts GPU hardware in the database for full acceleration, and it shows.

Other cloud providers claim to offer embeddings "inside the database", but[benchmarks](../../../../resources/benchmarks/mindsdb-vs-postgresml.md) show that they are orders of magnitude slower than PostgresML. The reason is they don't actually run inside the database with hardware acceleration. They are thin wrapper functions that make network calls to remote service providers. PostgresML is the only cloud that puts GPU hardware in the database for full acceleration, and it shows.

!!!