*[SQL extension](api/sql-extension/README.md)

*[pgml.embed()](api/sql-extension/pgml.embed.md)

*[pgml.transform()](api/sql-extension/pgml.transform/README.md)

*[FillMask](api/sql-extension/pgml.transform/fill-mask.md)

*[QuestionAnswering](api/sql-extension/pgml.transform/question-answering.md)

*[Fill-Mask](api/sql-extension/pgml.transform/fill-mask.md)

*[Questionanswering](api/sql-extension/pgml.transform/question-answering.md)

*[Summarization](api/sql-extension/pgml.transform/summarization.md)

*[TextClassification](api/sql-extension/pgml.transform/text-classification.md)

*[Textclassification](api/sql-extension/pgml.transform/text-classification.md)

*[Text Generation](api/sql-extension/pgml.transform/text-generation.md)

*[Text-to-Text Generation](api/sql-extension/pgml.transform/text-to-text-generation.md)

*[Token Classification](api/sql-extension/pgml.transform/token-classification.md)

|----------|-------------|---------|

| transformer| The name of a Hugging Face embedding model.|`intfloat/e5-large-v2`|

| text| The text to embed. This can be a string or the name of a column from a PostgreSQL table.|`'I am your father, Luke'`|

| kwargs| Additional arguments that are passed to the model.||

| kwargs| Additional arguments that are passed to the model during inference.||

{% endtab %}

{% endtabs %}

SQL functions can be used as part of a query to insert, update, or even automatically generate column values of any table:

{% endtabs %}

This query will return the quote with the most similar meaning to`'Feel the force!'` by generating an embedding of that quote and comparing it to all other embeddings in the table, using vector cosine similarity as the measure of distance.

First time`pgml.embed()` is called with a new model, it is downloaded from Hugging Face and saved in the cache directory. Subsequent calls will use the cached model, which is faster, and if the connection to the database is kept open, the model will be reused across multiple queries without being unloaded from memory.

If a GPU is available, the model will be automatically loaded onto the GPU and the embedding generation will be even faster.

The task-based API automatically chooses a modelto usebased on the task:

The task-based API automatically chooses a model based on the task:

| Argument| Description| Example|

|----------|-------------|---------|

| task| The name of a natural language processing task.|`text-generation`|

| args| Additional kwargs to pass to the pipeline.|`{"max_new_tokens": 50}`|

| inputs| Array of prompts to pass to the model for inference.|`['Once upon a time...']`|

| Argument| Description| Example| Required|

|----------|-------------|---------|----------|

| task| The name of a natural language processing task.|`'text-generation'`| Required|

| args| Additional kwargs to pass to the pipeline.|`'{"max_new_tokens": 50}'::JSONB`| Optional|

| inputs| Array of prompts to pass to the model for inference.Each prompt is evaluated independently and a separate result is returned.|`ARRAY['Once upon a time...']`| Required|

{% tabs %}

{% tab title="SQL" %}

{% tabs %}

{% tab title="Text generation" %}

{% endtab %}

{% tab title="Translation" %}

The model-based API requires the name of the model and the task, passed as a JSON object, which allows it to be more generic:

The model-based API requires the name of the model and the task, passed as a JSON object. This allows it to be more generic and support more models:

| Argument| Description| Example|

|----------|-------------|---------|

| task| Model configuration, including name and task.|`{"task": "text-generation", "model": "mistralai/Mixtral-8x7B-v0.1"}`|

| args| Additional kwargs to pass to the pipeline.|`{"max_new_tokens": 50}`|

| inputs| Array of prompts to pass to the model for inference.|`['Once upon a time...']`|

<tableclass="table-sm table">

<thead>

</thead>

<tbody>

</table>

{% tabs %}

{% tab title="SQL" %}

{% tab title="PostgresMLSQL" %}

|[Token classification](token-classification)|`token-classification`| Classify tokens in a text.|

|[Translation](translation)|`translation`| Translate text from one language to another.|

|[Zero-shot classification](zero-shot-classification)|`zero-shot-classification`| Classify a text without training data.|

| Conversational|`conversational`| Engage in a conversation with the model, e.g. chatbot.|

Much like`pgml.embed()`, the models used in`pgml.transform()` are downloaded from Hugging Face and cached locally. If the connection to the database is kept open, the model remains in memory, which allows for faster inference on subsequent calls. If you want to free up memory, you can close the connection.

description:Task to fill words in a sentence that are hidden

Fill-mask refers to a task where certain words in a sentence are hidden or "masked", and the objective is to predict what words should fill in those masked positions. Such models are valuable when we want to gain statistical insights about the language used to train the model.

Fill-Mask is a task where certain words in a sentence are hidden or "masked", and the objective for the model is to predict what words should fill in those masked positions. Such models are valuable when we want to gain statistical insights about the language used to train the model.

{% tabs %}

{% tab title="SQL" %}

SELECTpgml.transform(

task=>'{

}'::JSONB,

inputs=> ARRAY[

]

)AS answer;

_Result_

{% endtab %}

{% tab title="Result" %}

[

{"score":0.679,"token":812,"sequence":"Paris is the capital of France.","token_str":" capital"},

{"score":0.051,"token":32357,"sequence":"Paris is the birthplace of France.","token_str":" birthplace"},

{"score":0.038,"token":1144,"sequence":"Paris is the heart of France.","token_str":" heart"},

{"score":0.024,"token":29778,"sequence":"Paris is the envy of France.","token_str":" envy"},

{"score":0.022,"token":1867,"sequence":"Paris is the Capital of France.","token_str":" Capital"}]

{

"score":0.6811484098434448,

"token":812,

"sequence":"Paris is the capital of France.",

"token_str":" capital"

},

{

"score":0.050908513367176056,

"token":32357,

"sequence":"Paris is the birthplace of France.",

"token_str":" birthplace"

},

{

"score":0.03812871500849724,

"token":1144,

"sequence":"Paris is the heart of France.",

"token_str":" heart"

},

{

"score":0.024047480896115303,

"token":29778,

"sequence":"Paris is the envy of France.",

"token_str":" envy"

},

{

"score":0.022767696529626846,

"token":1867,

"sequence":"Paris is the Capital of France.",

"token_str":" Capital"

}

]

{% endtab %}

{% endtabs %}

-[Hugging Face documentation](https://huggingface.co/tasks/fill-mask)

description:Retrieve the answer to a question from a given text

description:Retrieve the answer to a question from a given text.

Question Answering models are designed to retrieve the answer to a question from a given text, which can be particularly useful for searching for information within a document. It's worth noting that some question answering models are capable of generating answers even without any contextual information.

Question answering models are designed to retrieve the answer to a question from a given text, which can be particularly useful for searching for information within a document. It's worth noting that some question answering models are capable of generating answers even without any contextual information.

{% tabs %}

{% tab title="SQL" %}

SELECTpgml.transform(

)AS answer;

_Result_

{% endtab %}

{% tab title="Result" %}

{

"answer":"İstanbul"

}

{% endtab %}

{% endtabs %}

-[Hugging Face documentation](https://huggingface.co/tasks/question-answering)

description:Task of creating a condensed version of a document

description:Task of creating a condensed version of a document.

Summarization involves creating a condensed version of a document that includes the important information while reducing its length. Different models can be used for this task, with some models extracting the most relevant text from the original document, while other models generate completely new text that captures the essence of the original content.

{% tabs %}

{% tab title="SQL" %}

SELECTpgml.transform(

task=>'{"task": "summarization",

task=>'{

}'::JSONB,

inputs=> array[

]

inputs=> array[

]

);

_Result_

{% endtab %}

{% tab title="Result" %}

[

{

"summary_text":"Paris is the capital and most populous cityofFrance, with an estimated population of 2,175,601 residents as of 2018 . The cityis the centre and seat of government of the region and province ofÎle-de-France, or Paris Region . Paris Regionhas an estimated 18 percent of the population of France as of 2017."

}

{

"summary_text":"The CityofParisis the centre and seat of government of the region and province ofle-de-France, or Paris Region, whichhas an estimatedpopulation of 12,174,880, or about18 percent of the population of France as of 2017."

}

]

You can control the length of summary\_text by passing`min_length` and`max_length` as arguments to the SQL query.

{% endtab %}

{% endtabs %}

SELECTpgml.transform(

task=>'{"task": "summarization",

}'::JSONB,

inputs=> array[

],

args=>'{

}'::JSONB

);

[

{

"summary_text":" Paris is the capital and most populous city of France, with an estimated population of 2,175,601 residents as of 2018 . City of Paris is centre and seat of government of the region and province of Île-de-France, or Paris Region, which has an estimated 12,174,880, or about 18 percent"

}

]

-[Hugging Face documentation](https://huggingface.co/tasks/summarization)

-[google/pegasus-xsum](https://huggingface.co/google/pegasus-xsum)