AI inference functions

AI inference functions#

AIDB provides a set of SQL functions for performing AI inference directly in queries. These functions let you encode data into vector representations, generate text with language models, and control inference behavior — without setting up a pipeline.

aidb.encode_text()#

Encodes a single text string into a vector using a registered embedding model.

SELECT aidb.encode_text(model_name => my_embedder, input => What is pgvector?);

__OUTPUT__
                         encode_text
- -------------------------------------------------------------
 [0.021,-0.043,0.117, ...]
(1 row)

For the full parameter reference, see Models reference .

aidb.encode_text_batch()#

Encodes multiple text strings into vectors in a single batched request. More efficient than calling encode_text() in a loop when processing many inputs.

SELECT * FROM aidb.encode_text_batch(
    model_name => my_model_name,
    input      => ARRAY[What is pgvector?, How does RAG work?, Explain embeddings.]
);

__OUTPUT__
  encode_text_batch
- ------------------------
 [0.021,-0.043,0.117,...]
 [0.008, 0.091,-0.034,...]
 [0.055,-0.012, 0.076,...]
(3 rows)

For the full parameter reference, see Models reference .

aidb.encode_image()#

Encodes a single image into a vector using a registered multimodal embedding model (for example, a CLIP model).

SELECT aidb.encode_image(
    model_name => my_model_name,
    input      => pg_read_binary_file(/path/to/image.png)::BYTEA
);

__OUTPUT__
                         encode_image
- -------------------------------------------------------------
 [-0.012, 0.084, 0.031, ...]
(1 row)

For the full parameter reference, see Models reference .

aidb.generate_text()#

Generates text from a language model (LLM) given a prompt. This is the core function for LLM inference in AIDB.

SELECT aidb.generate_text(
    model_name => my_model_name,
    input      => Explain what a knowledge base is in two sentences.
);

__OUTPUT__
                                         generate_text
- -------------------------------------------------------------------------------------------
 A knowledge base is a structured repository of information used to answer queries or ...
(1 row)

To control generation behavior, pass an inference_config object built by aidb.inference_config() . Cast its JSONB result to json so the call matches the aidb.generate_text(TEXT, TEXT, json) signature:

SELECT aidb.generate_text(
    model_name       => my_model_name,
    input            => Summarize the following text: ...,
    inference_config => aidb.inference_config(
        system_prompt => You are a concise technical writer.,
        temperature   => 0.2,
        max_tokens    => 256
    )::json
);

For the full parameter reference, see Models reference .

aidb.generate_text_batch()#

Generates text responses for multiple prompts in a single batched request.

SELECT aidb.generate_text_batch(
    model_name => my_model_name,
    input  => ARRAY[
        What is a vector database?,
        What is retrieval-augmented generation?
    ]
);

__OUTPUT__
                           generate_text_batch
- ---------------------------------------------------------
 A vector database stores high-dimensional vectors ...
 Retrieval-augmented generation (RAG) combines a ...
(2 rows)

For the full parameter reference, see Models reference .

aidb.inference_config()#

Builds an inference configuration object to control language model generation behavior. Pass the result as the inference_config argument of aidb.generate_text() or aidb.generate_text_batch() , or as part of aidb.summarize_text_config() inside a pipeline step.

SELECT aidb.generate_text(
    model_name       => my_llm,
    input            => Write a haiku about PostgreSQL.,
    inference_config => aidb.inference_config(
        temperature => 0.9,
        max_tokens  => 64,
        seed        => 42
    )::json
);

For the full parameter reference, see Models reference .

!!!note To use these functions as steps inside a pipeline, see Pipeline steps .

Contents