Functions reference

Reference for AIDB standalone SQL functions that transform data directly in queries, without requiring a pipeline. For guide-style documentation and usage examples, see SQL functions .

For AI inference functions (encode_text , decode_text , rerank_text , and related), see Inference functions .

---

aidb.chunk_text

Divides a text string into smaller, semantically coherent segments.

Parameters

Parameter	Type	Description
input	TEXT	The text to chunk.
options	JSONB	Chunking configuration (see below).

Options

Key	Type	Default	Description
desired_length	integer	Required	Target segment size. Acts as a strict upper limit if max_length is omitted.
max_length	integer	NULL	Upper bound for chunk size. Chunks extend past desired_length only to preserve semantic boundaries.
overlap_length	integer	0	Amount of content to repeat between consecutive chunks, to preserve cross-boundary context.
strategy	text	'chars'	Chunking unit: 'chars' (character-based) or 'words' (word-based). Determines the unit for desired_length, max_length, and overlap_length.

Returns

Column	Type	Description
part_id	integer	Zero-based segment index.
chunk	text	The text segment.

Example

SELECT * FROM aidb.chunk_text(
    input   => Long text here...,
    options => {"desired_length": 120, "max_length": 150}
);

---

aidb.parse_html

Extracts readable text from an HTML string, stripping tags while preserving structure.

Parameters

Parameter	Type	Description
html	TEXT	The HTML string to parse.
options	JSONB	Parsing configuration (see below).

Options

Key	Type	Default	Description
method	text	'StructuredPlaintext'	Parsing method: 'StructuredPlaintext' (plain text extraction) or 'StructuredMarkdown' (Markdown-like output that retains headers and lists).

Returns

TEXT — the extracted text content.

Example

SELECT aidb.parse_html(
    html    => <h1>Hello</h1><p>World</p>,
    options => {"method": "StructuredPlaintext"}
);

---

aidb.parse_pdf

Extracts text from binary PDF data. Returns one row per page.

Parameters

Parameter	Type	Description
bytes	BYTEA	Raw PDF binary data.
options	JSONB	Parsing configuration (see below).

Options

Key	Type	Default	Description
method	text	'Structured'	Parsing method. Currently 'Structured' (spec-based text block extraction).
allow_partial_parsing	boolean	true	When true, continues parsing when errors are encountered on individual pages, returning as much data as possible.

Returns

Column	Type	Description
part_id	integer	Page index (zero-based) from which the text was extracted.
text	text	Extracted text for that page.

Example

SELECT * FROM aidb.parse_pdf(
    bytes   => pg_read_binary_file(/path/to/doc.pdf)::BYTEA,
    options => {"allow_partial_parsing": true}
);

---

aidb.perform_ocr

Extracts text from image data using a registered OCR-capable model.

Parameters

Parameter	Type	Description
input	BYTEA	Raw binary image data.
options	JSONB	OCR configuration (see below).

Options

Key	Type	Description
model	text	Name of a registered OCR-capable model (for example, one using the nim_ocr provider).

Returns

Column	Type	Description
part_id	integer	Text block index. A single image may produce multiple rows if the provider returns multiple text segments.
text	text	Extracted text for that block.

Example

SELECT * FROM aidb.perform_ocr(
    input   => pg_read_binary_file(/path/to/image.png)::BYTEA,
    options => {"model": "my_ocr_model"}
);

---

aidb.summarize_text

Generates a concise summary of a text string using a registered language model.

Parameters

Parameter	Type	Description
input	TEXT	The text to summarize.
options	JSONB	Summarization configuration (see below).

Options

Key	Type	Default	Description
model	text	Required	Name of a registered model that supports decode_text.
prompt	text	(standard prompt)	Custom instruction to guide the summary style, for example 'Summarize for a 5th grader'.
chunk_config	JSONB	NULL	Chunking configuration to apply before summarization when input exceeds the model's context window. Accepts the same keys as aidb.chunk_text options.
strategy	text	'append'	Summarization strategy: 'append' (summarize each chunk independently and concatenate) or 'reduce' (iteratively summarize until the desired length is reached).
reduction_factor	integer	3	Used with the 'reduce' strategy. Controls how aggressively each iteration reduces the text.

Returns

TEXT — the generated summary.

Example

SELECT aidb.summarize_text(
    input   => Long article text here...,
    options => {"model": "my_t5_model"}
);

---

aidb.summarize_text_aggregate

Aggregate version of aidb.summarize_text . Accumulates text from all rows in each group, then sends the combined result to the LLM for summarization. Returns one summary per GROUP BY group. Empty and NULL rows are skipped.

Parameters

Parameter	Type	Required	Description
input	TEXT	Yes	Text column from each row. Empty/NULL rows are skipped.
options	JSON	Yes	Configuration object built with aidb.summarize_text_config(). Must contain model at minimum.

Options

Accepts the same options as aidb.summarize_text (see above). Note that options is required for the aggregate, not optional.

Returns

TEXT — the summary for the group.

Usage

SELECT category,
       aidb.summarize_text_aggregate(
           text_column,
           aidb.summarize_text_config(my_t5_model)::json ORDER BY id
       ) AS summary
FROM my_table
GROUP BY category;

---

Parameter defaults quick reference

Function	Parameter	SQL default	Runtime default
summarize_text	options	'{}'	Must include model
summarize_text_aggregate	input	— (required)	—
summarize_text_aggregate	options	— (required)	—
summarize_text_config	model	— (required)	—
summarize_text_config	chunk_config	NULL	No chunking
summarize_text_config	prompt	NULL	Standard summarize prompt
summarize_text_config	strategy	NULL	'append'
summarize_text_config	reduction_factor	NULL	3
summarize_text_config	inference_config	NULL	Provider defaults
chunk_text_config	desired_length	— (required)	—
chunk_text_config	max_length	NULL	Same as desired_length
chunk_text_config	overlap_length	NULL	0
chunk_text_config	strategy	NULL	'chars'