Text Utils
Utility functions for text processing in Gen AI applications.
format_size(size_bytes)
Format a byte count for a size-limit message.
Megabytes are rounded up to one decimal place so a value just over a limit does not appear to equal that limit.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
size_bytes
|
int
|
Number of bytes. |
required |
Returns:
| Name | Type | Description |
|---|---|---|
str |
str
|
A megabyte value for sizes of at least 1 MB, or a byte count for smaller sizes. |
join_with_or(names)
Joins names into an English list that ends with "or".
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
names
|
Iterable[str]
|
The names to join. |
required |
Returns:
| Name | Type | Description |
|---|---|---|
str |
str
|
|
normalize_text(text)
Normalizes line endings to a single newline and strips outer whitespace.
CRLF and CR line endings are converted to a single newline. Internal whitespace, blank lines, and Unicode are preserved.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
text
|
str
|
The text to normalize. |
required |
Returns:
| Name | Type | Description |
|---|---|---|
str |
str
|
The normalized text. |