Quickstart¶

This notebook gives a quick overview of some Semlib functionality. For a more in-depth treatment, see the Examples.

Using a Jupyter notebook or an asyncio REPL (python3 -m asyncio), import the library and start a session:

In [1]:

from semlib import Bare, Session

session = Session()

from semlib import Bare, Session session = Session()

prompt is a basic wrapper around prompting an LLM and optionally getting structured output:

In [2]:

presidents: list[str] = await session.prompt(
    "Who were the 39th through 42nd presidents of the United States? Return the name only.",
    return_type=Bare(list[str]),
)
presidents

presidents: list[str] = await session.prompt( "Who were the 39th through 42nd presidents of the United States? Return the name only.", return_type=Bare(list[str]), ) presidents

Out[2]:

['Jimmy Carter', 'Ronald Reagan', 'George H. W. Bush', 'Bill Clinton']

sort sorts a list of items based on a ranking criterion:

In [3]:

await session.sort(presidents, by="right-leaning")

await session.sort(presidents, by="right-leaning")

Out[3]:

['Jimmy Carter', 'Bill Clinton', 'George H. W. Bush', 'Ronald Reagan']

filter filters a list of items based on a criterion:

In [4]:

await session.filter(presidents, by="former actor", negate=True)

await session.filter(presidents, by="former actor", negate=True)

Out[4]:

['Jimmy Carter', 'George H. W. Bush', 'Bill Clinton']

map transforms a list of items based on a prompt template:

In [5]:

ages: list[int] = await session.map(
    presidents,
    template="How old was {} when he took office?",
    return_type=Bare(int),
)
ages

ages: list[int] = await session.map( presidents, template="How old was {} when he took office?", return_type=Bare(int), ) ages

Out[5]:

[52, 69, 64, 46]

total_cost returns the total cost of all LLM calls made in the session:

In [6]:

f"${session.total_cost():.3f}"

f"${session.total_cost():.3f}"

Out[6]:

'$0.007'

To see the full list of supported functionality, take a look at the methods defined on Session or take a look at the examples.