Quickstart

import pandas as pd

from blendsql import BlendSQL
from blendsql.models import TransformersLLM, LiteLLM

USE_LOCAL_CONSTRAINED_MODEL = False

# Load model, either a local transformers model, or remote provider via LiteLLM
if USE_LOCAL_CONSTRAINED_MODEL:
    model = TransformersLLM(
        "meta-llama/Llama-3.2-3B-Instruct", config={"device_map": "auto"}
    )  # Local models enable BlendSQL's predicate-guided constrained decoding
else:
    model = LiteLLM("openai/gpt-4o-mini")

# Prepare our BlendSQL connection
bsql = BlendSQL(
    {
        "People": pd.DataFrame(
            {
                "Name": [
                    "George Washington",
                    "John Adams",
                    "Thomas Jefferson",
                    "James Madison",
                    "James Monroe",
                    "Alexander Hamilton",
                    "Sabrina Carpenter",
                    "Charli XCX",
                    "Elon Musk",
                    "Michelle Obama",
                    "Elvis Presley",
                ],
                "Known_For": [
                    "Established federal government, First U.S. President",
                    "XYZ Affair, Alien and Sedition Acts",
                    "Louisiana Purchase, Declaration of Independence",
                    "War of 1812, Constitution",
                    "Monroe Doctrine, Missouri Compromise",
                    "Created national bank, Federalist Papers",
                    "Nonsense, Emails I Cant Send, Mean Girls musical",
                    "Crash, How Im Feeling Now, Boom Clap",
                    "Tesla, SpaceX, Twitter/X acquisition",
                    "Lets Move campaign, Becoming memoir",
                    "14 Grammys, King of Rock n Roll",
                ],
            }
        ),
        "Eras": pd.DataFrame({"Years": ["1700-1800", "1800-1900", "1900-2000", "2000-Now"]}),
    },
    model=model,
    verbose=True,
)

smoothie = bsql.execute(
    """
    SELECT * FROM People P
    WHERE P.Name IN {{
        LLMQA('First 3 presidents of the U.S?', quantifier='{3}')
    }}
    """,
    infer_gen_constraints=True,
)

print(smoothie.df)
# ┌───────────────────┬───────────────────────────────────────────────────────┐
# │ Name              │ Known_For                                             │
# ├───────────────────┼───────────────────────────────────────────────────────┤
# │ George Washington │ Established federal government, First U.S. Preside... │
# │ John Adams        │ XYZ Affair, Alien and Sedition Acts                   │
# │ Thomas Jefferson  │ Louisiana Purchase, Declaration of Independence       │
# └───────────────────┴───────────────────────────────────────────────────────┘
print(smoothie.summary())
# ┌────────────┬──────────────────────┬─────────────────┬─────────────────────┐
# │   Time (s) │   # Generation Calls │   Prompt Tokens │   Completion Tokens │
# ├────────────┼──────────────────────┼─────────────────┼─────────────────────┤
# │    1.25158 │                    1 │             296 │                  16 │
# └────────────┴──────────────────────┴─────────────────┴─────────────────────┘


smoothie = bsql.execute(
    """
    SELECT GROUP_CONCAT(Name, ', ') AS 'Names',
    {{
        LLMMap(
            'In which time period was this person born?',
            'People::Name',
            options='Eras::Years'
        )
    }} AS Born
    FROM People
    GROUP BY Born
    """,
)

print(smoothie.df)
# ┌───────────────────────────────────────────────────────┬───────────┐
# │ Names                                                 │ Born      │
# ├───────────────────────────────────────────────────────┼───────────┤
# │ George Washington, John Adams, Thomas Jefferson, J... │ 1700-1800 │
# │ Sabrina Carpenter, Charli XCX, Elon Musk, Michelle... │ 2000-Now  │
# │ Elvis Presley                                         │ 1900-2000 │
# └───────────────────────────────────────────────────────┴───────────┘
print(smoothie.summary())
# ┌────────────┬──────────────────────┬─────────────────┬─────────────────────┐
# │   Time (s) │   # Generation Calls │   Prompt Tokens │   Completion Tokens │
# ├────────────┼──────────────────────┼─────────────────┼─────────────────────┤
# │    1.03858 │                    2 │             544 │                  75 │
# └────────────┴──────────────────────┴─────────────────┴─────────────────────┘

smoothie = bsql.execute("""
    SELECT {{
        LLMQA(
            'Describe BlendSQL in 50 words',
            (
                SELECT content[0:5000] AS "README"
                FROM read_text('https://raw.githubusercontent.com/parkervg/blendsql/main/README.md');
            )
        )
    }} AS answer
""")

print(smoothie.df)
# ┌─────────────────────────────────────────────────────┐
# │ answer                                              │
# ├─────────────────────────────────────────────────────┤
# │ BlendSQL is a Python library that combines SQL a... │
# └─────────────────────────────────────────────────────┘

print(smoothie.summary())

# ┌────────────┬──────────────────────┬─────────────────┬─────────────────────┐
# │   Time (s) │   # Generation Calls │   Prompt Tokens │   Completion Tokens │
# ├────────────┼──────────────────────┼─────────────────┼─────────────────────┤
# │    4.07617 │                    1 │            1921 │                  50 │
# └────────────┴──────────────────────┴─────────────────┴─────────────────────┘