sql_agent.py

from dotenv import load_dotenv
from langchain_community.agent_toolkits import create_sql_agent
from langchain_community.vectorstores import FAISS
from langchain_core.example_selectors import SemanticSimilarityExampleSelector
from langchain_core.prompts import ChatPromptTemplate, FewShotPromptTemplate, MessagesPlaceholder, PromptTemplate, SystemMessagePromptTemplate
from langchain_openai import OpenAIEmbeddings
from langchain_openai import ChatOpenAI
from langchain_community.utilities import SQLDatabase
from prompt_templates import few_shot_examples, system_prefix


# Load the .env file
load_dotenv()

# Initialize the SQL database
db = SQLDatabase.from_uri("sqlite:///Chinook.db")

# Check the database connection
print(db.dialect)
print(db.get_usable_table_names())
db.run("SELECT * FROM Artist LIMIT 10;")

# Initialize the LLM
llm = ChatOpenAI(model="gpt-4o", temperature=0)


# Example selector will dynamically select examples based on the input question
example_selector = SemanticSimilarityExampleSelector.from_examples(
    few_shot_examples,
    OpenAIEmbeddings(),
    FAISS,
    k=5,
    input_keys=["input"],
)

# Few-shot prompt template
few_shot_prompt = FewShotPromptTemplate(
    example_selector=example_selector,
    example_prompt=PromptTemplate.from_template(
        "User input: {input}\nSQL query: {query}"
    ),
    input_variables=["input", "dialect", "top_k"],
    prefix=system_prefix,
    suffix="",
)

# Full prompt template
full_prompt = ChatPromptTemplate.from_messages(
    [
        SystemMessagePromptTemplate(prompt=few_shot_prompt),
        ("human", "{input}"),
        MessagesPlaceholder("agent_scratchpad"),
    ]
)

# Create the SQL agent
SQLAgent = create_sql_agent(
    llm=llm,
    db=db,
    prompt=full_prompt,
    verbose=True,
    agent_type="openai-tools",
)