SQL Agent for Google Big Query

[hugoferrero]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

# google
import vertexai

# Alchemy
from sqlalchemy import *
from sqlalchemy.schema import *
 Langchain
from langchain.agents import create_sql_agent
from langchain.agents.agent_toolkits import SQLDatabaseToolkit
from langchain.sql_database import SQLDatabase




# BQ db
sqlalchemy_url = f'bigquery://{PROJECT_ID}/{dataset}'
db = SQLDatabase.from_uri(sqlalchemy_url)

# llm 
llm = VertexAI(
    model_name="text-bison@001",
    max_output_tokens=1024,
    temperature=0,
    top_p=0.8,
    top_k=40,
    verbose=True
             )
# SQL Agent

sql_agent = create_sql_agent(
llm=llm,
toolkit=SQLDatabaseToolkit(db=db, llm=llm),
verbose=True,
top_k=1000,
agent_type=AgentType.ZERO_SHOT_REACT_DESCRIPTION

Description

Is it possible to create an sql agent to query tables on Google BigQuery with the latests versions of langchain?. It was possible with older versions.

System Info

a

[dosubot[bot]]

🤖

Hey @hugoferrero! Great to see you back here, diving into the possibilities with LangChain and Google BigQuery. I hope all's been well on your side!

Yes, it is indeed possible to create an SQL agent in the latest version of LangChain to query tables on Google BigQuery. The function create_sql_agent you've used in your code is designed to construct a SQL agent from a language model and a toolkit or database.

To use Google BigQuery, you would need to create an instance of SQLDatabase that connects to your Google BigQuery database and pass it to the create_sql_agent function.

Here is an example of how you might do this:

from langchain_openai import ChatOpenAI
from langchain_community.agent_toolkits import create_sql_agent
from langchain_community.utilities import SQLDatabase

# Connect to your Google BigQuery database
db = SQLDatabase.from_uri("bigquery://project_id")

# Create a language model
llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)

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

Please note that you would need to replace "bigquery://project_id" with the actual connection string to your Google BigQuery database.

As for your question about the SQLDatabase.from_uri method supporting Google BigQuery, I wasn't able to find a definitive answer within the repository. However, given that the method is designed to create a database connection from a URI, it should theoretically support any database that can be connected to via a URI, including Google BigQuery.

If you encounter any issues or need further clarification, please provide more details so I can assist you better.

Sources

• libs/community/langchain_community/agent_toolkits/sql/base.py

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

[hugoferrero]

your example throws the following error:
NoSuchModuleError: Can't load plugin: sqlalchemy.dialects:bigquery

[wyljpn]

Point: in the uri, only need to pass project_id, don't pass dataset_name. Otherwise, it couldn't work well.
db = SQLDatabase.from_uri("bigquery://project_id")

[PeterChenTW]

I solved it by pip3 install pybigquery. you can have a try