create_sql_query_chain returns SQL queries with SQL markdowns

[SahasPunchihewa]

Checked other resources

• [X] I added a very descriptive title to this issue.
• [X] I searched the LangChain documentation with the integrated search.
• [X] I used the GitHub search to find a similar question and didn't find it.
• [X] I am sure that this is a bug in LangChain rather than my code.
• [X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

import os

from langchain.chains.sql_database.query import create_sql_query_chain from langchain_community.utilities import SQLDatabase from langchain_openai import ChatOpenAI

db_user = "" db_password = "" db_host = "" db_name = ""

db = SQLDatabase.from_uri(f"postgresql+psycopg2://{db_user}:{db_password}@{db_host}/{db_name}")

os.environ["OPENAI_API_KEY"] = ""

llm = ChatOpenAI(model="gpt-4o")

chain = create_sql_query_chain(llm, db) response = chain.invoke({"question": "How many users are there"}) print(response)

Error Message and Stack Trace (if applicable)

"```sql SELECT COUNT(*) AS "user_count" FROM "users";

### Description

I'm trying to create an NL2SQL model with Lang chain with Postgres SQL database.
So I've expected a SQL query as plain text as the output but it returns a Query with markdowns that will cause issues when executing it

### System Info

platform: windows
python: 3.12

[keenborder786]

Do the following:

chain = create_sql_query_chain(llm, db)
chain | RunnableLambda(lambda x:x.replace('```','').replace('sql',''))