Using GPT 4 or GPT 3.5 with SQL Database Agent throws OutputParserException: Could not parse LLM output:

Question

I am using the SQL Database Agent to query a postgres database. I want to use gpt 4 or gpt 3.5 models in the OpenAI llm passed to the agent, but it says I must use ChatOpenAI. Using ChatOpenAI throws parsing errors.

The reason for wanting to switch models is reduced cost, better performance and most importantly - token limit. The max token size is 4k for 'text-davinci-003' and I need at least double that.

Here is my code

from langchain.agents.agent_toolkits import SQLDatabaseToolkit
from langchain.sql_database import SQLDatabase
from langchain.agents import create_sql_agent
from langchain.llms import OpenAI
from langchain.chat_models import ChatOpenAI
import os

os.environ["OPENAI_API_KEY"] = ""
db = SQLDatabase.from_uri(
    "postgresql://<my-db-uri>",
    engine_args={
        "connect_args": {"sslmode": "require"},
    },
)

llm = ChatOpenAI(model_name="gpt-3.5-turbo")
toolkit = SQLDatabaseToolkit(db=db, llm=llm)

agent_executor = create_sql_agent(
    llm=llm,
    toolkit=toolkit,
    verbose=True,
)

agent_executor.run("list the tables in the db. Give the answer in a table json format.")

When I do, it throws an error in the chain midway saying

> Entering new AgentExecutor chain...
Traceback (most recent call last):
  File "/home/ramlah/Documents/projects/langchain-test/sql.py", line 96, in <module>
    agent_executor.run("list the tables in the db. Give the answer in a table json format.")
  File "/home/ramlah/Documents/projects/langchain/langchain/chains/base.py", line 236, in run
    return self(args[0], callbacks=callbacks)[self.output_keys[0]]
  File "/home/ramlah/Documents/projects/langchain/langchain/chains/base.py", line 140, in __call__
    raise e
  File "/home/ramlah/Documents/projects/langchain/langchain/chains/base.py", line 134, in __call__
    self._call(inputs, run_manager=run_manager)
  File "/home/ramlah/Documents/projects/langchain/langchain/agents/agent.py", line 953, in _call
    next_step_output = self._take_next_step(
  File "/home/ramlah/Documents/projects/langchain/langchain/agents/agent.py", line 773, in _take_next_step
    raise e
  File "/home/ramlah/Documents/projects/langchain/langchain/agents/agent.py", line 762, in _take_next_step
    output = self.agent.plan(
  File "/home/ramlah/Documents/projects/langchain/langchain/agents/agent.py", line 444, in plan
    return self.output_parser.parse(full_output)
  File "/home/ramlah/Documents/projects/langchain/langchain/agents/mrkl/output_parser.py", line 51, in parse
    raise OutputParserException(
langchain.schema.OutputParserException: Could not parse LLM output: `Action: list_tables_sql_db, ''`

Please help. Thanks!

Update The recent updates to langchain version 0.0.215 seem to have fixed this issue, for me at least.

Pasadis

Answer 1

The previously accepted answer never seemed to work for me. However, as per a Github thread on the same issue, the way to handle this is like so.

agent_executor = create_sql_agent(llm,
                                   db=db,
                                   agent_type="openai-tools",
                                   agent_executor_kwargs={'handle_parsing_errors':True},
                               verbose=True)

Transfinite

This seems to be the way to handle it according to the latest version – Pasadis

Answer 2

pass handle_parsing_errors=True in create_sql_agent function most of the times it helps the code to get through the parsing error

Beecher

I have done that but despite that not a single query is working. – Transfinite