使用ChatOpenAI调用SQL Database Agent触发OutputParserException求助

问题描述 #

在使用LangChain的SQL Database Agent查询PostgreSQL数据库时，尝试将底层大模型从text-davinci-003切换为ChatOpenAI（gpt-3.5-turbo或GPT-4），核心诉求包括：

• 降低模型调用成本
• 提升响应性能
• 解决text-davinci-003仅4k token的容量限制，需要至少两倍的token处理能力

但切换后执行Agent时触发解析错误，报错提示无法识别LLM输出格式。

代码示例 #

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.")

错误信息 #

> 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, ''`

解决方案 #

LangChain版本0.0.215的更新已修复ChatOpenAI与SQL Database Agent之间的输出解析兼容问题，升级到该版本及以上即可解决此错误。

升级命令 #

pip install --upgrade langchain==0.0.215

若需使用最新功能，可去掉版本号直接执行：

pip install --upgrade langchain

内容的提问来源于stack exchange，提问作者RamlahAziz