composio.client.exceptions.ComposioClientError: Action CODEINTERPRETER_RUN_TERMINAL_CMD not found
Hi for the sql agent plotter, I am getting the following error when trying to run it recently. Was wondering what it was due to? Thanks!
5 Replies
can you run
pip install composio-core -U
pip install composio-framework -U
composio apps update
replace framework with whatever framework you are using
@snkewl let me know if this worked. Thanks.correct-apricot•4w ago
ValueError: Tool description exceeds maximum length of 1024 characters. Please shorten your description or move it to the prompt.
for the llama index plotter I got the following error:
import dotenv
dotenv.load_dotenv()
import os
from composio_llamaindex import App, ComposioToolSet
from llama_index.core.agent import FunctionCallingAgentWorker
from llama_index.core.llms import ChatMessage
from llama_index.llms.openai import OpenAI
import sys
import subprocess
subprocess.run(["composio", "apps", "update"])
from composio.tools.local import filetool, sqltool
toolset = ComposioToolSet(api_key=os.environ["COMPOSIO_API_KEY"])
sql_tool = toolset.get_tools(apps=[App.SQLTOOL])
file_tool = toolset.get_tools(apps=[App.FILETOOL])
code_interpretor_tool = toolset.get_tools(apps=[App.CODEINTERPRETER])
tools = toolset.get_tools(apps=[App.SQLTOOL, App.FILETOOL, App.CODEINTERPRETER])
llm = OpenAI(model="gpt-4o-2024-05-13", api_key=os.environ["OPENAI_API_KEY"])
prefix_messages = [
ChatMessage(
role="system",
content=(
"You are now a integration agent, and what ever you are requested, you will try to execute utilizing your toools."
),
)
]
agent = FunctionCallingAgentWorker(
tools=tools,
llm=llm,
prefix_messages=prefix_messages,
max_function_calls=10,
allow_parallel_tool_calls=False,
verbose=True,
).as_agent()
db_file_path = 'example_db/company.db'
print(db_file_path)
human_description = f"""The database to use is {db_file_path}"""
human_input = "Query the table MOCK_DATA for all rows and plot a graph between first names and salary by using code interpretor"
response = agent.chat(
"Database description ="+ human_description +"Task to perform:" + human_input
)
print("Response:", response)
After trying to upgrade
Checking.
So I found the error.
Llamaindex limits the char length of a tool by 1024 chars.
In the recent enhancement of filetool, we exceeded 1024 chars for the action edit_file. This resulted in the error. We are solving it by modifying edit file action back to change it to 1024.
correct-apricot•4w ago
Ah I see
thanks!