autogen/test/test_function_call.py

134 lines
5.0 KiB
Python
Raw Normal View History

try:
import openai
except ImportError:
openai = None
import pytest
import json
raise error when msg is invalid; fix docstr; improve ResponsiveAgent; update doc and packaging; capture ipython output; find code blocks with llm when regex fails. (#1154) * autogen.agent -> autogen.agentchat * bug fix in portfolio * notebook * timeout * timeout * infer lang; close #1150 * timeout * message context * context handling * add sender to generate_reply * clean up the receive function * move mathchat to contrib * contrib * last_message * Add OptiGuide: agent and notebook * Optiguide notebook: add figures and URL 1. figures and code points to remote URL 2. simplify the prompt for the interpreter, because all information is already in the chat history. * Update name: Agent -> GenericAgent * Update notebook * Rename: GenericAgent -> ResponsiveAgent * Rebase to autogen.agentchat * OptiGuide: Comment, sytle, and notebook updates * simplify optiguide * raise error when msg is invalid; fix docstr * allow return None for generate_reply() * update_system_message * test update_system_message * simplify optiguide * simplify optiguide * simplify optiguide * simplify optiguide * move test * add test and fix bug * doc update * doc update * doc update * color * optiguide * prompt * test danger case * packaging * docker * remove path in traceback * capture ipython output * simplify * find code blocks with llm * find code with llm * order * order * fix bug in context handling * print executing msg * print executing msg * test find code * test find code * disable find_code * default_auto_reply * default auto reply * remove optiguide * remove -e --------- Co-authored-by: Beibin Li <beibin79@gmail.com>
2023-07-31 19:22:30 -07:00
from flaml import autogen
from flaml.autogen.math_utils import eval_math_responses
raise error when msg is invalid; fix docstr; improve ResponsiveAgent; update doc and packaging; capture ipython output; find code blocks with llm when regex fails. (#1154) * autogen.agent -> autogen.agentchat * bug fix in portfolio * notebook * timeout * timeout * infer lang; close #1150 * timeout * message context * context handling * add sender to generate_reply * clean up the receive function * move mathchat to contrib * contrib * last_message * Add OptiGuide: agent and notebook * Optiguide notebook: add figures and URL 1. figures and code points to remote URL 2. simplify the prompt for the interpreter, because all information is already in the chat history. * Update name: Agent -> GenericAgent * Update notebook * Rename: GenericAgent -> ResponsiveAgent * Rebase to autogen.agentchat * OptiGuide: Comment, sytle, and notebook updates * simplify optiguide * raise error when msg is invalid; fix docstr * allow return None for generate_reply() * update_system_message * test update_system_message * simplify optiguide * simplify optiguide * simplify optiguide * simplify optiguide * move test * add test and fix bug * doc update * doc update * doc update * color * optiguide * prompt * test danger case * packaging * docker * remove path in traceback * capture ipython output * simplify * find code blocks with llm * find code with llm * order * order * fix bug in context handling * print executing msg * print executing msg * test find code * test find code * disable find_code * default_auto_reply * default auto reply * remove optiguide * remove -e --------- Co-authored-by: Beibin Li <beibin79@gmail.com>
2023-07-31 19:22:30 -07:00
from test_code import KEY_LOC
@pytest.mark.skipif(openai is None, reason="openai not installed")
def test_eval_math_responses():
raise error when msg is invalid; fix docstr; improve ResponsiveAgent; update doc and packaging; capture ipython output; find code blocks with llm when regex fails. (#1154) * autogen.agent -> autogen.agentchat * bug fix in portfolio * notebook * timeout * timeout * infer lang; close #1150 * timeout * message context * context handling * add sender to generate_reply * clean up the receive function * move mathchat to contrib * contrib * last_message * Add OptiGuide: agent and notebook * Optiguide notebook: add figures and URL 1. figures and code points to remote URL 2. simplify the prompt for the interpreter, because all information is already in the chat history. * Update name: Agent -> GenericAgent * Update notebook * Rename: GenericAgent -> ResponsiveAgent * Rebase to autogen.agentchat * OptiGuide: Comment, sytle, and notebook updates * simplify optiguide * raise error when msg is invalid; fix docstr * allow return None for generate_reply() * update_system_message * test update_system_message * simplify optiguide * simplify optiguide * simplify optiguide * simplify optiguide * move test * add test and fix bug * doc update * doc update * doc update * color * optiguide * prompt * test danger case * packaging * docker * remove path in traceback * capture ipython output * simplify * find code blocks with llm * find code with llm * order * order * fix bug in context handling * print executing msg * print executing msg * test find code * test find code * disable find_code * default_auto_reply * default auto reply * remove optiguide * remove -e --------- Co-authored-by: Beibin Li <beibin79@gmail.com>
2023-07-31 19:22:30 -07:00
config_list = autogen.config_list_from_models(
KEY_LOC, exclude="aoai", model_list=["gpt-4-0613", "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k"]
)
functions = [
{
"name": "eval_math_responses",
"description": "Select a response for a math problem using voting, and check if the response is correct if the solution is provided",
"parameters": {
"type": "object",
"properties": {
"responses": {
"type": "array",
"items": {"type": "string"},
"description": "The responses in a list",
},
"solution": {
"type": "string",
"description": "The canonical solution",
},
},
"required": ["responses"],
},
},
]
raise error when msg is invalid; fix docstr; improve ResponsiveAgent; update doc and packaging; capture ipython output; find code blocks with llm when regex fails. (#1154) * autogen.agent -> autogen.agentchat * bug fix in portfolio * notebook * timeout * timeout * infer lang; close #1150 * timeout * message context * context handling * add sender to generate_reply * clean up the receive function * move mathchat to contrib * contrib * last_message * Add OptiGuide: agent and notebook * Optiguide notebook: add figures and URL 1. figures and code points to remote URL 2. simplify the prompt for the interpreter, because all information is already in the chat history. * Update name: Agent -> GenericAgent * Update notebook * Rename: GenericAgent -> ResponsiveAgent * Rebase to autogen.agentchat * OptiGuide: Comment, sytle, and notebook updates * simplify optiguide * raise error when msg is invalid; fix docstr * allow return None for generate_reply() * update_system_message * test update_system_message * simplify optiguide * simplify optiguide * simplify optiguide * simplify optiguide * move test * add test and fix bug * doc update * doc update * doc update * color * optiguide * prompt * test danger case * packaging * docker * remove path in traceback * capture ipython output * simplify * find code blocks with llm * find code with llm * order * order * fix bug in context handling * print executing msg * print executing msg * test find code * test find code * disable find_code * default_auto_reply * default auto reply * remove optiguide * remove -e --------- Co-authored-by: Beibin Li <beibin79@gmail.com>
2023-07-31 19:22:30 -07:00
response = autogen.ChatCompletion.create(
config_list=config_list,
messages=[
{
"role": "user",
"content": 'evaluate the math responses ["1", "5/2", "5/2"] against the true answer \\frac{5}{2}',
},
],
functions=functions,
)
print(response)
raise error when msg is invalid; fix docstr; improve ResponsiveAgent; update doc and packaging; capture ipython output; find code blocks with llm when regex fails. (#1154) * autogen.agent -> autogen.agentchat * bug fix in portfolio * notebook * timeout * timeout * infer lang; close #1150 * timeout * message context * context handling * add sender to generate_reply * clean up the receive function * move mathchat to contrib * contrib * last_message * Add OptiGuide: agent and notebook * Optiguide notebook: add figures and URL 1. figures and code points to remote URL 2. simplify the prompt for the interpreter, because all information is already in the chat history. * Update name: Agent -> GenericAgent * Update notebook * Rename: GenericAgent -> ResponsiveAgent * Rebase to autogen.agentchat * OptiGuide: Comment, sytle, and notebook updates * simplify optiguide * raise error when msg is invalid; fix docstr * allow return None for generate_reply() * update_system_message * test update_system_message * simplify optiguide * simplify optiguide * simplify optiguide * simplify optiguide * move test * add test and fix bug * doc update * doc update * doc update * color * optiguide * prompt * test danger case * packaging * docker * remove path in traceback * capture ipython output * simplify * find code blocks with llm * find code with llm * order * order * fix bug in context handling * print executing msg * print executing msg * test find code * test find code * disable find_code * default_auto_reply * default auto reply * remove optiguide * remove -e --------- Co-authored-by: Beibin Li <beibin79@gmail.com>
2023-07-31 19:22:30 -07:00
responses = autogen.ChatCompletion.extract_text_or_function_call(response)
print(responses[0])
function_call = responses[0]["function_call"]
name, arguments = function_call["name"], json.loads(function_call["arguments"])
assert name == "eval_math_responses"
print(arguments["responses"])
# if isinstance(arguments["responses"], str):
# arguments["responses"] = json.loads(arguments["responses"])
arguments["responses"] = [f"\\boxed{{{x}}}" for x in arguments["responses"]]
print(arguments["responses"])
arguments["solution"] = f"\\boxed{{{arguments['solution']}}}"
print(eval_math_responses(**arguments))
Support function_call in `autogen/agent` (#1091) * update funccall * code format * update to comments * update notebook * remove test for py3.7 * allow funccall to class functions * add test and clean up notebook * revise notebook and test * update * update mathagent * Update flaml/autogen/agent/agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * revise to comments * revise function call design, notebook and test. add doc * code format * ad message_to_dict function * update mathproxyagent * revise docstr * update * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * simply funccall in userproxyagent, rewind auto-gen.md, revise to comments * code format * update * remove notebook for another pr * revise oai_conversation part in agent, revise function exec in user_proxy_agent * update test_funccall * update * update * fix pydantic version * Update test/autogen/test_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * fix bug * fix bug * update * update is_termination_msg to accept dict --------- Co-authored-by: Chi Wang <wang.chi@microsoft.com> Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-07-06 06:08:44 +08:00
def test_json_extraction():
from flaml.autogen.agentchat import UserProxyAgent
Support function_call in `autogen/agent` (#1091) * update funccall * code format * update to comments * update notebook * remove test for py3.7 * allow funccall to class functions * add test and clean up notebook * revise notebook and test * update * update mathagent * Update flaml/autogen/agent/agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * revise to comments * revise function call design, notebook and test. add doc * code format * ad message_to_dict function * update mathproxyagent * revise docstr * update * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * simply funccall in userproxyagent, rewind auto-gen.md, revise to comments * code format * update * remove notebook for another pr * revise oai_conversation part in agent, revise function exec in user_proxy_agent * update test_funccall * update * update * fix pydantic version * Update test/autogen/test_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * fix bug * fix bug * update * update is_termination_msg to accept dict --------- Co-authored-by: Chi Wang <wang.chi@microsoft.com> Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-07-06 06:08:44 +08:00
user = UserProxyAgent(name="test", code_execution_config={"use_docker": False})
Support function_call in `autogen/agent` (#1091) * update funccall * code format * update to comments * update notebook * remove test for py3.7 * allow funccall to class functions * add test and clean up notebook * revise notebook and test * update * update mathagent * Update flaml/autogen/agent/agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * revise to comments * revise function call design, notebook and test. add doc * code format * ad message_to_dict function * update mathproxyagent * revise docstr * update * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * simply funccall in userproxyagent, rewind auto-gen.md, revise to comments * code format * update * remove notebook for another pr * revise oai_conversation part in agent, revise function exec in user_proxy_agent * update test_funccall * update * update * fix pydantic version * Update test/autogen/test_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * fix bug * fix bug * update * update is_termination_msg to accept dict --------- Co-authored-by: Chi Wang <wang.chi@microsoft.com> Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-07-06 06:08:44 +08:00
jstr = '{\n"location": "Boston, MA"\n}'
assert user._format_json_str(jstr) == '{"location": "Boston, MA"}'
jstr = '{\n"code": "python",\n"query": "x=3\nprint(x)"}'
assert user._format_json_str(jstr) == '{"code": "python","query": "x=3\\nprint(x)"}'
jstr = '{"code": "a=\\"hello\\""}'
assert user._format_json_str(jstr) == '{"code": "a=\\"hello\\""}'
def test_execute_function():
from flaml.autogen.agentchat import UserProxyAgent
Support function_call in `autogen/agent` (#1091) * update funccall * code format * update to comments * update notebook * remove test for py3.7 * allow funccall to class functions * add test and clean up notebook * revise notebook and test * update * update mathagent * Update flaml/autogen/agent/agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * revise to comments * revise function call design, notebook and test. add doc * code format * ad message_to_dict function * update mathproxyagent * revise docstr * update * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * simply funccall in userproxyagent, rewind auto-gen.md, revise to comments * code format * update * remove notebook for another pr * revise oai_conversation part in agent, revise function exec in user_proxy_agent * update test_funccall * update * update * fix pydantic version * Update test/autogen/test_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * fix bug * fix bug * update * update is_termination_msg to accept dict --------- Co-authored-by: Chi Wang <wang.chi@microsoft.com> Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-07-06 06:08:44 +08:00
# 1. test calling a simple function
def add_num(num_to_be_added):
given_num = 10
return num_to_be_added + given_num
user = UserProxyAgent(name="test", function_map={"add_num": add_num})
# correct execution
correct_args = {"name": "add_num", "arguments": '{ "num_to_be_added": 5 }'}
assert user.execute_function(func_call=correct_args)[1]["content"] == "15"
Support function_call in `autogen/agent` (#1091) * update funccall * code format * update to comments * update notebook * remove test for py3.7 * allow funccall to class functions * add test and clean up notebook * revise notebook and test * update * update mathagent * Update flaml/autogen/agent/agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * revise to comments * revise function call design, notebook and test. add doc * code format * ad message_to_dict function * update mathproxyagent * revise docstr * update * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * simply funccall in userproxyagent, rewind auto-gen.md, revise to comments * code format * update * remove notebook for another pr * revise oai_conversation part in agent, revise function exec in user_proxy_agent * update test_funccall * update * update * fix pydantic version * Update test/autogen/test_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * fix bug * fix bug * update * update is_termination_msg to accept dict --------- Co-authored-by: Chi Wang <wang.chi@microsoft.com> Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-07-06 06:08:44 +08:00
# function name called is wrong or doesn't exist
wrong_func_name = {"name": "subtract_num", "arguments": '{ "num_to_be_added": 5 }'}
assert "Error: Function" in user.execute_function(func_call=wrong_func_name)[1]["content"]
Support function_call in `autogen/agent` (#1091) * update funccall * code format * update to comments * update notebook * remove test for py3.7 * allow funccall to class functions * add test and clean up notebook * revise notebook and test * update * update mathagent * Update flaml/autogen/agent/agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * revise to comments * revise function call design, notebook and test. add doc * code format * ad message_to_dict function * update mathproxyagent * revise docstr * update * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * simply funccall in userproxyagent, rewind auto-gen.md, revise to comments * code format * update * remove notebook for another pr * revise oai_conversation part in agent, revise function exec in user_proxy_agent * update test_funccall * update * update * fix pydantic version * Update test/autogen/test_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * fix bug * fix bug * update * update is_termination_msg to accept dict --------- Co-authored-by: Chi Wang <wang.chi@microsoft.com> Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-07-06 06:08:44 +08:00
# arguments passed is not in correct json format
wrong_json_format = {
"name": "add_num",
"arguments": '{ "num_to_be_added": 5, given_num: 10 }',
} # should be "given_num" with quotes
assert "You argument should follow json format." in user.execute_function(func_call=wrong_json_format)[1]["content"]
Support function_call in `autogen/agent` (#1091) * update funccall * code format * update to comments * update notebook * remove test for py3.7 * allow funccall to class functions * add test and clean up notebook * revise notebook and test * update * update mathagent * Update flaml/autogen/agent/agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * revise to comments * revise function call design, notebook and test. add doc * code format * ad message_to_dict function * update mathproxyagent * revise docstr * update * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * simply funccall in userproxyagent, rewind auto-gen.md, revise to comments * code format * update * remove notebook for another pr * revise oai_conversation part in agent, revise function exec in user_proxy_agent * update test_funccall * update * update * fix pydantic version * Update test/autogen/test_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * fix bug * fix bug * update * update is_termination_msg to accept dict --------- Co-authored-by: Chi Wang <wang.chi@microsoft.com> Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-07-06 06:08:44 +08:00
# function execution error with wrong arguments passed
wrong_args = {"name": "add_num", "arguments": '{ "num_to_be_added": 5, "given_num": 10 }'}
assert "Error: " in user.execute_function(func_call=wrong_args)[1]["content"]
Support function_call in `autogen/agent` (#1091) * update funccall * code format * update to comments * update notebook * remove test for py3.7 * allow funccall to class functions * add test and clean up notebook * revise notebook and test * update * update mathagent * Update flaml/autogen/agent/agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * revise to comments * revise function call design, notebook and test. add doc * code format * ad message_to_dict function * update mathproxyagent * revise docstr * update * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * simply funccall in userproxyagent, rewind auto-gen.md, revise to comments * code format * update * remove notebook for another pr * revise oai_conversation part in agent, revise function exec in user_proxy_agent * update test_funccall * update * update * fix pydantic version * Update test/autogen/test_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * fix bug * fix bug * update * update is_termination_msg to accept dict --------- Co-authored-by: Chi Wang <wang.chi@microsoft.com> Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-07-06 06:08:44 +08:00
# 2. test calling a class method
class AddNum:
def __init__(self, given_num):
self.given_num = given_num
def add(self, num_to_be_added):
self.given_num = num_to_be_added + self.given_num
return self.given_num
user = UserProxyAgent(name="test", function_map={"add_num": AddNum(given_num=10).add})
func_call = {"name": "add_num", "arguments": '{ "num_to_be_added": 5 }'}
assert user.execute_function(func_call=func_call)[1]["content"] == "15"
assert user.execute_function(func_call=func_call)[1]["content"] == "20"
Support function_call in `autogen/agent` (#1091) * update funccall * code format * update to comments * update notebook * remove test for py3.7 * allow funccall to class functions * add test and clean up notebook * revise notebook and test * update * update mathagent * Update flaml/autogen/agent/agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * revise to comments * revise function call design, notebook and test. add doc * code format * ad message_to_dict function * update mathproxyagent * revise docstr * update * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * simply funccall in userproxyagent, rewind auto-gen.md, revise to comments * code format * update * remove notebook for another pr * revise oai_conversation part in agent, revise function exec in user_proxy_agent * update test_funccall * update * update * fix pydantic version * Update test/autogen/test_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * fix bug * fix bug * update * update is_termination_msg to accept dict --------- Co-authored-by: Chi Wang <wang.chi@microsoft.com> Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-07-06 06:08:44 +08:00
# 3. test calling a function with no arguments
def get_number():
return 42
user = UserProxyAgent("user", function_map={"get_number": get_number})
func_call = {"name": "get_number", "arguments": "{}"}
assert user.execute_function(func_call)[1]["content"] == "42"
Support function_call in `autogen/agent` (#1091) * update funccall * code format * update to comments * update notebook * remove test for py3.7 * allow funccall to class functions * add test and clean up notebook * revise notebook and test * update * update mathagent * Update flaml/autogen/agent/agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * revise to comments * revise function call design, notebook and test. add doc * code format * ad message_to_dict function * update mathproxyagent * revise docstr * update * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * simply funccall in userproxyagent, rewind auto-gen.md, revise to comments * code format * update * remove notebook for another pr * revise oai_conversation part in agent, revise function exec in user_proxy_agent * update test_funccall * update * update * fix pydantic version * Update test/autogen/test_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * fix bug * fix bug * update * update is_termination_msg to accept dict --------- Co-authored-by: Chi Wang <wang.chi@microsoft.com> Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-07-06 06:08:44 +08:00
if __name__ == "__main__":
Support function_call in `autogen/agent` (#1091) * update funccall * code format * update to comments * update notebook * remove test for py3.7 * allow funccall to class functions * add test and clean up notebook * revise notebook and test * update * update mathagent * Update flaml/autogen/agent/agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * revise to comments * revise function call design, notebook and test. add doc * code format * ad message_to_dict function * update mathproxyagent * revise docstr * update * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * Update flaml/autogen/agent/math_user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * Update flaml/autogen/agent/user_proxy_agent.py Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> * simply funccall in userproxyagent, rewind auto-gen.md, revise to comments * code format * update * remove notebook for another pr * revise oai_conversation part in agent, revise function exec in user_proxy_agent * update test_funccall * update * update * fix pydantic version * Update test/autogen/test_agent.py Co-authored-by: Chi Wang <wang.chi@microsoft.com> * fix bug * fix bug * update * update is_termination_msg to accept dict --------- Co-authored-by: Chi Wang <wang.chi@microsoft.com> Co-authored-by: Qingyun Wu <qingyun.wu@psu.edu> Co-authored-by: Li Jiang <bnujli@gmail.com>
2023-07-06 06:08:44 +08:00
test_json_extraction()
test_execute_function()
test_eval_math_responses()