Traceback (most recent call last):
File "/dual_agent.py", line 4, in
from dbgpt.agent import AgentContext, AgentMemory, LLMConfig, UserProxyAgent
File "/Applications/miniconda3/envs/_env/lib/python3.10/site-packages/dbgpt/agent/init.py", line 18, in
from .core.plan import # noqa: F401, F403
File "/Applications/miniconda3/envs/****_env/lib/python3.10/site-packages/dbgpt/agent/core/plan/init.py", line 3, in
from .awel.agent_operator import ( # noqa: F401
File "/Applications/miniconda3/envs/_env/lib/python3.10/site-packages/dbgpt/agent/core/plan/awel/agent_operator.py", line 25, in
from dbgpt.serve.prompt.api.endpoints import get_service
ModuleNotFoundError: No module named 'dbgpt.serve'
What you expected to happen
...
How to reproduce
import asyncio
import os
from dbgpt.agent import AgentContext, AgentMemory, LLMConfig, UserProxyAgent
from dbgpt.agent.expand.tool_assistant_agent import ToolAssistantAgent
from dbgpt.agent.resource import ToolPack, tool
from dbgpt.model.proxy.llms.chatgpt import OpenAILLMClient
from pydantic import BaseModel, Field
class ArgsSchema(BaseModel):
a: int = Field(description="The first number.")
b: int = Field(description="The second number.")
@tool(args_schema=ArgsSchema)
def two_sum(a: int, b: int) -> int:
"""Add two numbers and return the sum."""
return a + b
tools = ToolPack([two_sum])
async def main():
llm_client = OpenAILLMClient(
model_alias="gpt-4o",
api_base=os.getenv("OPENAI_API_BASE"),
api_key=os.getenv("OPENAI_API_KEY"),
)
context: AgentContext = AgentContext(
conv_id="test123", language="en", temperature=0.5, max_new_tokens=2048
)
agent_memory = AgentMemory()
user_proxy = await UserProxyAgent().bind(agent_memory).bind(context).build()
tool_man = (
await ToolAssistantAgent()
.bind(context)
.bind(LLMConfig(llm_client=llm_client))
.bind(agent_memory)
.bind(tools)
.build()
)
await user_proxy.initiate_chat(
recipient=tool_man,
reviewer=user_proxy,
message="Calculate the product of 10 and 99",
)
await user_proxy.initiate_chat(
recipient=tool_man,
reviewer=user_proxy,
message="Count the number of files in /tmp",
)
print("Done!")
if __name__ == "__main__":
asyncio.run(main())
it looks like from dbgpt.serve.prompt.api.endpoints import get_service problem. we will fix that soon.
/assign @yhjun1026 please take a look.
or downgrade your dbgpt sdk
try
Search before asking
Operating system information
MacOS(x86)
Python version information
3.10
DB-GPT version
latest release (v0.6.1)
Related scenes
Installation Information
[X] Installation From Source
[ ] Docker Installation
[ ] Docker Compose Installation
[ ] Cluster Installation
[ ] AutoDL Image
[ ] Other
Device information
MacOS M2 pip install dbgpt (version is v0.6.1)
Models information
gpt-4o, want to use tool calling.
What happened
me % python dual_agent.py
Traceback (most recent call last): File "/dual_agent.py", line 4, in
from dbgpt.agent import AgentContext, AgentMemory, LLMConfig, UserProxyAgent
File "/Applications/miniconda3/envs/_env/lib/python3.10/site-packages/dbgpt/agent/init.py", line 18, in
from .core.plan import # noqa: F401, F403
File "/Applications/miniconda3/envs/****_env/lib/python3.10/site-packages/dbgpt/agent/core/plan/init.py", line 3, in
from .awel.agent_operator import ( # noqa: F401
File "/Applications/miniconda3/envs/ _env/lib/python3.10/site-packages/dbgpt/agent/core/plan/awel/agent_operator.py", line 25, in
from dbgpt.serve.prompt.api.endpoints import get_service
ModuleNotFoundError: No module named 'dbgpt.serve'
What you expected to happen
...
How to reproduce
Additional context
No module named 'dbgpt.serve'
Are you willing to submit PR?