You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Just using the base project from create crew CLI command and using OpenAI API key I am able to train and test my agents just fine. When I add knowledge sources of type JSON I do get a pydantic error from a dependency that I cannot fix. Simply importing the package will fail to train the agent. It will run the crew fine however. Is this intentional? As I do not see anyplace in the documentation for training that that is the case.
Steps to Reproduce
follow create crew instructions
change nothing
Add knowledge source to agent using default user_preference.txt
try to train model
Expected behavior
Ability to train on sample data
Screenshots/Code snippets
macOS Sequoia
Operating System
Other (specify in additional context)
Python Version
3.11
crewAI Version
0.95.0
crewAI Tools Version
0.25.8
Virtual Environment
Venv
Evidence
`crewai train -n 1
Training the Crew for 1 iterations
Traceback (most recent call last):
File "/path/src/tf_jits/main.py", line 36, in train
TfJits().crew().train(n_iterations=int(sys.argv[1]), filename=sys.argv[2], inputs=inputs)
File "/path/.venv/lib/python3.11/site-packages/crewai/crew.py", line 491, in train
train_crew = self.copy()
^^^^^^^^^^^
File "/path/.venv/lib/python3.11/site-packages/crewai/crew.py", line 1012, in copy
cloned_agents = [agent.copy() for agent in self.agents]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/path/.venv/lib/python3.11/site-packages/crewai/crew.py", line 1012, in
cloned_agents = [agent.copy() for agent in self.agents]
^^^^^^^^^^^^
File "/path/.venv/lib/python3.11/site-packages/crewai/agents/agent_builder/base_agent.py", line 265, in copy
copied_agent = type(self)(**copied_data, llm=existing_llm, tools=self.tools)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/path/.venv/lib/python3.11/site-packages/pydantic/main.py", line 214, in init
validated_self = self.pydantic_validator.validate_python(data, self_instance=self)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: Can't instantiate abstract class BaseKnowledgeSource with abstract methods add, validate_content
During handling of the above exception, another exception occurred:`
Possible Solution
None
Additional context
None
The text was updated successfully, but these errors were encountered:
Description
Just using the base project from
create crew
CLI command and using OpenAI API key I am able to train and test my agents just fine. When I add knowledge sources of type JSON I do get a pydantic error from a dependency that I cannot fix. Simply importing the package will fail to train the agent. It will run the crew fine however. Is this intentional? As I do not see anyplace in the documentation for training that that is the case.Steps to Reproduce
create crew instructions
user_preference.txt
Expected behavior
Ability to train on sample data
Screenshots/Code snippets
macOS Sequoia
Operating System
Other (specify in additional context)
Python Version
3.11
crewAI Version
0.95.0
crewAI Tools Version
0.25.8
Virtual Environment
Venv
Evidence
`crewai train -n 1
Training the Crew for 1 iterations
Traceback (most recent call last):
File "/path/src/tf_jits/main.py", line 36, in train
TfJits().crew().train(n_iterations=int(sys.argv[1]), filename=sys.argv[2], inputs=inputs)
File "/path/.venv/lib/python3.11/site-packages/crewai/crew.py", line 491, in train
train_crew = self.copy()
^^^^^^^^^^^
File "/path/.venv/lib/python3.11/site-packages/crewai/crew.py", line 1012, in copy
cloned_agents = [agent.copy() for agent in self.agents]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/path/.venv/lib/python3.11/site-packages/crewai/crew.py", line 1012, in
cloned_agents = [agent.copy() for agent in self.agents]
^^^^^^^^^^^^
File "/path/.venv/lib/python3.11/site-packages/crewai/agents/agent_builder/base_agent.py", line 265, in copy
copied_agent = type(self)(**copied_data, llm=existing_llm, tools=self.tools)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/path/.venv/lib/python3.11/site-packages/pydantic/main.py", line 214, in init
validated_self = self.pydantic_validator.validate_python(data, self_instance=self)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: Can't instantiate abstract class BaseKnowledgeSource with abstract methods add, validate_content
During handling of the above exception, another exception occurred:`
Possible Solution
None
Additional context
None
The text was updated successfully, but these errors were encountered: