jyapayne/langflow
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

🐛 fix(OpenAIConversationalAgent.py): ignore type errors for memory_key, system_message, prompt, agent, and tools variables

Browse source 
✨ feat(OpenAIConversationalAgent.py): add support for return_intermediate_steps parameter in AgentExecutor constructor to enable returning intermediate steps during conversation
This commit is contained in:
Gabriel Luiz Freitas Almeida 2023-08-09 21:58:25 -03:00
commit 33ef3b0a7e
1 changed files with 6 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

10
src/backend/langflow/components/agents/OpenAIConversationalAgent.py
View file

@ -54,17 +54,19 @@ class ConversationalAgent(CustomComponent):
max_token_limit=max_token_limit, max_token_limit=max_token_limit,
) )
else: else:
memory_key = memory.memory_key memory_key = memory.memory_key # type: ignore
_system_message = system_message or _get_default_system_message() _system_message = system_message or _get_default_system_message()
prompt = OpenAIFunctionsAgent.create_prompt( prompt = OpenAIFunctionsAgent.create_prompt(
system_message=_system_message, system_message=_system_message, # type: ignore
extra_prompt_messages=[MessagesPlaceholder(variable_name=memory_key)], extra_prompt_messages=[MessagesPlaceholder(variable_name=memory_key)],
) )
agent = OpenAIFunctionsAgent(llm=llm, tools=tools, prompt=prompt) agent = OpenAIFunctionsAgent(
llm=llm, tools=tools, prompt=prompt # type: ignore
)
return AgentExecutor( return AgentExecutor(
agent=agent, agent=agent,
tools=tools, tools=tools, # type: ignore
memory=memory, memory=memory,
verbose=True, verbose=True,
return_intermediate_steps=True, return_intermediate_steps=True,