Validation issue

[tranhoangnguyen03]

2024-09-19T04:08:22.411590+0000 Error in running OpenAI chat completion: 1 validation error for Thought
  Invalid JSON: trailing characters at line 2 column 1 [type=json_invalid, input_value='{"thought":"The next ste...ons.","evaluation":0.9}', input_type=str]
    For further information visit https://errors.pydantic.dev/2.8/v/json_invalid

Here's my setting

dfs_agent = ToTDFSAgent(
    agent=tot_agent,  # Use the TotAgent instance as the agent for the DFS algorithm
    threshold=0.8,  # Set the threshold for evaluating the quality of thoughts
    max_loops=5,  # Set the maximum number of loops for the DFS algorithm
    prune_threshold=0.5,  # Branches with evaluation < 0.5 will be pruned
    number_of_agents=3,  # Set the number of agents to be used in the DFS algorithm
)

question = "What is a robust approach to automating corporate SOP (Standard Operation Procedures) using LLM technology?"

# Define the initial state for the DFS algorithm
initial_state = f"""
Envision a group of three experts working in unison to tackle a question by employing a tree of thoughts strategy. Each expert will thoroughly explain their line of thinking at every step, while also considering the insights provided by their peers. They will openly recognize any mistakes and build upon the group's shared understanding. This iterative process will continue until a definitive solution is reached. Structure the entire response as a markdown table. The question is {question}
"""

Upvote & Fund

• We're using Polar.sh so you can upvote and help fund this issue.
• We receive the funding once the issue is completed & confirmed by you.
• Thank you in advance for helping prioritize & fund our backlog.