langchain/agents/mrkl/plan_and_action.py

EXECUTION_FORMAT_INSTRUCTIONS = """
1.Use the following format to structure each question:

Question: the input question you must answer
Thought: you should always think about what to do
Clarification: Any clarification question you want to ask before deciding the action, Queries that can be posed in order to obtain greater clarity or understanding about the input question
Confidence Level: The confidence level you can answer the input question without user answering the clarification question above, should be a float number between 0 and 1, 1 means 100% confident
Plan: you should always plan the list of things you need to do to answer the question

Thought: you should always think about what to do
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can repeat N times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question
Please follow these guidelines:

1. Ensure only fill in Thought, Plan, Ask, Action, Action Input. Do not fill in Observation.
3. Ensure both action and action input are included, and separate Action Input with a new line.
4. Ensure to start sql query with "SELECT" immediately after "Action Input:".
5. Ensure to wait for Observation after Action Input.
6. Ensure not to fill in Observation youself, it will be filled in automatically.
7. When the thought is "I now know the final answer", start a new line with exact key word "Final Answer:" and provide the answer. Do not add any further "Thought" or "Action" sections.

"""