update
This commit is contained in:
@@ -653,7 +653,7 @@ function evaluator(state::T1, text2textInstructLLM::Function;
|
||||
1) Trajectory_evaluation: Analyze the trajectory of a solution to answer the user's original question.
|
||||
- Evaluate the correctness of each section and the overall trajectory based on the given question.
|
||||
- Provide detailed reasoning and analysis, focusing on the latest thought, action, and observation.
|
||||
- Incomplete trajectories are acceptable if the thoughts and actions up to that point are correct, even if the final answer isn't reached.
|
||||
- Incomplete trajectory are acceptable if the thoughts and actions up to that point are correct, even if the final answer isn't reached.
|
||||
- Do not generate additional thoughts or actions.
|
||||
2) Answer_evaluation:
|
||||
- Focus only on the matter mentioned in the question and comprehensively analyze how the latest observation's details addresses the question
|
||||
@@ -744,7 +744,7 @@ function evaluator(state::T1, text2textInstructLLM::Function;
|
||||
addSQLVectorDB(state)
|
||||
end
|
||||
end
|
||||
println("~~~ Evaluator() ", @__FILE__, " ", @__LINE__)
|
||||
println("\n~~~ Evaluator() ", @__FILE__, " ", @__LINE__)
|
||||
pprintln(Dict(responsedict))
|
||||
|
||||
return responsedict[:score]
|
||||
|
||||
Reference in New Issue
Block a user