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
Observation: �[33;1m�[1;3m The ratio of the prices of stocks 'ABC' and 'XYZ' in January 3rd is 0.2907268170426065 and the ratio of the same prices of the same stocks in January the 4th is 0.2830188679245283.�[0m
Thought:�[32;1m�[1;3m Do I need to use a tool? No
AI: The answer is 0.4444444444444444. Is there anything else I can help you with?�[0m
�[1m> Finished chain.�[0m
Spent a total of 2518 tokens
With this, the agent still manages to solve the question but uses a more complex approach of pure SQL rather than relying on more straightforward SQL and the calculator tool.
However, the agent actually fails to solves the question since it hallucinates the end result (0.29 * 0.28 != 0.44).
Just as minor improvement, the sentence could be changed to read that the agent actually fails to solve complex queries.
Is this a new bug?
Current Behavior
Chapter 6 of the "Langchain AI Handbook" reads:
With this, the agent still manages to solve the question but uses a more complex approach of pure SQL rather than relying on more straightforward SQL and the calculator tool.
However, the agent actually fails to solves the question since it hallucinates the end result (0.29 * 0.28 != 0.44).
Just as minor improvement, the sentence could be changed to read that the agent actually fails to solve complex queries.
Expected Behavior
N/A
Steps To Reproduce
N/A
Relevant log output
No response
Environment
Additional Context
No response
The text was updated successfully, but these errors were encountered: