Hitting enter at command line with no information on the line produces unexpected results.
Reproduce
Start openinterpreter
hit enter several times in succession
LLM generates random input.
Expected behavior
Ignore empty inputs, and do not send to LLM.
Screenshots
No response
Open Interpreter version
0.2.4
Python version
3.11.8
Operating System name and version
Arch Linux
Additional context
I'm using jan as a local model provider, with groq mixtral0-8x7b.
[?] Enter the id of the model you have running on Jan: mixtral-8x7b-32768
Using Jan model: mixtral-8x7b-32768
>
Sure! Here's an example of a code block in Python that prints "Hello, World!" to the console:
print("Hello, World!")
Would you like to run this code? (y/n)
>
Sure! Here's an example of a code block in Python that prompts the user to enter their name and then prints a greeting message with their name:
name = input("Enter your name: ")
print(f"Hello, {name}! It's nice to meet you.")
Would you like to run this code? (y/n)
>
I understand that you are not able or do not wish to run the code. Here is a code block that you can try running on your own machine. It is a Python program that calculates the factorial
of a number entered by the user: [
def factorial(n):
# This function calculates the factorial of a number
# It uses recursion to call itself until it reaches the base case of n=1
if n == 1:
return 1
else:
return n * factorial(n-1)
num = int(input("Enter a number: "))
result = factorial(num)
print(f"The factorial of {num} is {result}.")
Would you like to run this code? (y/n)
I've never asked open interpreter to run these, so they're not coming from cache. It's literally passing the empty string and probably any system prompts on to the LLM.
Describe the bug
Hitting enter at command line with no information on the line produces unexpected results.
Reproduce
Expected behavior
Ignore empty inputs, and do not send to LLM.
Screenshots
No response
Open Interpreter version
0.2.4
Python version
3.11.8
Operating System name and version
Arch Linux
Additional context
I'm using jan as a local model provider, with groq mixtral0-8x7b.
[?] Enter the id of the model you have running on Jan: mixtral-8x7b-32768
Using Jan model: mixtral-8x7b-32768
>
Sure! Here's an example of a code block in Python that prints "Hello, World!" to the console:
print("Hello, World!")
Would you like to run this code? (y/n)
>
Sure! Here's an example of a code block in Python that prompts the user to enter their name and then prints a greeting message with their name:
Would you like to run this code? (y/n)
>
I understand that you are not able or do not wish to run the code. Here is a code block that you can try running on your own machine. It is a Python program that calculates the factorial
of a number entered by the user: [
Would you like to run this code? (y/n)
I've never asked open interpreter to run these, so they're not coming from cache. It's literally passing the empty string and probably any system prompts on to the LLM.