OI hangs after executing some python code

[markredito]

Describe the bug

OI hangs after completing task.

> please pull up ethereum's price action for the month of august - september

  Sure, I can help with that. Here's the plan:

   1 Import the necessary libraries (yfinance and matplotlib).
   2 Use the yfinance library to download Ethereum's price data for the specified period (August - September).
   3 Plot the price action using matplotlib.

  Let's start by importing the necessary libraries and downloading the price data.



  import yfinance as yf
  import matplotlib.pyplot as plt

  # Download Ethereum's price data
  eth_data = yf.download('ETH-USD', start='2021-08-01', end='2021-09-30')
  eth_data


  Would you like to run this code? (y/n)

  y


  import yfinance as yf
  import matplotlib.pyplot as plt

  # Download Ethereum's price data
  eth_data = yf.download('ETH-USD', start='2021-08-01', end='2021-09-30')
  eth_data


  Output truncated. Showing the last 2000 characters.

  502987
  2021-09-01  3430.762451  3836.867432  ...  3834.828125  30070890104
  2021-09-02  3825.027832  3830.711426  ...  3790.989990  24387397330
  2021-09-03  3787.486572  4022.469238  ...  3940.614746  26207765094
  2021-09-04  3937.910156  3969.448730  ...  3887.828369  20806963328
  2021-09-05  3886.331055  3979.186523  ...  3952.133545  18371468576
  2021-09-06  3951.520752  3968.426514  ...  3928.379395  18674691198
  2021-09-07  3926.527588  3945.314209  ...  3426.394287  39131346397
  2021-09-08  3428.378174  3559.121338  ...  3497.315186  31738430771
  2021-09-09  3452.548340  3562.992676  ...  3427.340088  24118055831
  2021-09-10  3425.564941  3512.571289  ...  3211.505859  22355974097
  2021-09-11  3209.030518  3346.526367  ...  3270.278076  18627122934
  2021-09-12  3270.291748  3462.468262  ...  3410.134521  16810411424
  2021-09-13  3407.471924  3426.502197  ...  3285.511719  22721552948
  2021-09-14  3286.316406  3429.169678  ...  3429.169678  19125420848
  2021-09-15  3431.217285  3615.282715  ...  3615.282715  17548551804
  2021-09-16  3613.073730  3673.310791  ...  3571.294922  20093903064
  2021-09-17  3569.568115  3589.305176  ...  3398.538818  17722363229
  2021-09-18  3397.422852  3540.807617  ...  3432.018311  15995220233
  2021-09-19  3433.287842  3448.322021  ...  3329.447998  14257609743
  2021-09-20  3329.670654  3343.325439  ...  2958.993408  27371684581
  2021-09-21  2977.310547  3101.697510  ...  2764.431152  30405062665
  2021-09-22  2763.209229  3089.083008  ...  3077.867920  23742102645
  2021-09-23  3077.974365  3173.544678  ...  3155.523682  18516291047
  2021-09-24  3154.562012  3159.644043  ...  2931.669189  25595422789
  2021-09-25  2930.884766  2968.994629  ...  2925.565674  18932786754
  2021-09-26  2926.343018  3114.857422  ...  3062.265381  21172766310
  2021-09-27  3065.837891  3163.665039  ...  2934.138916  19164053681
  2021-09-28  2928.963379  2970.770508  ...  2807.296631  16895079070
  2021-09-29  2809.297607  2946.881348  ...  2853.143311  15763456158
  [60 rows x 6 columns]


  The Ethereum price data for August and September 2021 has been successfully downloaded. The data includes the Open, High, Low,
  Close, Adjusted Close prices, and the Volume of Ethereum traded each day.

  Next, I will plot the closing price of Ethereum for this period.



  plt.figure(figsize=(14, 7))
  plt.plot(eth_data['Close'])
  plt.title('Ethereum Price Action August - September 2021')
  plt.xlabel('Date')
  plt.ylabel('Price (USD)')
  plt.grid(True)
  plt.savefig('eth_price_action.png')
  plt.show()


  Would you like to run this code? (y/n)

  y


  plt.figure(figsize=(14, 7))
  plt.plot(eth_data['Close'])
  plt.title('Ethereum Price Action August - September 2021')
  plt.xlabel('Date')
  plt.ylabel('Price (USD)')
  plt.grid(True)
  plt.savefig('eth_price_action.png')
  plt.show()█


  <Figure size 1400x700 with 0 Axes>
  [<matplotlib.lines.Line2D object at 0x000001F182C3AAD0>]
  Text(0.5, 1.0, 'Ethereum Price Action August - September 2021')
  Text(0.5, 0, 'Date')
  Text(0, 0.5, 'Price (USD)')
                                                            

The LLM completed the task but my CLI becomes unresponsive after.

Reproduce

1. promnpt: please pull up ethereum's price action for the month of august - september
2. LLM runs code with user confirmation
3. LLM visualizes data via matplotlib
4. CLI becomes unresponsive after.

Expected behavior

After completing task, CLI should go back to "ready" state.

Screenshots

No response

Open Interpreter version

0.1.4

Python version

3.11.4

Operating System name and version

Windows 10

Additional context

No response

[LEI]

The CLI also hangs on Linux after executing any command via SSH, the expected output shows up but "command was executed successfully" never does, for example:

%reset %debug Run "ls example"

Running code:
echo "ACTIVE_LINE:1"
ls example

echo "END_OF_EXECUTION"
---
Recieved output line:
ACTIVE_LINE:1

---
Recieved output line:
END_OF_EXECUTION

---

  ls example

  [output]

Sending `messages` to LLM:

...

The command ls example was executed successfully.

%reset %debug Run "ssh host ls example"

Running code:
echo "ACTIVE_LINE:1"
ssh host ls example

echo "END_OF_EXECUTION"
---
Recieved output line:
ACTIVE_LINE:1

---

  ssh host ls example

  [output]

In the second case END_OF_EXECUTION never seems to be reached, though the output is visible and the command does not hang when executed manually.

[sschepis]

I'm experiencing this problem too - eventually, the interpreter hangs after some amount of conversation. The app always fails in the same way - it just stops working

[mobmobhask]

I’m experiencing this problem too. I believe the cause of this bug is this issue: https://github.com/KillianLucas/tokentrim/issues/3

[ericrallen]

Hey there, folks!

Can anyone confirm if this is still an issue with the latest version of Open Interpreter?

We integrated some changes in underlying dependencies that I think might have resolved it.