Commit History

  1. Try to change output to stream instead of wait for completion

    Verified signature
    82af3b6
  2. Removed chat history

    Verified signature
    fd25069
  3. Removed trying to remove text from input box

    Verified signature
    9428c8a
  4. Revert back to qwen.

    Verified signature
    d218ef0
  5. Try earlier llama model

    Verified signature
    4e0c6dc
  6. fixed syntax error in previous commit

    Verified signature
    31daeee
  7. Switch model to llama

    Verified signature
    8932ece
  8. Update app.py⁠

    Verified signature
    63728fb
  9. Changed to mistral model

    Verified signature
    9391655
  10. Changed model and alterned default context to remove location.

    Verified signature
    100673e
  11. Try fix problem with clearing user input box

    Verified signature
    c9b44c4
  12. Clear input box after use

    Verified signature
    9898aa3
  13. Update app.py⁠

    Verified signature
    2249329
  14. Rearranged help checkbox after ask button

    Verified signature
    30f53de
  15. Rearranged columns below input box

    Verified signature
    187d5dc
  16. Try to realign items

    Verified signature
    634e250
  17. Try to fix problems with method not being initialized in time

    Verified signature
    a7a6cbd
  18. Try to realign elements to take less vertical space.

    Verified signature
    11a6534
  19. Remove header to make it fit better inside Adrega

    Verified signature
    f5e81c3

  1. Reduced max tokens further to make sure it accepts a larger question

    Verified signature
    ca90665
  2. Changed max tokens to take Help into consideration for max total tokens

    Verified signature
    33c3d9e
  3. Change token limit to Qwen max

    Verified signature
    5616271
  4. Changed output text to always display last question and answer at top

    Verified signature
    5b8c9a0
  5. Updated context for non-help related questions. Try to add answers in scrollable div, with better overview of question and answer.

    Verified signature
    52ef193
  6. Try to replace textarea with markdown to display nice html

    Verified signature
    c28c28f
  7. Updated to use session state variable instead of just variable for include_context

    Verified signature
    c119414
  8. Removed code for include_context. It should always have a value

    Verified signature
    07d6d5e
  9. Test update with invalid information to test context with and without checkbox

    Verified signature
    9e74383
  10. Write text to screen, to see if the formatting is better

    Verified signature
    42fd51d
  11. Reverted trying to not load dataset, as it causes problem with requests

    Verified signature
    e7169f6
  12. Rearranged the submit button.

    Verified signature
    b0c57d4
  13. Prevent loading dataset if Help checkbox is not checked

    Verified signature
    9dfb04d
  14. Fix session_state try2

    Verified signature
    cbd1365
  15. Initialize include_context before usage

    Verified signature
    442c909
  16. Fixed minor syntax error

    Verified signature
    3a24c45
  17. Moved checkbox up, added possibility to press enter to submit

    Verified signature
    d943ab1
  18. Fix problem with conversation not being initialized

    Verified signature
    ec395fa
  19. Keep and display chat history

    Verified signature
    fed0941
  20. Update to yellow background #3

    Verified signature
    165ae3e
  21. Make background yellow try2

    Verified signature
    811ba5a
  22. Test setting a specific background color

    Verified signature
    2e57e8b
  23. Fixed syntax error

    Verified signature
    7ed9b7b
  24. Added button to turn help on or off

    Verified signature
    88e2d62
  25. Removed chunks, as it didn't work anyway

    Verified signature
    82909b4
  26. Try to split query into chunks to prevent overloading model

    Verified signature
    2fc80c5
  27. Test qwen 72B

    Verified signature
    7498c16
  28. Test what happens if switch to cold inference model

    Verified signature
    85fad1d
  29. One more try to get inference llama 3.2 model working

    Verified signature
    14ef7cc
  30. Try to switch to llama model to see if it handles more tokens

    Verified signature
    c06b155
  31. Switched from using specific .txt file to referencing whole dataset

    Verified signature
    d1b814f