fix: changing control.py so that it doesnt execute unecessary functions and also changing llm.py to better prompts and better responses

changing auto-gptq version and torchvision

changing auto-gptq version and torchvision

changing auto-gptq version and torchaudio

changing auto-gptq version and torch

changing auto-gptq version

changing auto-gptq version

changing auto-gptq version

added auto-gptq

test from page 9 to 13

deleting peft

deleting autogptq

trying with another torch version

trying with another torch version

changed the llama2 version to the hf version

token in the tokenizer

added the token to the environ and the llm agent

added the token to hf

updating to real llama2

updating versions of packages

deleting pydantic

deleting the persistency of chroma client

tried upgrading torchaudi to 0.14.0

tried upgrading torchaudi to 0.13.0

tried upgrading torch to 0.13.0

tried downgrading torchvision to 0.12.0

tried downgrading pytorch to 1.11.0

tried downgrading pytorch to 1.11.0

tried downgrading pytorch

added a package urllib3

added the dll sqlite file

fix: deleted the +cu behind some packages

fix: updated all versions of packages

fix: versions of some packages

fix: deleted the wrong package

fix: added sqlite in requirements

changing versions

changing version

maybe

fix: update all packages

fix: deleted openai key import

fix: requirements.txt +cuda v2

fix: requirements.txt +cuda

fix: requirements.txt

first push from pages 9 to 25

initial commit