ngz91/eunomia

Analyze your code locally using a GPT LLM.

⛩️ Ngz91 profile page ⛩️

🍜 About Me 🍜

Name: Nevio (蟻)

BSc. in Industrial Engineering, Software Developer.

Currently learning: Golang, Rust, and C++.

Hobbies: Guitar 🎸, Programming 💻, Ricing 🍙, Reading 📖.

Portfolio: https://ngz91.github.io/NgzPortfolio/ (Outdated)

Dotfiles & Guide: https://github.com/Ngz91/dotfiles/

Medium: https://medium.com/@neviogomez91

Random fact: CS2 Enyojer 🚬

Working on: LLM code assistant, CS Capsules & Stickers App,
   Pathfinding SFML application and Rust HTTP client terminal App.

🍙 Languages & Technologies 🍙

                    
                    
                   
       

eunomia's Issues

Error when Eunomia start

gitpod /workspace/Eunomia (master) $ python Eunomia.py start
Traceback (most recent call last):
  File "/workspace/Eunomia/Eunomia.py", line 200, in <module>
    eunomia.start()
  File "/workspace/Eunomia/Eunomia.py", line 72, in start
    llm = self._initialize_llm(self.llm, self.model_n_ctx, self.backend)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/workspace/Eunomia/Eunomia.py", line 154, in _initialize_llm
    return GPT4All(
           ^^^^^^^^
  File "/workspace/.pyenv_mirror/user/current/lib/python3.12/site-packages/pydantic/main.py", line 341, in __init__
    raise validation_error
pydantic.error_wrappers.ValidationError: 1 validation error for GPT4All
__root__
  Failed to retrieve model (type=value_error)

And my .env :
PERSIST_DIRECTORY=db
LLM = ggml-gpt4all-j-v1.3-groovy.bin
BACKEND = gptj
EMBEDDINGS_MODEL = all-MiniLM-L6-v2
MODEL_N_CTX = 1000
TARGET_SOURCE_CHUNKS = 6
IGNORE_FOLDERS = '["folder\\to\\ignore", "folder\\to\\ignore2"]'

And I have downloaded "ggml-gpt4all-j-v1.3-groovy.bin"

Thanks

Not all listed models work

Hi,

First off: thanks for this. Exactly what I wanted to build myself.

Second: not all listed models seem to be working on my Mac (Intel).

Working:

1. ggml-gpt4all-j-v1.3-groovy.bin

Not working: (gptj_model_load: invalid model file (bad magic))

1. ggml-gpt4all-l13b-snoozy.bin
2. ggml-nous-gpt4-vicuna-13b.bin