HackerLLM Download - HackerLLM Source code download

HackerLLM

Other source code

1.0.0

Download

HackerLLM

Introduction

This project is based on vue (front-end) and fastapi (back-end). It embeds vector database text by calling the bce-embedding model, and combines it with the propt to call the qwen-long long dialogue model of the previous text of the Tongyi text to realize Q&A in specific fields. At the same time, vue introduced the vuetify component to visually display the analysis results of https://www.hackthebox.com website

run

Suitable for ubuntu linux (also suitable for running locally in windows)

Install anaconda/miniconda and initialize

mkdir -p ~ /miniconda3
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~ /miniconda3/miniconda.sh
bash ~ /miniconda3/miniconda.sh -b -u -p ~ /miniconda3
rm -rf ~ /miniconda3/miniconda.sh

~ /miniconda3/bin/conda init bash
~ /miniconda3/bin/conda init zsh

The Python library required for downloading the project is mainly dashscope, langchain, fastapi, chromadb, etc. If there is an error, you can just pip install xx.
Install node.js (not necessary)

sudo apt-get update 
sudo apt-get install nodejs

Apply for model api_key for details, please see https://help.aliyun.com/zh/dashscope/ At least as of July 24, there are still quite a lot of free quotas.

And configure api_key in main.py , see: https://help.aliyun.com/zh/dashscope/developer-reference/acquisition-and-configuration-of-api-key?spm=a2c4g.11186623.0.0.42124937yljUMp

Download the huggingface model download address: https://huggingface.co/maidalun1020/bce-embedding-base_v1/tree/main After downloading, change the code segment in main.py

 model_name = r"/root/huggingface_cache/bce-embedding-base_v1"
model_kwargs = { 'device' : 'cpu' }
encode_kwargs = { 'normalize_embeddings' : False }
hfembedding = HuggingFaceEmbeddings (
    model_name = model_name ,
    model_kwargs = model_kwargs ,
    encode_kwargs = encode_kwargs
)