HackerLLM
1.0.0
本項目基於vue(前端)以及fastapi(後端),通過調用bce-embedding模型進行向量數據庫文本嵌入,結合到prompt調用通義前文qwen-long長對話模型,實現特定領域的問答。同時vue引入vuetify組件實現對https://www.hackthebox.com 網站的分析結果進行可視化展示
適用於ubuntu linux(也適用於windows本地運行)
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 zshsudo apt-get update
sudo apt-get install nodejs並且在main.py中配置api_key,詳見: https://help.aliyun.com/zh/dashscope/developer-reference/acquisition-and-configuration-of-api-key?spm=a2c4g.11186623.0.0.42124937yljUMp
main.py中更改代碼段 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
)將model_name改為你下載好後放的路徑
SWS3023 Web Mining Group1
Welcome pull request