-
安装Anaconda、pytorch
-
安装LightRAG
创建一个新的conda环境:
conda create -n LightRAG python=3.10
conda activate LightRAG
git clone https://github.com/HKUDS/LightRAG.git
安装LightRAG,推荐源码安装:
cd LightRAG
pip install -e .
安装ollama,可以使用修改后的安装脚本以加快速度:
curl -fsSL https://ollama.com/install.sh -o ollama_install.sh
chmod +x ollama_install.sh
./ollama_install.sh
准备demo数据:
curl https://raw.githubusercontent.com/gusye1234/nano-graphrag/main/tests/mock_data.txt > ./book.txt
修改源码:
./examples/lightrag_ollama_demo.py
import os
import logging
from lightrag import LightRAG, QueryParam
from lightrag.llm import ollama_model_complete, ollama_embedding
from lightrag.utils import EmbeddingFunc
WORKING_DIR = "./dickens"
logging.basicConfig(format="%(levelname)s:%(message)s", level=logging.INFO)
if not os.path.exists(WORKING_DIR):
os.mkdir(WORKING_DIR)
rag = LightRAG(
working_dir=WORKING_DIR,
llm_model_func=ollama_model_complete,
llm_model_name="qwen2",
llm_model_max_async=4,
llm_model_max_token_size=32768,
llm_model_kwargs={"host": "http://localhost:11434", "options": {"num_ctx": 32768}},
embedding_func=EmbeddingFunc(
embedding_dim=768,
max_token_size=8192,
func=lambda texts: ollama_embedding(
texts, embed_model="nomic-embed-text", host="http://localhost:11434"
),
),
)
with open("./book.txt", "r", encoding="utf-8") as f:
rag.insert(f.read())
# Perform naive search
print(rag.query("What are the top themes in this story?", param=QueryParam(mode="naive")))
# Perform local search
print(rag.query("What are the top themes in this story?", param=QueryParam(mode="local")))
# Perform global search
print(rag.query("What are the top themes in this story?", param=QueryParam(mode="global")))
# Perform hybrid search
print(rag.query("What are the top themes in this story?", param=QueryParam(mode="hybrid")))
确保llm_model_name设置为你使用的模型名称,例如qwen2
。
- 运行结果
python examples/lightrag_ollama_demo.py
参考:https://blog.csdn.net/wshzd/article/details/143157062
LightRAG环境搭建与运行示例
765

被折叠的 条评论
为什么被折叠?



