基于graphrag源码使用conda安装graphrag
·
windowns下安装conda可以参考这篇文章:【安装conda】
1.创建graphrag安装环境
使用以下命令创建graphrag环境,这里,我们还指定了安装graphrag环境存储目录。注意,环境名称不能重复。
conda create --prefix D:\Work\AI\graphrag_conda_env
其中:
--prefix D:\Work\AI\graphrag_conda_env 指定了环境的安装目录。
注意,创建conda环境时,--name、--prefix不能同时使用。--name是把指定的环境名在conda默认目录进创建,--prefix则是使用指定的目录。
回车后开始执行环境创建,创建过程出现提示时输入y再回车:
3 channel Terms of Service accepted
Retrieving notices: done
Channels:
- defaults
Platform: win-64
Collecting package metadata (repodata.json): done
Solving environment: done
## Package Plan ##
environment location: D:\Work\AI\graphrag_conda_env
Proceed ([y]/n)? y
继续完成后续环境的创建,创建过程的信息如下:
C:\Users\Administrator>conda create --prefix D:\Work\AI\graphrag_conda_env
3 channel Terms of Service accepted
Retrieving notices: done
Channels:
- defaults
Platform: win-64
Collecting package metadata (repodata.json): done
Solving environment: done
## Package Plan ##
environment location: D:\Work\AI\graphrag_conda_env
Proceed ([y]/n)? y
Downloading and Extracting Packages:
Preparing transaction: done
Verifying transaction: done
Executing transaction: done
#
# To activate this environment, use
#
# $ conda activate D:\Work\AI\graphrag_conda_env
#
# To deactivate an active environment, use
#
# $ conda deactivate
C:\Users\Administrator>
2.激活graphrag安装环境
执行第一步的提示命令(如下所示)来激活graphrag安装环境。
conda activate D:\Work\AI\graphrag_conda_env
激活后,命令行效果如下:
C:\Users\Administrator>conda activate D:\Work\AI\graphrag_conda_env
(D:\Work\AI\graphrag_conda_env) C:\Users\Administrator>
3.下载graphrag源码
使用以下命令下载源码到D:\Work\AI\目录下
cd D:\Work\AI\
git clone https://github.com/microsoft/graphrag.git
4.基于源码安装graphrag
执行以下命令基于源码安装graphrag
cd D:\Work\AI\graphrag
pip install -e ".[default]"
看到以下信息表示安装成功:
Building wheels for collected packages: graphrag
Building editable for graphrag (pyproject.toml) ... done
Created wheel for graphrag: filename=graphrag-2.7.0-0.editable-py3-none-any.whl size=6421 sha256=5a67d99c56f15cf501604a295a68463748b04f707de4c0ba0f99aa98c897f801
Stored in directory: C:\Users\Administrator\AppData\Local\Temp\pip-ephem-wheel-cache-12i4rpxs\wheels\9a\0f\19\8061494895f503bc97ce936c7a80b531a05b8e085a9ae6ecdb
Successfully built graphrag
Installing collected packages: graphrag
Attempting uninstall: graphrag
Found existing installation: graphrag 2.7.0
Uninstalling graphrag-2.7.0:
Successfully uninstalled graphrag-2.7.0
Successfully installed graphrag-2.7.0
(D:\Work\AI\graphrag_conda_env) D:\Work\AI\graphrag>
输入以下命令可以进一步验证安装是否成功:
(D:\Work\AI\graphrag_conda_env) D:\Work\AI\graphrag>graphrag
安装成功时将返回以下信息:
Usage: graphrag [OPTIONS] COMMAND [ARGS]...
GraphRAG: A graph-based retrieval-augmented generation (RAG) system.
┌─ Options ────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ --install-completion Install completion for the current shell. │
│ --show-completion Show completion for the current shell, to copy it or customize the installation. │
│ --help Show this message and exit. │
└──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
┌─ Commands ───────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ init Generate a default configuration file. │
│ index Build a knowledge graph index. │
│ update Update an existing knowledge graph index. │
│ prompt-tune Generate custom graphrag prompts with your own data (i.e. auto templating). │
│ query Query a knowledge graph index. │
└──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────┘
(D:\Work\AI\graphrag_conda_env) D:\Work\AI\graphrag>
更多推荐

所有评论(0)