update@Wikipedia

This commit is contained in:
yanqiang 2023-04-19 14:00:09 +08:00
parent 947602b15e
commit 665354c3b0
1 changed files with 17 additions and 3 deletions

View File

@ -22,6 +22,19 @@ https://github.com/yanqiangmiffy/Chinese-LangChain
- 显存12g实际运行9g够了
- 运行内存32g
### 运行环境
```text
langchain
gradio
transformers
sentence_transformers
faiss-cpu
unstructured
duckduckgo_search
mdtex2html
chardet
cchardet
```
## 🚀 特性
- 📝 2023/04/19 发布45万Wikipedia的文本预处理语料以及FAISS索引向量
@ -44,9 +57,10 @@ https://github.com/yanqiangmiffy/Chinese-LangChain
### 知识库向量索引
| 知识库数据 |FAISS向量|
|--------|----|
|💹 [大规模金融研报知识图谱](http://openkg.cn/dataset/fr2kg)|链接https://pan.baidu.com/s/1FcIH5Fi3EfpS346DnDu51Q?pwd=ujjv 提取码ujjv |
| 知识库数据 |FAISS向量|
|--------------------------------------------------|----|
| 截止去年九月的130w条中文维基百科处理结果和对应faiss向量文件 @[yubuyuabc](https://github.com/yubuyuabc) |链接https://pan.baidu.com/s/1Yls_Qtg15W1gneNuFP9O_w?pwd=exij 提取码exij|
| 💹 [大规模金融研报知识图谱](http://openkg.cn/dataset/fr2kg) |链接https://pan.baidu.com/s/1FcIH5Fi3EfpS346DnDu51Q?pwd=ujjv 提取码ujjv |
## 🔨 TODO