seg_yinzy
/
dify-docs
mirror of https://github.com/langgenius/dify-docs.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

GITBOOK-38: change request with no subject merged in GitBook

pull/28/head
vincehe 2023-11-19 07:22:34 +00:00 committed by gitbook-bot
parent 419c4f2ea4
commit ffd33ab58a
No known key found for this signature in database
GPG Key ID: 07D2180C7B12D0FF
2 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
zh_CN/.gitbook/assets/image (129).png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 496 KiB

2
zh_CN/advanced/retrieval-augment/README.md
View File

@ -8,7 +8,7 @@
在下图中，当用户提问时 “美国总统是谁？” 时，系统并不是将问题直接交给大模型来回答，而是先将用户问题在知识库中（如下图中的维基百科）进行向量搜索，通过语义相似度匹配的方式查询到相关的内容（拜登是美国现任第46届总统…），然后再将用户问题和搜索到的相关知识提供给大模型，使得大模型获得足够完备的知识来回答问题，以此获得更可靠的问答结果。
<figure><img src="https://langgenius.feishu.cn/space/api/box/stream/download/asynccode/?code=ZTIxODY4NzllOGZhNjg0YjgwNjEyODQ2ZjQ3MTk2NDJfajZUU1RzblI4RHY2bUpIZW5JNmRLd01JbmNINDhra3ZfVG9rZW46U0xjaWJ0d2FDb1JaR2J4eUFJWGN4NHY1bjVnXzE3MDAzMTk4MzE6MTcwMDMyMzQzMV9WNA" alt="" width="563"><figcaption></figcaption></figure>
<figure><img src="../../.gitbook/assets/image (129).png" alt=""><figcaption><p>RAG 基本架构</p></figcaption></figure>
**为什么需要这样做呢？**