[RFC] 123(WIP) - 自定义知识库 Embedding 模型 #8487
Asuka109
started this conversation in
RFC | 特性开发
Replies: 1 comment 9 replies
-
|
Beta Was this translation helpful? Give feedback.
9 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
简述
本 RFC 提议为 LobeChat 的 Embedding 功能添加模型选择能力。目前 LobeChat 在进行文本向量化时仅能使用硬编码的
openai-text-embedding-3-small
模型,限制了用户的灵活性和应用场景。本提案旨在允许用户选择多种向量化模型,并在使用过程中根据需要切换不同模型。实现细节
maxDimension>=1024
并支持指定dimension
的向量化模型。交互界面
https://v0.dev/chat/ai-chatbox-settings-nR67t3ypwgN
Drawbacks
以下问题留待后续 RFC 讨论和实现。
Beta Was this translation helpful? Give feedback.
All reactions