mirror of
https://github.com/deepseek-ai/DeepSeek-R1.git
synced 2026-11-05 00:47:42 +00:00
[GH-ISSUE #323] 不本地部署如何实现模型微调,建立知识库,deepseek api能理解并回答知识库里的内容 #252
Labels
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
deepseek-ai/DeepSeek-R1#252
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @zhuyongbo100 on GitHub (Feb 8, 2025).
Original GitHub issue: https://github.com/deepseek-ai/DeepSeek-R1/issues/323
官方文档未提供相关说明,网上查到的有通过本地部署,Rag向量化数据,实现读取本地知识库并回答,deepseek api能实现吗?
@deepsicker commented on GitHub (Feb 8, 2025):
可以的 你可以用agent的形式
https://www.yuque.com/unreal/gpynrn/qxkg1bmxdpq3iumw
@zhengzhen0417 commented on GitHub (Feb 8, 2025):
可以看这个教程,确实可以https://www.bilibili.com/video/BV1vrNAegEiz/?spm_id_from=333.1391.0.0&vd_source=8477480390dde3da9865f36968e92f40
@Pines-Cheng commented on GitHub (Feb 8, 2025):
可以试试 Coze 等平台。
@icejean commented on GitHub (Feb 15, 2025):
RAG是外挂的知识库,模型不需要微调,直接调LLM 的API即可。可以参阅我的GraphRAG研究系列文章《GraphRAG课题研究总结》。