arc53/DocsGPT

Using Oracle Vector store

Open

#981 创建于 2024年6月5日

在 GitHub 查看
 (16 评论) (0 反应) (2 负责人)Python (13,691 star) (1,359 fork)batch import
applicationbackendgood first issuehelp wantedpython

描述

Discussed in https://github.com/arc53/DocsGPT/discussions/980

Can be added by creating a file here https://github.com/arc53/DocsGPT/tree/main/application/vectorstore

Will require concrete class similar to others.

Also looks like langchain supports it, which will make integration extra easy. https://python.langchain.com/v0.2/docs/integrations/vectorstores/oracle/#load-documents

贡献者指南

技术栈
python
领域
databaseapi
议题类型
feature
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
1-2 days
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
active
清晰度议题是否清楚说明期望改动、验收标准和下一步。
mostly clear
前置要求
PythonLangChainVector store patterns
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
30
研究方向
Review the discussion in #980 and existing vector store implementations in application/vectorstore, e.g., Weaviate. LangChain's Oracle integration (https://python.langchain.com/v0.2/docs/integrations/vectorstores/oracle/) provides a reference. The issue has two assignees, so check their progress or consider a different unassigned issue.