obsidian-copilot

obsidian-copilot copied to clipboard

Regarding Third-party Custom Models for Azure API

4

I am having some problem when trying to use a thiry-party custom model with a customed base URL. The following are my steps to where I am now, to give...

Ericc99

Cursor-like context menu

1

中文： 用 “send note to prompt” 功能跟笔记聊天时，笔记中途更改后，读取的还是原来的内容。 希望参考cursor的“add context”功能，每次发送一段新的信息，都读取一遍笔记，以便能读取到更改后的内容。 我个人使用的时候，这样的需求还是很多的。 比如： 我让AI根据笔记内容写一段话，插入笔记中。 因为这时候笔记已经更改，所以之后对笔记整体的修改或者扩写，需要考虑更改之后整体的上下文。 如果AI读取的内容不变的话，就不能很好的联系更改之后的上下文了。 English: When using the "send note to prompt" feature to chat with notes, if the note...

Wooden-Gear

FR: Support external vector store

1

My vault has about 5000 notes collected over the years, some of which are quite large. It also contains PDF documents, which would increase the size even more once they...

corani

**Is your feature request related to a problem? Please describe.** The menu in the editor now only has one built-in function option. Hope the sub-option can be expanded. **Describe the...

zhuxining

Per-Model Folder Settings for Obsidian Copilot

2

## Feature Request: Per-Model Folder Settings for Obsidian Copilot **Description:** Currently, Obsidian Copilot uses a single global folder for storing model-specific data, such as API keys and configuration settings. This...

logicsec

Optionally execute code in LLM output

3

Obsidian auto-executes code blocks for certain languages such as Mermaid. If you have a plugin like dataview, dataview and dataviewjs code are executed automatically too. Since LLM output is rendered...

logancyang

[FR] New mode: memory model

3

1. 通过增加一个点赞按钮，让用户积累有价值的，回答更好的问题对。 2. 将这些新的问题对积累到新的文件夹中（或文件中）。并且可以对问题对进行再修改 3. 结合现有的一些LLM记忆组件，比如mem0ai。或者简单将这些问题对作为问答的具有高可信度的前置知识。 4. 当然这部分问题对也是需要结合提问做相应的向量匹配。 5. 这样可以保证对相关问题的回答逐渐精准。但由于用户可能需要新的启发，所以应该将这个作为一个独立的新模式。 --- 1. By adding a "like" button, users can accumulate valuable question-answer pairs that lead to better responses. 2. These...

wwjCMP

Optimized support for the API for Qwen streaming (paragraph-by-paragraph answers)优化对于通义千问API的支持，让其能够流式传输（一段一段的回答）

1

I use a third party compatible with the OpenAI API to enable the Qwen model, but cross-domain needs to be enabled, otherwise it will not work properly. 我使用兼容OpenAI API的第三方可以启用通义千问模型，但是需要开启跨域，否则无法正常工作。 However,...

XSR-WatchPioneer

Any way to use lm-studio for QA mode?

7

I see lm-studio in general settings but not in QA settings. So far it works great for chat with lm-studio but I can't get it to work with QA mode....

tbergeron

Regenerate does not render custom prompt correctly

1

For example, `Summarize {activeNote}` works on the first try but doesn't work when I switched model and hit regenerate, active note doesn't get passed

logancyang