Logan Yang

Chapter 15 small issue in train

2

`bs` is not defined and should probably be `batch_size` ```python def train(model, input_data, target_data, batch_size=500, iterations=5): criterion = MSELoss() optim = SGD(parameters=model.get_parameters(), alpha=0.01) n_batches = int(len(input_data) / batch_size) for iter...

Just released Copilot for Obsidian v2.4.8 with Ollama local model integration. Thank you all for your awesome work on Ollama!

Ollama serve fails silently when an input is too long

6

When I use `ollama serve` and provide a context of ~30k tokens with a mistral model that has a max context window of 32768, the server doesn't show any error...

The "path" argument must be of type string or an instance of URL. Received undefined

5

### System Info transformers.js version: 2.14.0 MacOS Sonoma 14.2.1 NodeJS: v19.8.1 React: v18.2.0 ### Environment/Platform - [ ] Website/web-app - [ ] Browser extension - [ ] Server-side (e.g., Node.js,...

Codebase retrieval mode doesn't properly answer using the context

4

### Before submitting your bug report - [X] I believe this is a bug. I'll try to join the [Continue Discord](https://discord.gg/NWtdYexhMs) for questions - [X] I'm not able to find...

Continuing #331, expanding the custom retriever with full-text search support

Currently doesn't work, opened issue: https://github.com/langchain-ai/langchainjs/issues/4526

New Chat does not stop streaming

1

**Describe the bug** Right now the new chat button doesn't disrupt ongoing streaming **To Reproduce** Click new chat when it's streaming **Expected behavior** New chat should disrupt streaming like Stop...

Just like the ChatGPT web version. https://github.com/logancyang/obsidian-copilot/issues/190

Fixes #408. However, the answer quality is quite problematic. It seems LM Studio only support these 2 embedding models and the context length is fixed to 512, which won't work...