Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).
Although I believe the problem is jinja not accepting string literals. Adding some kind of new-line preserving transformation here would probably be ideal, I think?
🐛 Describe the bug
In below image, you can see that in harness visualize, where it should have been some output, there is nothing.
I would treat this as a bug, just because string literals are so ubiquitous for python-based LLM apps now it would be crazy to not support it