Simon Willison

Related: - https://github.com/simonw/llm/issues/1027#issuecomment-2878697664 > Would also be neat if exceptions were shown in a different color in the `--td` and the logs. Currently errors are turned into undifferentiated strings.

I just tried to merge `main` back into this and it was a real mess, because the work on tool attachments in #1142 modified the code that this bit had...

I lost some time to this one today.

Got this working: ```bash llm tools ``` ``` Traceback (most recent call last): ... File "/Users/simon/Dropbox/Development/llm/llm/cli.py", line 2511, in tools_list tools: Dict[str, Union[Tool, Type[Toolbox]]] = get_tools() ~~~~~~~~~^^ File "/Users/simon/Dropbox/Development/llm/llm/__init__.py", line...

I hope I got that type stuff right in https://github.com/simonw/llm/pull/847/commits/2ce2510945382af203745d28a01e6c04359b029a - which cover what happens when you do `for chunk in model.prompt(...)` and the `execute()` method may return `str` or...

> Spin up a dummy model with annotations that I can start writing tests against Idea: I could have this model class live in the `llm` source code but NOT...

I have that `llm-debug` plugin now: ```python import llm from llm.examples import Markov, AnnotationsModel, AnnotationsModelAsync @llm.hookimpl def register_models(register): register(Markov()) register(AnnotationsModel(), AnnotationsModelAsync()) ``` Can't package and ship it until I have...

First question is how these should be stored. One way could be to add a `chunks` optional integer column to the `embeddings` table - that way when something is chunked...

Is there a simple basic starting point for chunking I could implement in a way that would let me add more advanced patterns in the future without breaking anything?

I think all embedding vectors go in the same place, the `embeddings` table. Whether or not they are for a whole document, or a section, or a sentence needs to...