Marius Nita

Isn't it kinda strange to pass a view into a model? Normally a model is view-agnostic.

So this would be a config object nested in the options object?

Yep! So if a module system is available, you don't want it to attach to the global namespace, and instead register itself as a module. If there's no module system...

That could be fine but I think the more significant bit is to decompose agentscript into individually-meaningful modules that can be imported separately. Import only patches, only agents, a renderer,...

A simple thing to do would be to support the Python `Future` interface http://pythonhosted.org/futures/#future-objects It has `cancel()`, `running()`, `done()`, `result(timeout)`, and `add_done_callback(cb)`.

I just tried, and I don't get any errors with the vector or list indexes. BTW, I just noticed the vector index is 20x cheaper and faster to create, and...

Seeing the same error when using the `code-davinci-002` model with the vector index: ```py llm_predictor = gpt_index.LLMPredictor( llm=langchain.OpenAI( temperature=0, model_name="code-davinci-002" ) ) index = gpt_index.GPTSimpleVectorIndex( docs, llm_predictor=llm_predictor ) ``` >...

@jerryjliu This is likely a bad example because it's probably not useful to feed SVGs into gpt-index; nonetheless this causes gpt-index to crash: https://www.roojs.org/roojs1/fonts/nunito/nunito-v16-latin-italic.svg Example program: ```py filename = "nunito-v16-latin-italic.svg"...

The same file causes GPTTreeIndex to fail: ```py filename = "nunito-v16-latin-italic.svg" with open(filename) as f: contents = f.read() index = gpt_index.GPTTreeIndex( [gpt_index.Document(contents)], ) ```

Can't speculate on the root cause, but I would recommend that you put the constructor in the thread too. Something like: ```py def thread(input_queue, output_queue, stop_event): gpt = ChatGPT() while...