Catch llama.cpp errors in Node

[fmaclen]

I couldn't find anything in the docs regarding catch this error I'm getting, which I'm guessing means that my request is using too many tokens:

...............................................................................................
llama_new_context_with_model: n_ctx      = 4096
llama_new_context_with_model: freq_base  = 1000000.0
llama_new_context_with_model: freq_scale = 1
llama_new_context_with_model: kv self size  =  512.00 MB
llama_new_context_with_model: compute buffer total size = 294.13 MB
GGML_ASSERT: /my-project/node_modules/node-llama-cpp/llama/llama.cpp/llama.cpp:5867: n_tokens <= n_batch
zsh: abort      npm run dev
(base) me@computer my-project % 

I tried wrapping the instantiation of new LlamaChatSession with a try/catch, but the process running node-llama-cpp crashes completely.

Edit: this is running on macOS with an x86 CPU.

[giladgd]

There's currently an issue with prompts that are longer than the batchSize; it'll be fixed as part of #85.
For a workaround for now, see #76