fixes issue seen with some models in lm studio resulting in:
"The number of tokens to keep from the initial prompt is greater than the context length (n_keep: 4705>= n_ctx: 4096)"
Fixed char/token estimate, the old value was too optimistic,
causing the cap to allow more text than the budget allowed in actual tokens.
After RAG injection, estimates the system prompt token count.
If it exceeds ~3000 tokens, requests the next standard context size (8192, 16384, 32768, or 65536),
large enough to fit the prompt plus a 2048-token buffer for the conversation and response.
For Ollama, num_ctx is honoured per-request and will load the model with that context
window. For LM Studio, the parameter is silently ignored — but the tighter char
estimate will also reduce how much RAG text gets stuffed in, so it's less likely to
overflow.
Exisiting Ollama API support still functions as before. OpenAI vs
Ollama API mostly have the same features, however model file size is not
support with OpenAI's API so when a user chooses one of those then the
models will just show up as the model name without the size.
`npm install openai` triggered some updates in admin/package-lock.json
such as adding many instances of "dev: true".
This further enhances the user's ability to run the LLM on a different
host.
This adds a new setting in the chat app under "models & settings" where
the user can set "Remote Ollama URL" to an IP or hostname of another
device on the network running ollama which is also running with the
setting "OLLAMA_HOST=0.0.0.0:11434"
