On 14/7/24 13:52, Emanuel Berg wrote:
jeremy ardley wrote:
Then create a prompt/context with the search text and
instructions to generate a similarity index and report any
that meet some threshold.
You will have to get the results in some format such as json
and post process
You may want to get ChatGPT 4 to help you craft the
general prompt.
Okay, context is context and query is the question after
the context.
But then what is the prompt and what is the general prompt?
Ask ChatGPT4 . Explain what you are trying to do and get it to give you
a suitable context and prompt
localdocs
There are no hits for that in the man page, maybe it is called
something else.
Is the idea to have a big context locally in directories
and stuff? That should be supported but maybe it isn't.
localdocs contains text you trust that can be used in responses in
preference to something synthesised from the internet.
My suggestion is to use localdocs as the text you want to search and the
context is how to match and the prompt is the string you want to match.
