-
Notifications
You must be signed in to change notification settings - Fork 42
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat(assistants): improve context #2105
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Originally posted by @nokome in #2096 (comment)
executionMessages
of the instruction - in addition this should betracing::error!
-ed so develops can see the issue.CodeChunk
e.g.hint
propertycontext.code_chunks
is empty (i.e. don't print header for these)instruction_block
andinstruction_inline
fields to theContext
and collect those that have accepted suggestions. The reasoning for this is...We know "few shot in-context learning" - pairs of example instruction / response - is very useful. Our system prompt templates have some in them. But instead of using generic ones, why not use pairs drawn from the current document (and, in the future, from the user's other documents). This is likely to give responses that match the users expectations and style a lot more closelyinstruction_inline.rs
withimpl Executable for InstructionInline
; this can be based largely onInstructionInline
and modifyinsert-code-expression
Executor.context
. Currently this is cleared each time the document is executed, so that there are not duplicate entries for code chunks. But ifExecutor.node_ids.is_some()
then we don't want to do that. Also we need to think about removing code chunks etc from the context when it the code chunk etc is remove from the document.examples/kernels
for exemplars of setup and naming - trying to provide the same example test examples across different kernels.The text was updated successfully, but these errors were encountered: