Skip to content
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: request contextualization #54

Open
mhordynski opened this issue Jun 18, 2024 · 0 comments · May be fixed by #65
Open

feat: request contextualization #54

mhordynski opened this issue Jun 18, 2024 · 0 comments · May be fixed by #65
Assignees
Labels
feature New feature or request

Comments

@mhordynski
Copy link
Contributor

Feature description

db-ally should allow the provision of extra context for its runs, such as identifying the user who is asking the question. This context can be particularly useful in StructuredViews to craft responses in a personalized manner, taking into consideration parameters like the identity of the person asking the question or other relevant details.

Motivation

Given the following filters for searching employee database:

filter_by_department(department: str)
filter_by_skill(skill: str)

and user question like this:

Find me employees from my department that are skilled in Python

db-ally should be able to fecth user department from injected context and answer the question.

Additional context

We probably need to design how we want to indicate in IQL that we wish to use context rather than an explicit value. For example:

@decorators.view_filter()
def filter_by_department(self, department: str | SelfKeyword):
    ...

and later in IQL LLM could call filter like this:

filter_by_department(SELF)

@mhordynski mhordynski added the feature New feature or request label Jun 18, 2024
@jcierocki jcierocki linked a pull request Jun 26, 2024 that will close this issue
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
feature New feature or request
Projects
Status: In review
Development

Successfully merging a pull request may close this issue.

2 participants