-
Notifications
You must be signed in to change notification settings - Fork 59
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
examples: adopt RAG examples for remote execution #3117
Conversation
can you elaborate on what non-local file local storage means ? |
c10760d
to
b279626
Compare
@@ -189,3 +192,6 @@ def run(job_input: IJobInput): | |||
data_file, | |||
confluence_reader.fetch_all_pages_in_confluence_space(parent_page_id), | |||
) | |||
|
|||
storage = DatabaseStorage(get_value(job_input, "storage_connection_string")) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
you are saving all information to one row in the database?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yeah. Because before it was saved to a file and I just replace the line to save to a file , to save it in DB.
I supposed I was too lazy to write a for loop
can you remove the duplicated classes? |
Updated description of PR |
83f8a14
to
276fca1
Compare
276fca1
to
395a22d
Compare
To be able to run the RAG DAG in a deployment we need non-local file local storage.
The POC was build to pass data between jobs using a local file. Since I want to deploy the jobs I need a way to pass data between them without that since they do not share a file system. Postgres based storage was created for that.
So moved created one and adopt it.
It's currently copied in both jobs. I will refactor it away after this PR.
I also ended up removing NLKT from everywhere. And also few doc fixes