-
Notifications
You must be signed in to change notification settings - Fork 31
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
Realtime embedding updates #38
Conversation
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.
Very clean! LGTM
@@ -23,7 +25,8 @@ fn table( | |||
transformer: default!(String, "'text-embedding-ada-002'"), | |||
search_alg: default!(types::SimilarityAlg, "'pgv_cosine_similarity'"), | |||
table_method: default!(types::TableMethod, "'append'"), | |||
schedule: default!(String, "'* * * * *'"), | |||
// cron-like for a cron based update model, or 'realtime' for a trigger-based | |||
schedule: default!(String, "'realtime'"), |
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.
I like having options here for both approaches ✅
@@ -29,7 +28,7 @@ pub async fn handle_response<T: for<'de> serde::Deserialize<'de>>( | |||
// handle an OpenAI compatible embedding transform request | |||
pub async fn openai_embedding_request(request: EmbeddingRequest) -> Result<Vec<Vec<f64>>> { | |||
log!( | |||
"pg-vectorize: openai request size: {}", | |||
"pg-vectorize: embedding request size: {}", |
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.
Nice :)
vectorize.table
that handle row updates.schedule
parameter torealtime