Skip to content

SDK - Patch parallel uploads #1468

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

Merged
merged 1 commit into from
May 15, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 14 additions & 16 deletions pgml-sdks/pgml/src/collection.rs
Original file line number Diff line number Diff line change
Expand Up @@ -533,23 +533,21 @@ impl Collection {

let mut set = JoinSet::new();
for batch in documents.chunks(batch_size as usize) {
if set.len() < parallel_batches {
let local_self = self.clone();
let local_batch = batch.to_owned();
let local_args = args.clone();
let local_pipelines = pipelines.clone();
let local_pool = pool.clone();
set.spawn(async move {
local_self
._upsert_documents(local_batch, local_args, local_pipelines, local_pool)
.await
});
} else {
if let Some(res) = set.join_next().await {
res??;
progress_bar.inc(batch_size);
}
if set.len() >= parallel_batches {
set.join_next().await.unwrap()??;
progress_bar.inc(batch_size);
}

let local_self = self.clone();
let local_batch = batch.to_owned();
let local_args = args.clone();
let local_pipelines = pipelines.clone();
let local_pool = pool.clone();
set.spawn(async move {
local_self
._upsert_documents(local_batch, local_args, local_pipelines, local_pool)
.await
});
}

while let Some(res) = set.join_next().await {
Expand Down
11 changes: 7 additions & 4 deletions pgml-sdks/pgml/src/lib.rs
Original file line number Diff line number Diff line change
Expand Up @@ -442,7 +442,10 @@ mod tests {
json!({
"title": {
"semantic_search": {
"model": "intfloat/e5-small"
"model": "intfloat/e5-small-v2",
"parameters": {
"prompt": "passage: "
}
}
},
"body": {
Expand All @@ -454,9 +457,9 @@ mod tests {
}
},
"semantic_search": {
"model": "hkunlp/instructor-base",
"model": "intfloat/e5-small-v2",
"parameters": {
"instruction": "Represent the Wikipedia document for retrieval"
"prompt": "passage: "
}
},
"full_text_search": {
Expand All @@ -475,7 +478,7 @@ mod tests {
documents.clone(),
Some(
json!({
"batch_size": 4,
"batch_size": 2,
"parallel_batches": 5
})
.into(),
Expand Down