Skip to content

feat(core): make openai and mlx embedding progress bars conditional on build mode #379

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.

Sign up for GitHub

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
ASuresh0524 merged 2 commits into from
Jun 25, 2026
Merged

feat(core): make openai and mlx embedding progress bars conditional on build mode #379

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
92f0135
feat(core): make openai and mlx embedding progress bars conditional o…
pritpatel2412 Jun 23, 2026
13caafa
fix: format tqdm call to a single line to pass ruff-format
pritpatel2412 Jun 24, 2026
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
27 changes: 17 additions & 10 deletions packages/leann-core/src/leann/embedding_compute.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -481,9 +481,10 @@ def compute_embeddings(
base_url=provider_options.get("base_url"),
api_key=provider_options.get("api_key"),
provider_options=provider_options,
is_build=is_build,
)
elif mode == "mlx":
return compute_embeddings_mlx(texts, model_name)
return compute_embeddings_mlx(texts, model_name, is_build=is_build)
elif mode == "ollama":
return compute_embeddings_ollama(
texts,
Expand Down Expand Up @@ -848,8 +849,8 @@ def compute_embeddings_openai(
base_url: Optional[str] = None,
api_key: Optional[str] = None,
provider_options: Optional[dict[str, Any]] = None,
is_build: bool = False,
) -> np.ndarray:
# TODO: @yichuan-w add progress bar only in build mode
"""Compute embeddings using OpenAI API"""
try:
import openai
Expand Down Expand Up @@ -936,9 +937,12 @@ def compute_embeddings_openai(

total_batches = (len(texts) + max_batch_size - 1) // max_batch_size
batch_range = range(0, len(texts), max_batch_size)
batch_iterator = tqdm(
batch_range, desc="Computing embeddings", unit="batch", total=total_batches
)
if is_build:
batch_iterator = tqdm(
batch_range, desc="Computing embeddings", unit="batch", total=total_batches
)
else:
batch_iterator = batch_range
except ImportError:
# Fallback when tqdm is not available
batch_iterator = range(0, len(texts), max_batch_size)
Expand Down Expand Up @@ -967,8 +971,9 @@ def compute_embeddings_openai(
return embeddings


def compute_embeddings_mlx(chunks: list[str], model_name: str, batch_size: int = 16) -> np.ndarray:
# TODO: @yichuan-w add progress bar only in build mode
def compute_embeddings_mlx(
chunks: list[str], model_name: str, batch_size: int = 16, is_build: bool = False
) -> np.ndarray:
"""Computes embeddings using an MLX model."""
try:
import mlx.core as mx
Expand Down Expand Up @@ -999,9 +1004,11 @@ def compute_embeddings_mlx(chunks: list[str], model_name: str, batch_size: int =
try:
from tqdm import tqdm

batch_iterator = tqdm(
range(0, len(chunks), batch_size), desc="Computing embeddings", unit="batch"
)
batch_range = range(0, len(chunks), batch_size)
if is_build:
batch_iterator = tqdm(batch_range, desc="Computing embeddings", unit="batch")
else:
batch_iterator = batch_range
except ImportError:
batch_iterator = range(0, len(chunks), batch_size)

Expand Down
Loading