Skip to content

Clean up nemo-retriever dependencies #2180

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

Closed
colesmcintosh wants to merge 1 commit into from
+177 −21
Closed

Clean up nemo-retriever dependencies #2180

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
20 changes: 15 additions & 5 deletions nemo_retriever/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,26 +52,34 @@ dependencies = [
# HTTP clients
"httpx>=0.27.0",
"requests>=2.32.5",
"aiohttp>=3.12.0",
"urllib3>=2.7.0",
# Utilities
"pydantic>=2.8.0",
"rich>=13.7.0",
"universal-pathlib>=0.2.0",
"numpy>=1.26.0",
"python-dateutil>=2.9.0",
"debugpy>=1.8.0",
"fsspec>=2025.5.1",
"s3fs>=2025.5.1",
"fastparquet>=2024.11.0,<2026",
# Core ingest packages
# Document parsing and NIM client libs
"pypdfium2==4.30.0",
"pillow==12.2.0",
"opencv-python-headless>=4.8.0",
"scikit-learn>=1.6.0",
"scipy>=1.11.0",
"nltk>=3.9.4",
"markitdown",
"langchain-nvidia-ai-endpoints>=0.3.0",
"unstructured-client",
# Default VDB solution
"lancedb",
# gRPC client for Parakeet/Riva ASR. Required for ASRCPUActor when it
# targets the public NVCF Parakeet endpoint (the default) or any remote NIM.
"grpcio",
"nvidia-riva-client>=2.25.1",
]

Expand All @@ -94,7 +102,6 @@ service = [
"glom",
"easydict",
"addict",
"scikit-learn>=1.6.0",
"psutil>=5.9.0",
"apscheduler>=3.10",
# Audio resampling used by ParakeetClient
Expand All @@ -109,7 +116,6 @@ local = [
"transformers>=4.57.6,<5",
"tokenizers>=0.21.1",
"accelerate==1.12.0",
"opencv-python-headless>=4.8.0",
"torch==2.11.0; sys_platform == 'linux'",
"torch==2.11.0; sys_platform == 'win32'",
"torch==2.11.0; sys_platform == 'darwin'",
Expand All @@ -120,7 +126,6 @@ local = [
"einops",
"easydict",
"addict",
"scikit-learn>=1.6.0",
"timm==1.0.22",
"albumentations==2.0.8",
"nemotron-page-elements-v3>=0.dev0",
Expand All @@ -141,11 +146,10 @@ local = [
]

# ── Multimedia — audio/ASR and SVG rendering ────────────────────────────────
# soundfile + scipy enable local Parakeet ASR on audio/video content.
# soundfile enables local Parakeet ASR on audio/video content.
# cairosvg enables SVG-to-image rendering (requires libcairo system library).
multimedia = [
"soundfile>=0.12.0",
"scipy>=1.11.0",
"cairosvg>=2.7.0",
"librosa>=0.10.2",
]
Expand Down Expand Up @@ -189,6 +193,12 @@ dev = [
"pytest>=8.0.2",
]

test = [
# MoviePy 2.x caps Pillow below 12; core currently pins Pillow 12.2.0.
"moviepy<2",
"pytest>=8.0.2",
]

# ── Convenience: full install ─────────────────────────────────────────────────
all = [
"nemo_retriever[service,local,multimedia,nemotron-parse,tabular,benchmarks,llm]",
Expand Down
Loading