NVIDIA/NeMo-Retriever

View on GitHub

NeMo Retriever Library is a scalable, performance-oriented document content and metadata extraction microservice. NeMo Retriever Library uses specialized NVIDIA NIM microservices to find, contextualize, and extract text, tables, charts and images that you can use in downstream generative applications.

Stars: 3k
Forks: 349
Open beginner issues: 0
Indexed issues: 133
Avg merge: 1d 23h
Merged PRs (30d): 116

Dominant language: Python
License: Apache-2.0
Last GitHub push: Sep 18, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: good first issue

Beginner friendly Everything

Open All

133 open issues indexed

VideoFrameTextDedup global repartition overflows Arrow string offsets at multi-video scale Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

NVIDIA/NeMo-Retriever#2643 · 1 comment · Opened Sep 9, 2026
[FEA]: Add support for pulling content from URLs Open

feature request

NVIDIA/NeMo-Retriever#2626 · 1 assignee · Opened Sep 2, 2026
Feature request: generate retrieval-oriented VLM descriptions for extracted charts while preserving OCR text Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

NVIDIA/NeMo-Retriever#2620 · 1 comment · Opened Aug 31, 2026
[FEA]: Have store task use semantic chunk image naming Open

feature request

Difficulty 3/5 1-2 days Newbie friendliness 68/100

NVIDIA/NeMo-Retriever#2618 · Opened Aug 30, 2026
[FEA]: Provide linux/arm64 container images for NeMo Retriever Extraction on NGC Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA/NeMo-Retriever#2568 · Opened Aug 20, 2026
Derive page rasterization requirements from embedding configuration Open

NVIDIA/NeMo-Retriever#2513 · 1 comment · 1 assignee · Opened Aug 17, 2026
[BUG]: Default ingest pipeline via CLI skips OCR extract_text Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 64/100

NVIDIA/NeMo-Retriever#2443 · 1 comment · Opened Aug 7, 2026
Fix service-mode Compose config drift and NIM startup portability Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

NVIDIA/NeMo-Retriever#2424 · Opened Aug 3, 2026
Refresh CONTRIBUTING.md to match current repository practices Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

NVIDIA/NeMo-Retriever#2395 · 1 comment · Opened Jul 22, 2026
harness: add first-class dataset and ground-truth paths for portable single runs Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

NVIDIA/NeMo-Retriever#2390 · Opened Jul 21, 2026
[FEA]: Fully in-process Service query Open

feature request next-release

Difficulty 5/5 Over a week Newbie friendliness 45/100

NVIDIA/NeMo-Retriever#2373 · Opened Jul 16, 2026
Refocus PR Docker CI on validating the shipped service image Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

NVIDIA/NeMo-Retriever#2357 · Opened Jul 14, 2026
[FEA]: Run Fine tuned models in pipeline Open

feature request next-release

NVIDIA/NeMo-Retriever#2356 · 2 assignees · Opened Jul 14, 2026
[FEA]: Enable using VLM for answer generation Open

feature request next-release

NVIDIA/NeMo-Retriever#2354 · 1 assignee · Opened Jul 14, 2026
Persist LanceDB index metadata and resolve query embedding models automatically Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA/NeMo-Retriever#2346 · Opened Jul 13, 2026
[FEA]: Enable re-ranker with MCP tools Open

feature request next-release

NVIDIA/NeMo-Retriever#2344 · 1 assignee · Opened Jul 13, 2026
[FEA]: Explore GPU based page image rendering Open

feature request next-release

NVIDIA/NeMo-Retriever#2343 · 1 assignee · Opened Jul 13, 2026
[FEA]: Explore Dynamo/vLLM inference perf optimization Open

feature request next-release

Difficulty 5/5 Over a week Newbie friendliness 15/100

NVIDIA/NeMo-Retriever#2342 · Opened Jul 13, 2026
[FEA]: Reduce required client dependencies Open

feature request next-release

NVIDIA/NeMo-Retriever#2340 · 1 comment · 1 assignee · Opened Jul 13, 2026
[BUG] Propagate advertised ExtractParams fields to graph operators Open

bug python

NVIDIA/NeMo-Retriever#2324 · 1 comment · 1 assignee · Opened Jul 9, 2026
Unify normalized text chunking for HTML and plain-text inputs Open

NVIDIA/NeMo-Retriever#2320 · 1 assignee · Opened Jul 9, 2026
Base install cannot ingest HTML/TXT because tokenizer dependency is only in local extra Open

NVIDIA/NeMo-Retriever#2303 · 1 assignee · Opened Jul 6, 2026
[BUG]: Review Riva team's accuracy evaluation Open

bug

NVIDIA/NeMo-Retriever#2189 · 1 assignee · Opened Jun 1, 2026
[BUG]: Restore the portal and automated runners for RTX Pro 6k Open

bug next-release

NVIDIA/NeMo-Retriever#2188 · 1 assignee · Opened Jun 1, 2026
[BUG]: Support lancedb streaming ingest during ingestion job Open

bug next-release

NVIDIA/NeMo-Retriever#2187 · 1 assignee · Opened Jun 1, 2026
BUG]: NIMCache creation fails - template references undefined storageClass value Open

Difficulty 3/5 1-2 days Newbie friendliness 58/100

NVIDIA/NeMo-Retriever#1686 · 1 comment · Opened Mar 23, 2026
BUG]: Duplicate NEMOTRON_PARSE_HTTP_ENDPOINT env var causes upgrade failure when enabling nemotron_parse Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

NVIDIA/NeMo-Retriever#1685 · 1 comment · Opened Mar 23, 2026
[FEA]: Complete the async API by allowing async ingestion jobs for library (non-service) API Open

feature request next-release

NVIDIA/NeMo-Retriever#1674 · 2 comments · 1 assignee · Opened Mar 20, 2026
[BUG]: Audio ingestion does not automatically use a GPU resource Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 25/100

NVIDIA/NeMo-Retriever#1640 · Opened Mar 16, 2026
[BUG]: Helm chart NIMCache templates missing nodeSelector and tolerations fields Open

Difficulty 2/5 1-3 hours Newbie friendliness 62/100

NVIDIA/NeMo-Retriever#1636 · 1 comment · Opened Mar 16, 2026
[FEA]: to_markdown/to_markdown_by_page should differentiate by distinct document ingested Open

feature request

NVIDIA/NeMo-Retriever#1630 · 1 assignee · Opened Mar 14, 2026
[BUG]: Tables/Chart has missing text Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 55/100

NVIDIA/NeMo-Retriever#1615 · Opened Mar 13, 2026
[BUG]: not able to override NodeSelector for NIM Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 38/100

NVIDIA/NeMo-Retriever#1572 · Opened Mar 11, 2026
[BUG]: Traceid is not propogated correctly with pdf_split_page_count Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

NVIDIA/NeMo-Retriever#1564 · Opened Mar 11, 2026
[BUG]: With high concurrency/ingest rate, job just sit in redis but never get picked up for execution Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 28/100

NVIDIA/NeMo-Retriever#1551 · Opened Mar 10, 2026
[BUG]: single N/A value in embedding, whole file get rejected for parquet file s3 upload. Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 42/100

NVIDIA/NeMo-Retriever#1549 · Opened Mar 10, 2026
[BUG]: Clean up dependencies in `api/pyproject.toml` Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 68/100

NVIDIA/NeMo-Retriever#1392 · 1 comment · Opened Feb 10, 2026
[DOC]: What happens when extract method is none? Open

doc

Difficulty 3/5 1-2 days Newbie friendliness 45/100

NVIDIA/NeMo-Retriever#1154 · Opened Nov 12, 2025
[DOC]: Create a docs page explaining how Tracing works Open

doc

Difficulty 4/5 3-5 days Newbie friendliness 30/100

NVIDIA/NeMo-Retriever#1152 · Opened Nov 7, 2025
[BUG]: Retry for GRPC errors still at 5 but not 10 Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 45/100

NVIDIA/NeMo-Retriever#1139 · Opened Nov 3, 2025
[DOC]: Add docs for async ingestor API jobs Open

doc

Difficulty 3/5 1-2 days Newbie friendliness 65/100

NVIDIA/NeMo-Retriever#1134 · 1 comment · Opened Oct 30, 2025
[FEA]: Support embedding of custom content fields in the embedding stage Open

feature request

NVIDIA/NeMo-Retriever#1078 · 1 assignee · Opened Oct 7, 2025
[ALERT] Access to NVIDIA's Self-Hosted Runners is Expiring Open

nvidia-runners

Difficulty 2/5 1-3 hours Newbie friendliness 25/100

NVIDIA/NeMo-Retriever#1075 · Opened Oct 5, 2025
[BUG]: Redis SSL fails and isn't defined correctly for a connection pool Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 42/100

NVIDIA/NeMo-Retriever#1073 · Opened Oct 3, 2025
[BUG]: Deadlock (infinite loop) when paddle is not ready Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 45/100

NVIDIA/NeMo-Retriever#1052 · 3 comments · Opened Sep 22, 2025
[BUG]: Issue running Python API quickstart on macOS Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

NVIDIA/NeMo-Retriever#1049 · Opened Sep 19, 2025
[DOC]: Add LLM Prompt File for Documentation Standards Open

doc

Difficulty 3/5 1-2 days Newbie friendliness 35/100

NVIDIA/NeMo-Retriever#1046 · 1 comment · Opened Sep 18, 2025
[FEA]: Use asynccontextmanager to manage ingest_service life cycle Open

feature request

Difficulty 4/5 3-5 days Newbie friendliness 42/100

NVIDIA/NeMo-Retriever#969 · 1 comment · Opened Aug 13, 2025
[BUG]: Ingestion Issue: Subsequent Document Upload Re-ingests Previous Document with Significant Delay Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

NVIDIA/NeMo-Retriever#966 · 3 comments · 3 reactions · Opened Aug 13, 2025
[FEA]: Add utilities to the API that allow for stripping audio tracks from common video formats Open

feature request

NVIDIA/NeMo-Retriever#916 · 1 comment · 1 assignee · Opened Jul 25, 2025

NVIDIA/NeMo-Retriever

Get new issues in your inbox