gpu-document-processing

A tool for processing large PDF files and document collections with a graphics processor (GPU), including text extraction, chunking, and creating document embeddings.

In plain words
What is it for?
Extracting text and structured data from large or unstructured documents, splitting bulk text into chunks, and creating embeddings for document collections.
Why use it?
It moves heavy document-processing work to a GPU, which can help when handling long PDFs or many files at once. The coding agent can then use the returned structured results for further analysis.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/langchain-ai/deepagents/gpu-document-processing
Any agent
npx skills add langchain-ai/deepagents --skill gpu-document-processing
Clone the repo
git clone --depth 1 https://github.com/langchain-ai/deepagents

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 745 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00041 $0.00745
Opus 5 $0.00020 $0.00373
Sonnet 5 $0.00008 $0.00149
Haiku 4.5 $0.00004 $0.00075

Measured 2d ago against content hash 80fad4867bc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gpu-document-processing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

examples/nvidia_deep_agent/skills/gpu-document-processing/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GPU Document Processing Skill

Process large documents and document collections using GPU-accelerated tools. This skill uses the sandbox-as-tool pattern: the agent runs on CPU for reasoning, and sends document processing work to a GPU-equipped environment.

When to Use This Skill

Use this skill when:

  • Processing large PDF files (50+ pages)
  • Analyzing collections of documents (10+ files)
  • Extracting structured data from unstructured documents
  • Performing bulk text extraction and chunking
  • Generating embeddings for large document sets
  • The user uploads or references large documents for analysis

Architecture: Sandbox as Tool

This skill follows the sandbox-as-tool pattern for GPU execution:

  1. Agent reasons on CPU - planning, synthesis, report writing
  2. Processing sent to GPU sandbox - document parsing, embedding, extraction
  3. Results returned to agent - structured output for further analysis

This separation ensures:

  • API keys stay outside the sandbox (security)
  • Agent state persists independently of processing jobs
  • Processing can be parallelized across documents
  • Cost-efficient: GPU used only during processing, not during reasoning

Capabilities

PDF Text Extraction

Extract text content from PDF documents with layout preservation:

  • Headers, paragraphs, lists, and tables detected separately
  • Page numbers and section boundaries preserved
  • Multi-column layout handling

Tabular Data Extraction

Extract tables from documents into structured formats:

  • PDF tables to CSV/DataFrames using GPU-accelerated parsing
  • Automatic column type detection
  • Handles merged cells and multi-row headers

Document Chunking

Split large documents into meaningful chunks for analysis:

  • Semantic chunking (by topic/section boundaries)
  • Fixed-size chunking with overlap for embedding
  • Configurable chunk sizes (default: 512 tokens)

Embedding Generation

Generate vector embeddings for document chunks:

  • Uses NVIDIA NeMo Retriever NIM for GPU-accelerated embedding
  • Supports batch processing for large document sets
  • Compatible with standard vector stores (Milvus, ChromaDB)

Read the full file on GitHub · 94 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 94 lines · 41 tokens per session scan A 80fad4867bc9

Subscribe to this mod's changes

gpu-document-processing is a skill published in the GitHub repository langchain-ai/deepagents (28,721 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 745 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.