Index of every page on this site: llms.txt
All skills
langchain-ai avatar

/gpu-document-processing

@3748a9e
by LangChainlangchain-ai/deepagents31k stars
4,447
Run it yourself

Use when processing large PDFs, document collections, or bulk text extraction tasks that benefit from GPU-accelerated processing. Triggers when the user provides large documents or needs bulk document analysis.

Use this Skill: https://skilld.dev/gh/langchain-ai/deepagents/gpu-document-processing

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈59 tokens for metadata: the name and description. ≈871 when used: this file.

Description uses 2.9% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈236 characters, or 2.9%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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)

Workflow

  1. Receive document reference from the orchestrator
  2. Determine processing type (extraction, analysis, embedding)
  3. Send to GPU sandbox for processing
  4. Collect structured results (text, tables, embeddings)
  5. Write findings to /shared/ for the orchestrator to synthesize

Processing Large Document Collections

For multiple documents:

  1. Process documents in parallel batches (3-5 concurrent)
  2. Extract key metadata first (title, date, author, page count)
  3. Generate per-document summaries
  4. Cross-reference findings across documents
  5. Write consolidated findings with per-document citations

Output Format

When reporting document processing results:

  • Include document metadata (filename, pages, size)
  • Structure extracted content by section/chapter
  • Format tables as markdown tables
  • Include page references for all extracted content
  • Note any extraction quality issues (scanned images, corrupted pages)

Integration with NVIDIA NIM

For production deployments, GPU document processing can leverage:

  • NVIDIA NeMo Retriever: GPU-accelerated embedding and retrieval
  • NVIDIA RAPIDS cuDF: Tabular data processing from extracted tables
  • NVIDIA Triton: Scalable inference for document classification models

See NVIDIA's NIM documentation for self-hosted deployment options.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts8mo4 checks · Risk SAFE
  • Gen Agent Trust Hub8mo

    This skill provides architectural guidance for GPU-accelerated document processing and contains no executable code or scripts. It outlines workflows for processing large PDFs and document collections using the sandbox-as-tool pattern. No security concerns were detected within the documentation-only content provided.

  • Socket8mo

    No alerts

  • Snyk8mo

    Risk: LOW · No issues

  • Runlayer8mo

    1 file scanned · No issues

Signed by skilld at 3748a9e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 4 hours ago.

Activeupdated 8 months ago

README badge

README badge for langchain-ai/deepagents/gpu-document-processing