langchain-ai/gpu-document-processing
examples/nvidia_deep_agent/skills/gpu-document-processing/SKILL.md
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.
$ install --global
skillsauthnpx skillsauth add langchain-ai/deepagents gpu-document-processingInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 8:47 PM2.5s1 file scanned
SKILL.md
- name:
- gpu-document-processing
- description:
- 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.
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:
- Agent reasons on CPU - planning, synthesis, report writing
- Processing sent to GPU sandbox - document parsing, embedding, extraction
- 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
- Receive document reference from the orchestrator
- Determine processing type (extraction, analysis, embedding)
- Send to GPU sandbox for processing
- Collect structured results (text, tables, embeddings)
- Write findings to /shared/ for the orchestrator to synthesize
Processing Large Document Collections
For multiple documents:
- Process documents in parallel batches (3-5 concurrent)
- Extract key metadata first (title, date, author, page count)
- Generate per-document summaries
- Cross-reference findings across documents
- 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.
Related Skills
langchain-ai/remember
testing
VerifiedTrustedCommunity
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture learnings.
20,805SKILL.mdUpdated Apr 15, 2026
langchain-ai/schema-exploration
data-ai
VerifiedTrustedCommunity
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
20,805SKILL.mdUpdated Apr 15, 2026
langchain-ai/query-writing
documentation
VerifiedTrustedCommunity
Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables.
20,805SKILL.mdUpdated Apr 15, 2026
langchain-ai/data-visualization
testing
VerifiedTrustedCommunity
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.
20,805SKILL.mdUpdated Apr 15, 2026