{"categories":[{"label":"Text Processing","url":"https://skillfed.io/packages/category/text-processing/3"}],"enrichment":{"capability":"Python client library for submitting and managing document ingestion and processing jobs to the NVIDIA nv-ingest microservice, with support for extraction, splitting, and other data preparation tasks.","skillfed_tags":["document-processing","nvidia-ecosystem","data-preparation"],"use_cases":["Extract text and images from PDF documents in bulk and submit them to a processing pipeline via the nv-ingest service.","Split large documents into smaller chunks with configurable overlap for use in vector databases or semantic search systems.","Automate document ingestion workflows by defining job specifications with multiple extraction and splitting tasks.","Build data preparation pipelines that transform raw documents into structured, embeddings-ready text chunks.","Monitor and manage the status of long-running document processing jobs submitted to a remote nv-ingest microservice."],"what_it_does":"NV-Ingest-Client is a Python library that acts as a client interface to NVIDIA's nv-ingest microservice, enabling programmatic submission and management of document processing jobs. It abstracts the complexity of communicating with the microservice by providing a high-level API for defining jobs, configuring extraction and splitting tasks, and submitting them for processing. The library includes task factories for common operations like text extraction from PDFs and document splitting by word, sentence, or passage boundaries, along with a command-line interface for direct terminal use.\n\nThe package is designed for workflows that require batch processing of large document collections\u2014extracting text and images from PDFs, splitting documents into chunks for embedding or retrieval systems, and preparing data for downstream AI/ML pipelines. It depends on standard HTTP and data-handling libraries (httpx, requests, pydantic) to communicate with the microservice and manage job specifications, making it suitable for integration into data preparation and retrieval-augmented generation (RAG) systems.","worth_installing":"Yes, if you are building a document ingestion or data preparation pipeline that integrates with NVIDIA's nv-ingest microservice. The package has low install friction, active maintenance, permissive licensing, and no known vulnerabilities. Install only if you have a running nv-ingest microservice instance available and need Python-level control over job submission and task configuration; it is not a standalone tool."},"id":"nv-ingest-client","links":{"html":"https://skillfed.io/packages/nv-ingest-client","md":"https://skillfed.io/packages/nv-ingest-client.md","pypi":"https://pypi.org/project/nv-ingest-client/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-03-16","license_spdx":"Apache-2.0","license_treatment":"permissive","name":"nv-ingest-client","python_support":"supports_current","summary":"Python client for the nv-ingest service"},"popularity":{"monthly_downloads":85003,"position":13960,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"26.3.0"}