managed-ingestion-service
Scale document ingestion into Amazon OpenSearch using OSIS pipelines. Upload pre-chunked JSONL to S3 for indexing, or send raw PDFs to the cloud for automatic parsing and embedding. Supports both OpenSearch Service domains and Serverless collections.
Managed Ingestion Service ingests documents into Amazon OpenSearch at scale via OSIS pipelines from S3.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-22
Managed Ingestion Service ingests documents into Amazon OpenSearch at scale via OSIS pipelines from S3. Scale document ingestion into Amazon OpenSearch using OSIS pipelines. Upload pre-chunked JSONL to S3 for indexing, or send raw PDFs to the cloud for automatic parsing and embedding. Supports both OpenSearch Service domains and Serverless collections.
Use it when
- managed-ingestion-service uses OpenSearch Ingestion Service (OSIS) pipelines as managed connectors between cloud storage and OpenSearch.
- Yes.
Verify before relying
Read SKILL.md below before installing (2 files). Open directory: indexed for reading, not audited.
Install
opensearch-project/opensearch-agent-skills/managed-ingestion-service · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How to ingest documents into OpenSearch at scale?
managed-ingestion-service enables large-scale document ingestion through OSIS pipelines that connect S3 sources directly to OpenSearch domains or Serverless collections. You can upload pre-chunked JSONL files or raw PDFs; the service handles parsing, chunking, and indexing automatically with optional semantic enrichment including automatic embeddings.
What is an OSIS pipeline and how do I set one up?
managed-ingestion-service uses OpenSearch Ingestion Service (OSIS) pipelines as managed connectors between cloud storage and OpenSearch. Set up involves configuring a pipeline via YAML that specifies your S3 bucket as source, document processing options (PDF/DOCX extraction, chunking), and your target OpenSearch domain or Serverless collection as sink.
Can I upload PDF to Amazon OpenSearch from S3?
Yes. managed-ingestion-service supports uploading raw PDF and DOCX files from S3 buckets to OpenSearch. The OSIS pipeline automatically extracts text, applies semantic enrichment, and indexes documents into your OpenSearch domain or Serverless collection without manual preprocessing.
How does managed-ingestion-service handle semantic enrichment?
managed-ingestion-service can automatically apply semantic enrichment during ingestion, including automatic sparse embeddings and dense vector generation. This enrichment happens within the OSIS pipeline, transforming raw documents into searchable, semantically-aware indexed content ready for hybrid or vector search queries.
What document formats does managed-ingestion-service support?
managed-ingestion-service handles pre-chunked JSONL files and raw cloud documents in PDF and DOCX formats. JSONL chunks can be uploaded directly from S3 for immediate indexing, while raw PDFs and DOCX files are automatically extracted, parsed, and chunked before indexing into OpenSearch.
Can I migrate my local document workflow to managed-ingestion-service?
Yes. managed-ingestion-service simplifies migration by replacing local ingestion infrastructure with managed OSIS pipelines. Upload your documents to S3, configure the pipeline to point to your bucket and target OpenSearch domain or Serverless collection, and the service handles all cloud-based processing and indexing automatically.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Managed Ingestion Service
Overview
Ingest documents into Amazon OpenSearch at scale via OSIS pipelines. Supports both Amazon OpenSearch Service (AOS) domains and Amazon
(truncated - see the full file via the links below)
File tree — 2 files
skills/opensearch-skills/cloud/managed-ingestion-service/SKILL.md
skills/opensearch-skills/cloud/managed-ingestion-service/iam-setup.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Ingest documents into OpenSearch at scale using OSIS pipelines”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Cloud is a category skill for deploying OpenSearch search applications to AWS infrastructure. It guides you through provisioning Amazon OpenSearch Service domains or Serverless collections, configuring IAM roles, setting up Bedrock connectors for ML models, and migrating local setups to the cloud.
ingest is a category skill for transforming unstructured files into JSONL chunks on your machine. It handles PDF, DOCX, and PPTX formats through the document-processing skill, which uses Docling to produce search-ready output without requiring cloud infrastructure or AWS.
OpenSearch Launchpad is your guided path from initial requirements to a fully operational search system. It handles data ingestion, strategy selection (keyword, semantic, hybrid, or agentic), and deployment to either local Docker or Amazon OpenSearch Serverless. The skill walks you through architecture planning and launches a search UI ready for queries.
Document Processing transforms unstructured files into indexed-ready JSONL chunks using the open-source Docling library, running entirely on your machine. Output includes text, headings, source file references, and page numbers for direct ingestion into OpenSearch.
This skill guides you through building complete search applications on OpenSearch, covering index setup, document processing, and multiple search strategies including BM25, semantic, hybrid, and agentic approaches. Deploy ML models, ingest PDFs and other documents, and evaluate search quality end-to-end.
Provision and configure Amazon OpenSearch Service domains or Serverless collections, then deploy your search configurations to AWS. Handles infrastructure setup, IAM role configuration, Bedrock connector integration, and supports both managed domains and serverless deployments with optional agentic search capabilities.
More skills opensearch-skills (Apache-2.0) · aoss-nextgen-provisioning (Apache-2.0) · trace-analytics (Apache-2.0)