--- title: PrimeCut — Document Ingestion and RAG Chunking ⬣ POMA AI description: PrimeCut: patent-protected document ingestion & RAG chunking. Structure-aware across 50+ filetypes. 23% of the tokens, 100% recall vs. Unstructured.io. Free tier. canonical: https://www.poma-ai.com/products/primecut-rag-ingestion-chunking generated: Markdown variant of the page above, built from the prerendered HTML --- # Our secret sauce Document Ingestion and RAG Chunking PrimeCut is POMA AI's patent-protected document ingestion & RAG chunking core — structure-aware across text, tables, scanned PDFs (OCR), and 50+ filetypes. The structural awareness matters most on technical documents — research papers, financial filings, engineering specs — where naive chunkers split a single argument across three chunks and break retrieval. Drop it into your existing pipeline; retrieval, embeddings, and vector store stay where they are. [ Try for free ](https://console.poma-ai.com/?mode=register)[ Read the docs ](https://www.poma-ai.com/docs/) ## How Hierarchical Ingestion and Chunking Works: Structure to RAG-Ready Chunks How POMA PrimeCut Sees Your Document Hierarchy Every document carries an internal logic: a hierarchy of headings, sub-sections, tables, lists, and supporting elements that define what content belongs together and why. That structure is not decoration — it is the semantic map of the document. Standard ingestion pipelines discard this map. They extract raw text and hand it to a chunker that has no knowledge of where one idea ends and another begins. PrimeCut understands your document’s content hierarchy before chunking — preserving structural relationships, eliminating context poisoning, and producing semantically coherent chunksets that make every downstream RAG component more accurate by default. ### Text, Chart & Table — One Document, Fully Resolved MSCI World Index (USD) Factsheet, Sep 2025 Chunksets 0–5 of 43 Shared root Shared hierarchy Leaf (unique to one chunkset) Text Image description Table data Source: MSCI World Index (USD) factsheet — processed by POMA PrimeCut into 43 chunksets from 85 structural chunks. [ Try for Free ](https://console.poma-ai.com/?mode=register) ## What you get back Every upload returns a POMA archive. Send us a document — any supported filetype — and you get back a POMA archive: a zip containing the structured SDK output your pipeline can read directly. No glue code, no per-file branching. The archive bundles the chunks your retrieval layer consumes alongside the intermediate artifacts that produced them, so you can debug, re-process, or surface source content without re-running the pipeline. [Read the POMA archive reference](https://poma-ai.com/docs/sdk/reference/poma-archive) ### Inside a POMA archive Core SDK files `chunks.json` Extracted chunks with hierarchy and page references. `chunksets.json` Grouped chunk collections for retrieval. `image_sources.json` Image references and metadata (when applicable). `assets/` Supporting files referenced by chunks (when applicable). Extended processing artifacts Every archive also carries the intermediate artifacts that produced those chunks: input as markdown and HTML, structurally-indented plain text, AI/OCR image descriptions, extracted tables, pre-processed source files, and archive- and content-level metadata. ## What it does From document to embedding-ready chunkset, one call. PrimeCut treats each document as a structure, not as just bytes. It detects the hierarchy of your document - headings, subsections, and clauses. This allows it to preserves clauses with their definitions, tables with their captions, and graph content in their section. It then emits chunksets that your embedding model can use directly. - ### Structure-aware parsing Headings, tables, lists, and captions retain their hierarchical relationships through chunking. No flattening to character runs. - ### Fifty-plus filetypes PDF, DOCX, PPTX, XLSX, HTML — same engine for all of them. Images, charts, and tabulated data are handled inline as searchable content. - ### Hierarchical chunksets Output is structured JSON: chunks with full ancestor metadata and ready-to-embed traversal paths. Drop into any embedding model or vector DB. ## What POMA PrimeCut Does Differently POMA PrimeCut vs Unstructured.io vs Conventional Chunking: Hierarchical Chunking Compared ### Conventional Chunk an SPDF is one approach to help ensure that the QS regulation is met. Because of its benefits in helping comply with the QS regulation and cybersecurity, FDA encourages manufacturers to use an SPDF, but other approaches might also satisfy the QS regulation. \### B. Designing for Security When reviewing premarket submissions, FDA intends to assess device cybersecurity based on a number of factors, including, but not limited to, the device's ability to provide and implement the security objectives below throughout the device architecture. The security objectives below generally may apply broadly to devices within the scope of this guidance, including, but not limited to, devices containing artificial intelligence (AI) and cloud-based services. Security Objectives: • Authenticity, which includes integrity; • Authorization: • Availability: • Confidentiality; and • Secure and timely updatability and patchability. Premarket submissions should include information that describes how the above security objectives are addressed by and integrated into the device design. The extent to which security requirements, architecture, supply chain, and implementation are needed to meet these objectives will depend on but may not be limited to: \- The device’s intended use, indications for use, and reasonably foreseeable misuse; \- The presence and functionality of its electronic data interfaces; • Its intended and actual environment of use: \- The risks presented by cybersecurity vulnerabilities; \- The exploitability of the vulnerabilities; and \- The risk of patient harm due to vulnerability exploitation. SPDF processes aim to reduce the number and severity of vulnerabilities and thereby reduce the exploitability of a medical device system and the associated risk of patient harm. Because exploitation of known vulnerabilities or weak cybersecurity controls should be considered reasonably foreseeable failure modes for medical device systems, these factors should be addressed in the device design. $ ^{19} $ One of the key benefits of using an SPDF is that a medical device system is more likely to be secure by design, such that the device is designed from the outset to be secure within its system and/or network of use throughout the device lifecycle. \### C. Transparency A lack of cybersecurity information, such as information necessary to integrate the device into the use environment, as well as information needed by users to maintain the medical device system’s cybersecurity over the device lifecycle, has the potential to affect the safety and effectiveness of a device. In order to address these concerns, it is important for device users to \## Contains Nonbinding Recommendations have access to information pertaining to the device’s cybersecurity controls, potential risks to the medical device system, and other relevant - very **long** - spanning multiple sections - isolating **heading from subsequent content** ### Unstructured.io Chunk • The device’s intended use, indications for use, and reasonably foreseeable misuse; • The presence and functionality of its electronic data interfaces; • Its intended and actual environment of use; 18 • The risks presented by cybersecurity vulnerabilities; • The exploitability of the vulnerabilities; and • The risk of patient harm due to vulnerability exploitation. - No section indication - Random artifacts as part of apparent main text (“18”) - No context/positioning within the document ### POMA Chunk(Set): Full Context Path Cybersecurity Guidance for Medical Devices: Quality Systems and Premarket Submission Requirements \[…\] Guidance for Industry and Food and Drug Administration Staff \[…\] Contains Nonbinding Recommendations outline \[…\] B. Designing for Security When reviewing premarket submissions, FDA intends to assess device cybersecurity based on a number of factors, including, but not limited to, the device's ability to provide and implement the security objectives below throughout the device architecture. \[…\] The extent to which security requirements, architecture, supply chain, and implementation are needed to meet these objectives will depend on but may not be limited to: \[…\] • Its intended and actual environment of use: \[…\] • The risk of patient harm due to vulnerability exploitation. It just works [ What We Do Differently - Explained ]() ## The benchmark 23% of the tokens, 100% recall. Standard chunking ignores how your documents are structured. So a query like 'How high was the interest rate last year?' retrieves a wide net of chunks where most of the content has nothing to do with the question — and you still pay for every token returned. PrimeCut chunks structure-aware: queries return only the relevant content, no loss of recall. [Full benchmark on GitHub](https://github.com/poma-ai/poma-officeqa) [Explore chunking strategies](https://www.poma-ai.com/docs/guides/rag-chunking/) ## One API That Adapts to Every Document PrimeCut Adaptive PrimeCut adapts processing to each document — preserving hierarchy, cross-references, and visual content where it matters, and staying lean where it doesn't. One balance, priced per page. ## PrimeCut **Adaptive** Full structural and visual intelligence where your documents need it — lean, fast processing where they don't. **max €0.01** / page / 1000 token / min **Features** - Rapid, full document hierarchy parsing - Semantically bounded, neighbour-aware chunks with ancestor context inheritance - Context-aware, ready-to-embed chunksets - Full AI processing — figures, tables, and images parsed as semantic content - Visual elements extracted, placeholdered, and converted to retrievable, context-aware textual chunks - Optimized for multimodal accurate hierarchical textual representation of complex content - Optimized for low cost — lean processing where documents are simple - Title generation **One API, both ends of the spectrum** - Complex, high-stakes documents (legal & regulatory, financial & insurance, medical, engineering) — full structural and visual fidelity, maximum search accuracy - Large, simple corpora — lean processing that keeps cost near the floor - Mixed knowledge bases — PrimeCut Adaptive auto-classifies every document and gives it the right processing at the right price **Structured files** — `xml`, `cir`, `json`, `yaml`, `toml`, `ini`, `env`, `csv`, `tsv`, `xls`, `xlsx`, `xlsb` — are always chunked with full structural fidelity. [ Try for Free ](https://console.poma-ai.com/?mode=register) ## Integration into Your RAG Pipeline LangChain Document Chunking and RAG Pipeline Integration — No Architectural Overhaul PrimeCut sits at the ingestion layer of your RAG pipeline — upstream of your vector database, your embedding model, and your retrieval logic. It receives documents. It returns structured, hierarchically-bounded chunksets. The SDK is lightweight. The API is flexible. PrimeCut's output schema is consistent across both configurations. **Compatible with:** **LLMs** OpenAI Anthropic Other leading LLMs **Vector Databases** [ Qdrant](https://qdrant.tech/documentation/data-management/poma/) Integration Partner Integration Partner Pinecone Weaviate Other vector databases **Frameworks** LangChain LlamaIndex Custom RAG implementations ## Ready to get started? Try it on your own pipeline. Free tier covers 1,000 pages — drop the SDK in, point it at a document, see what comes back. No retrieval refactor, no vector DB swap, no architectural overhaul. Processing at scale? [Let's talk](https://meetings-eu1.hubspot.com/florian-athens) [ Try for free ](https://console.poma-ai.com/?mode=register)[ Read the documentation ](https://www.poma-ai.com/docs/) 1,000 free pages. No credit card required.