--- title: "File enrichment glossary | LLMind" description: "Definitions for file enrichment, XMP metadata, C2PA, MCP, and every term that matters when you work with LLM-ready files." url: https://llmind.org/glossary/ source_format: html --- # File enrichment glossary Definitions for the terms that matter when you work with LLM-ready files — file enrichment, XMP, C2PA, MCP, tamper-evident metadata, and the rest. - [**LLM-ready file**](https://llmind.org/glossary/llm-ready-file/) — A file whose metadata carries a structured, AI-readable semantic layer so language models can consume it without re-parsing. - [**File enrichment engine**](https://llmind.org/glossary/file-enrichment-engine/) — Software that writes structured, signed semantic metadata into the file's own XMP packet. - [**Self-describing file**](https://llmind.org/glossary/self-describing-file/) — A file whose embedded metadata includes the information needed for AI tools to understand its content without external lookups. - [**Semantic layer for files**](https://llmind.org/glossary/semantic-layer-files/) — A structured, AI-readable metadata stratum inside the file itself — analogous to a BI semantic layer, applied to files. - [**LRFS**](https://llmind.org/glossary/lrfs/) — The LLM-Ready File Specification — LLMind's open spec for in-file semantic metadata and signing. - [**C2PA**](https://llmind.org/glossary/c2pa/) — Coalition for Content Provenance and Authenticity — a standard for cryptographically-signed origin metadata in image and video files. - [**Content Credentials**](https://llmind.org/glossary/content-credentials/) — Adobe's open-source implementation of the C2PA standard for signed provenance metadata. - [**Tamper-evident metadata**](https://llmind.org/glossary/tamper-evident-metadata/) — File metadata that can be cryptographically verified as unmodified since signing. - [**Signed semantic metadata**](https://llmind.org/glossary/signed-semantic-metadata/) — Metadata describing a file's meaning, cryptographically signed so consumers can verify integrity. - [**Provenance**](https://llmind.org/glossary/provenance/) — The verifiable origin and modification history of a file or its content. - [**HMAC-SHA256**](https://llmind.org/glossary/hmac-sha256/) — A keyed message-authentication code built on SHA-256 — LLMind's default signing primitive for LRFS layers. - [**File checksum**](https://llmind.org/glossary/file-checksum/) — A fixed-length digest (typically SHA-256) that uniquely identifies a file's byte contents. - [**XMP**](https://llmind.org/glossary/xmp/) — Extensible Metadata Platform — Adobe's standard for embedded, structured file metadata in XML-like RDF. - [**EXIF**](https://llmind.org/glossary/exif/) — Exchangeable Image File Format — the oldest widely-used standard for image metadata, typically for camera-origin data. - [**IPTC**](https://llmind.org/glossary/iptc/) — International Press Telecommunications Council — metadata standard for news photography and editorial imagery. - [**Dublin Core**](https://llmind.org/glossary/dublin-core/) — A minimal 15-element metadata vocabulary for describing any resource — often reused as XMP schema. - [**XMP namespace**](https://llmind.org/glossary/xmp-namespace/) — A URI that identifies the vocabulary of XMP properties a file uses — LLMind's is https://llmind.org/ns/1.0/. - [**Sidecar file**](https://llmind.org/glossary/sidecar-file/) — A separate file (often .xmp) that stores metadata for a primary file, rather than embedding metadata inside it. - [**Embedded metadata**](https://llmind.org/glossary/embedded-metadata/) — Metadata stored inside the file itself — e.g., in the XMP packet — rather than in a separate sidecar or database. - [**MCP**](https://llmind.org/glossary/mcp/) — Model Context Protocol — Anthropic's open standard for connecting AI agents to tools, files, and data sources. - [**RAG**](https://llmind.org/glossary/rag/) — Retrieval-Augmented Generation — a pattern where an LLM retrieves relevant chunks before generating a response. - [**Vector database**](https://llmind.org/glossary/vector-database/) — A database optimized for nearest-neighbor search over high-dimensional embedding vectors — common in RAG stacks. - [**Chunking**](https://llmind.org/glossary/chunking/) — Splitting a document into smaller passages for embedding and retrieval in a RAG pipeline. - [**Embedding**](https://llmind.org/glossary/embedding/) — A dense vector representation of text (or other data) where semantic similarity corresponds to vector proximity. - [**Context window**](https://llmind.org/glossary/context-window/) — The maximum amount of text an LLM can read at once, measured in tokens. - [**AI agent**](https://llmind.org/glossary/ai-agent/) — An LLM-powered program that can plan, call tools, and act in a loop to accomplish a goal. - [**AI Overview**](https://llmind.org/glossary/ai-overview/) — Google's generative answer feature that synthesizes responses from multiple sources and cites them. - [**OCR**](https://llmind.org/glossary/ocr/) — Optical Character Recognition — extracting text from an image or scanned page. - [**IDP**](https://llmind.org/glossary/idp/) — Intelligent Document Processing — AI-assisted extraction of structured data from documents, including OCR plus understanding. - [**DAM**](https://llmind.org/glossary/dam/) — Digital Asset Management — software that stores, organizes, and distributes media files across an organization. ## Explore more - [Learn](https://llmind.org/learn/) - [Spec](https://llmind.org/spec/)