> ## Documentation Index > Fetch the complete documentation index at: https://docs.omnifact.ai/llms.txt > Use this file to discover all available pages before exploring further. # Attachments vs. Uploaded Files > Choose the right document strategy in Omnifact: ephemeral chat attachments vs. long-term Space retrieval. export const Glossary = ({children, term}) => { const glossaryDefinitions = { 'ai': 'Artificial Intelligence - computer systems that can perform tasks typically requiring human intelligence', 'artificial-intelligence-ai': 'Computer systems that can perform tasks typically requiring human intelligence', 'ai-assistant': 'An AI system designed to help users with tasks through conversation', 'space': 'A dedicated environment with a specialized AI assistant and optional Uploaded Files', 'spaces': 'Dedicated environments with specialized AI assistants and optional Uploaded Files', 'knowledge': 'The sub-menu in Space settings where you manage Uploaded Files and Connected Sources', 'uploaded-files': 'Documents manually uploaded to a Space under the Knowledge tab', 'prompt': 'Instructions or questions you give to an AI assistant', 'response': 'The AI assistant\'s answer to your prompt or question', 'query': 'A question or request for information', 'context': 'Background information that helps the AI understand your request', 'llm': 'Large Language Model - an AI system trained on vast amounts of text data to understand and generate human language', 'large-language-model-llm': 'An AI system trained on vast amounts of text data to understand and generate human language', 'privacy-filter': 'A system that automatically detects and masks sensitive information before it reaches AI models, and restricts images from being sent to non-EU hosted models for compliance', 'chat-instructions': 'Custom guidelines that define how an AI assistant behaves and responds in a Space', 'pattern-matching': 'The process by which AI recognizes and uses patterns in data to provide responses', 'patterns': 'Recognizable structures or trends in data that AI systems can identify and use', 'training-data': 'The text and information used to teach an AI system how to understand and respond to requests', 'natural-language': 'Everyday human language that people use to communicate, as opposed to computer code or formal syntax', 'hallucination': 'When an AI generates information that sounds plausible but is actually incorrect or fabricated', 'filtering': 'The process of automatically detecting and temporarily replacing sensitive information to protect it during AI processing', 'masking': 'Temporarily replacing sensitive information with generic labels to protect it from being seen by external AI models', 're-insertion': 'The automatic process of putting original sensitive information back into AI responses after they\'ve been generated with filtered data', 'retrieval': 'The process of finding and accessing relevant documents from Uploaded Files to answer questions', 'hosting': 'Where an AI model is deployed and made available for use - either by third-party providers, on your organization\'s own servers, or in private cloud environments', 'cite': 'To reference or mention the source of information, helping you know where an AI\'s answer came from', 'sidebar': 'A panel that appears on the side of the screen showing additional information and options', 'toggle': 'A button or control that switches something on or off, like opening and closing a sidebar', 'navigation': 'The system of menus and buttons that help you move between different parts of Omnifact', 'favoriting': 'Marking a Space as a favorite to pin it to the main navigation for quick access', 'pinning': 'Attaching a Space to the main navigation bar so it\'s always visible and easily accessible' }; const definition = glossaryDefinitions[term]; return {children}; }; Omnifact offers two primary ways to work with documents and files: **Chat Attachments** and **Space Uploaded Files**. Both allow your AI assistant to analyze document content, but they serve fundamentally different needs. Understanding when to use each approach helps you work faster, manage document storage efficiently, and collaborate better with your team. Use **Chat Attachments** for quick, one-off questions about a single file in your current conversation. Use **Space Uploaded Files** when you want a collection of documents to serve as permanent reference material for yourself or your team across multiple chats. ## Comparison at a Glance | Feature | Chat Attachments | Space Uploaded Files | | :-------------------- | :----------------------------------------------------------- | :----------------------------------------------------------- | | **Primary Scope** | Single chat thread | Entire Space (all current and future chats) | | **Lifetime** | Ephemeral (tied to conversation context) | Persistent (stored permanently in Space settings) | | **Access & Sharing** | Visible only within the active chat session | Accessible to all members of the Space | | **Processing Method** | Direct file context insertion into current prompt | Vector indexing and semantic retrieval | | **Document Capacity** | Up to 5 files per message | Plan page quota (e.g. 5,000+ pages per Space) | | **File Size Limits** | 20 MB images, 25 MB audio | Standard document upload limits | | **Best For** | Reviewing a draft, analyzing a single invoice, visual charts | Employee handbooks, policy sets, project archives, team FAQs | ## Understanding Chat Attachments [Chat Attachments](/en/platform/core-features/chats/attaching-documents) allow you to upload files directly into the chat input bar. The content of attached files is included as immediate context for your specific conversation. No pre-indexing required. Attach a document and ask a question right away. Supports documents (PDF, Word, Excel, PowerPoint), text files (TXT, JSON, CSV), images, and audio files. Attached files remain private to that specific conversation thread unless you explicitly share the chat. Great for quick draft revisions, one-time summaries, or ad-hoc data analysis. ### When to Use Chat Attachments * **One-time Document Review:** You received a PDF report or contract draft and need an immediate summary or risk evaluation. * **Visual Chart or Diagram Analysis:** You want to attach a screenshot or diagram to ask specific visual questions. * **Audio Transcription & Summarization:** You have a recorded meeting file (up to 25 MB) and need quick action items. * **Ad-hoc Comparison:** You want to compare two spreadsheet exports side by side in a single message (up to 5 attachments). ## Understanding Space Uploaded Files [Space Uploaded Files](/en/platform/core-features/spaces/uploaded-files-retrieval) is a dedicated knowledge repository attached to a specific [Space](/en/platform/core-features/spaces/introduction). When documents are uploaded to a Space, Omnifact processes, chunks, and indexes them for vector-based semantic search. Files stay available indefinitely in the Space. Every new chat in that Space can tap into the full document set. When you ask a question, Omnifact retrieves only the relevant chunks from large document sets, saving prompt context. All Space members benefit from the same authoritative source documents, ensuring consistent answers across the team. Responses automatically include clear references showing which documents from the Uploaded Files were consulted. ### When to Use Space Uploaded Files * **Departmental Knowledge Bases:** Storing HR policies, onboarding guides, brand guidelines, or standard operating procedures. * **Project Repositories:** Keeping technical specifications, project requirements, and meeting notes together for an ongoing initiative. * **Research & Strategy Libraries:** Aggregating industry market reports, competitor analyses, and quarterly financial reviews. * **Strict Compliance Queries:** Using **Simple Lookup** response mode to force answers strictly from verified company documents. ## Decision Matrix: Which Should You Use? To choose the right approach for your task, follow this decision matrix: * **Yes:** Upload it to a **Space Uploaded Files** so it remains indexed and available to all Space members. * **No:** Proceed to step 2. * **Yes:** Use a **Space Uploaded Files**, which leverages vector indexing to search large document collections efficiently. * **No:** Proceed to step 3. * **Yes:** Use **Chat Attachments** for quick, one-off analysis. ## Transitioning from Attachments to Uploaded Files A common workflow is to start by attaching a file to a chat for initial testing. If you find yourself repeatedly attaching the same document or if colleagues ask for access to that information, convert it into permanent knowledge: 1. Go to **Spaces** in the main navigation and select or create the relevant Space. 2. Open **Space Settings** (requires Space Admin role or Uploaded Files Manager permission). 3. Select the **Knowledge** tab and upload your verified document. 4. From then on, any team member in that Space can ask questions about that document without re-attaching it. ## Next Steps * Learn the details of [Attaching Documents & Images](/en/platform/core-features/chats/attaching-documents) in chat * Understand how [Uploaded Files Retrieval](/en/platform/core-features/spaces/uploaded-files-retrieval) works in Spaces * Explore [Managing Uploaded Files](/en/platform/core-features/spaces/managing-uploaded-files) as a Space Administrator