Written by asad
Last updated 1 month ago
What are File Buckets?
File Buckets are a special type of bucket designed for documents. Unlike memory buckets that store text snippets, file buckets store complete files that are automatically processed for semantic search.Persistent Storage
Files stay available across all conversations and AI tools
Semantic Search
Find relevant passages based on meaning, not just keywords
Source Attribution
Answers reference specific files and page numbers
Cross-Platform
Query from Ask tool, MCP server, or TypingMind plugin
Supported File Types
| Format | Extensions | Notes |
|---|---|---|
.pdf | Text extracted from all pages | |
| Word | .docx | Microsoft Word documents |
| Markdown | .md | Plain markdown files |
| Text | .txt | Plain text files |
Scanned PDFs (image-only) are not currently supported. The PDF must contain extractable text.
How It Works
Upload Process
- Upload: Drag and drop or select files to upload
- Processing: Files are parsed and split into searchable chunks
- Indexing: Chunks are embedded for semantic search
- Ready: Files appear in your bucket and are queryable
Querying Files
When you search your files (through Ask, MCP, or TypingMind):- Your query is matched against file chunks using semantic search
- Relevant passages are retrieved with source metadata
- Results include file name, page numbers, and relevance scores
Using File Buckets
Creating a File Bucket
- Open the dashboard and look for the sidebar
- Click “New Bucket” and select “File Bucket” as the type
- Name your bucket (e.g., “Reference Docs”, “Project Files”)
- Click Create
Uploading Files
- Select your file bucket in the sidebar
- Drag and drop files into the upload area, or click to browse
- Wait for processing — status shows when files are ready
- View your files in the bucket list
Querying Files
Through Ask tool:- Open Ask and select Files mode
- Optionally select a specific file bucket
- Ask questions about your documents
search_uploaded_files tool with your query.
Through TypingMind:
The plugin’s search_uploaded_files function queries your documents.
Use Cases
Reference Documentation
Upload technical docs, API references, or style guides. Query them while working without leaving your AI conversation.Research Materials
Store papers, articles, or reports. Ask questions that synthesize across multiple sources.Project Context
Upload project specs, meeting notes, or requirements docs. Keep context available for all related conversations.Personal Knowledge Base
Store manuals, guides, or reference materials you frequently need to look up.Best Practices
Organize by purpose
Organize by purpose
Create separate file buckets for different projects or topics. This lets you filter searches to relevant documents.
Use descriptive file names
Use descriptive file names
File names appear in search results. Clear names help you identify sources quickly.
Keep files focused
Keep files focused
Smaller, focused documents often give better search results than massive files with mixed content.
Check processing status
Check processing status
Wait for files to finish processing before querying. The status indicator shows when files are ready.
Limits
| Aspect | Limit |
|---|---|
| File size | 10 MB per file |
| Storage | Varies by plan |
| Processing | Files are queued and processed in order |
File Buckets are a Premium feature. Check your plan for storage limits.
Integration
Ask Tool
Select Files mode in Ask to query your uploaded documents. Answers include source references with file names and page numbers. Related docs: AskMCP Server
Use thesearch_uploaded_files tool:
TypingMind Plugin
The plugin includessearch_uploaded_files for querying documents directly in TypingMind conversations.
Related docs: TypingMind plugin