Indexed
Guides

Index Your Local Docs

Make a folder of documents searchable with semantic search.

Index Your Local Docs

By the end of this guide, you'll have a folder of local documents indexed and searchable — with results ranked by meaning, not just keywords.

Prerequisites

Create a Collection

Point Indexed at your folder:

Terminal
indexed index create files -c project-docs -p ~/work/docs
Indexing collection 'project-docs'...
  Parsed 24 documents
  Created 96 chunks
  Generated embeddings
✓ Collection 'project-docs' created (96 chunks, 5.1 MB)

Indexed will recursively scan the folder, parse every supported file, split documents into chunks, and embed them into a FAISS vector index — all locally.

Filter with Include/Exclude Patterns

To index only specific file types or skip certain files, use regex patterns:

Terminal
# Only Markdown and text files
indexed index create files -c docs-only -p ~/work/docs \
  --include ".*\.md$" --include ".*\.txt$"

# Skip draft files
indexed index create files -c final-docs -p ~/work/docs \
  --exclude ".*\.draft\.md$" --exclude ".*WIP.*"

Patterns are regular expressions. You can repeat --include and --exclude to specify multiple patterns.

Verify the Collection

Terminal
indexed index inspect project-docs
Collection: project-docs
  Type:       files
  Source:     /Users/you/work/docs
  Documents:  24
  Chunks:     96
  Size:       5.1 MB
  Created:    2025-03-15 14:30:22
Terminal
indexed index search "deployment process"
Results for 'deployment process' (top 5):

1. [project-docs] deploy-guide.md (chunk 1/3)
   Score: 0.87
   ...To deploy to production, first ensure all CI checks pass,
   then run the release pipeline from the main branch...

2. [project-docs] runbook.md (chunk 4/6)
   Score: 0.79
   ...If a rollback is needed, revert the last deployment using
   the rollback script in the ops/ directory...

Additional Options

FlagDescription
--forceOverwrite an existing collection with the same name
--fail-fastStop on the first document that fails to parse
--no-fail-fastSkip unparseable documents and continue (default)
--use-cacheReuse cached parsed documents (default)
--no-cacheRe-parse all documents from scratch

What's Next