Skip to main content

Local-first document retrieval. Your data never leaves your disk.

Project description

Alcove

CI PyPI Python Versions License

Index your world. Share it with the universe.

Alcove is a local-first document search library. Install it, point it at your files, and search. No server, no sign-up, no data leaves your disk.

Watch the 30-second demo

✨ Features

  • 🔒 Private — documents stay on your machine, no cloud calls, no telemetry
  • ⚡ Zero configpip install, two commands, searching in under a minute
  • 🔌 Extensible — custom extractors, embedders, and vector backends
  • 📄 Multi-format — PDF, EPUB, HTML, Markdown, CSV, JSON, JSONL, DOCX, TXT
  • 🌐 Web UI — upload and search from your browser

📦 Installation

Requirements: Python 3.10+ · Linux, macOS, or Windows

pip install alcove-search

Optional extras:

Extra Install command What it adds
Semantic search pip install alcove-search[semantic] Real vector similarity via sentence-transformers (~80 MB model download on first use)
EPUB support pip install alcove-search[epub] .epub file ingestion
DOCX support pip install alcove-search[docx] .docx file ingestion

⚡ Quick Start

alcove seed-demo          # download sample corpus + build index
alcove serve              # open http://localhost:8000
Alcove web UI

🔒 Trust Model

  • Local disk only — no hosted control plane
  • No telemetry. Period. (ChromaDB's upstream telemetry is also disabled.)
  • You choose what enters your index
  • We do not want your data

📚 Documentation

📄 License

Apache 2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

alcove_search-0.3.0.tar.gz (102.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

alcove_search-0.3.0-py3-none-any.whl (24.3 kB view details)

Uploaded Python 3

File details

Details for the file alcove_search-0.3.0.tar.gz.

File metadata

  • Download URL: alcove_search-0.3.0.tar.gz
  • Upload date:
  • Size: 102.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for alcove_search-0.3.0.tar.gz
Algorithm Hash digest
SHA256 e9cf7ea636e9b433fd577bb80f0211cc1fe7700ac6406d095893a5ad3afc98fb
MD5 7e05d8084d0a72039df2f194ce50b817
BLAKE2b-256 414e05789163418eabc2792e216edd444390a383346c717e80b2850c10333f6e

See more details on using hashes here.

Provenance

The following attestation bundles were made for alcove_search-0.3.0.tar.gz:

Publisher: publish.yml on Pro777/alcove

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file alcove_search-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: alcove_search-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 24.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for alcove_search-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c24e5d0e694bbac1246ff6b23f7bfbdcec1c23fcc511816fa1100cfd195c1969
MD5 cdcdf94d12a5f5079bfe6f0584bfd911
BLAKE2b-256 2bb632206139136782779f998f32355ef5674973f59c7fd688b82656cf670078

See more details on using hashes here.

Provenance

The following attestation bundles were made for alcove_search-0.3.0-py3-none-any.whl:

Publisher: publish.yml on Pro777/alcove

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page