Skip to main content

Local-first document navigation with AI-powered queries and citations

Project description

docnav

DocNav

DocNav is a local-first Python library for navigating, understanding, and querying documents using AI. It provides precise, citation-backed answers from real files (PDFs, Word documents, slides, spreadsheets, text) using a simple API.

Features

  • Zero-config ingestion: Works with PDFs, DOCX, TXT, Markdown, PPTX, Excel, CSV
  • Smart chunking: Structure-aware document splitting
  • Local-first: Works offline with local embeddings
  • Cloud LLM support: OpenAI and Google Gemini
  • Persistent storage: Update documents incrementally
  • Citations: Every answer includes source references
  • CLI & Python API: Use from terminal or code
  • Production-ready: Supports continuous updates, not just one-time indexing

Installation

pip install docnav

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

docnav-1.0.0.tar.gz (13.0 kB view details)

Uploaded Source

Built Distribution

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

docnav-1.0.0-py3-none-any.whl (12.8 kB view details)

Uploaded Python 3

File details

Details for the file docnav-1.0.0.tar.gz.

File metadata

  • Download URL: docnav-1.0.0.tar.gz
  • Upload date:
  • Size: 13.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for docnav-1.0.0.tar.gz
Algorithm Hash digest
SHA256 61eeb77b1a231ee139483c622af05073733ea4bfe58b799186ca91ae12f8d975
MD5 22bdc9302565bb6d7a7a37fc72df842b
BLAKE2b-256 bc265424af046427f413753875b266e7d68f63c4d677b9acbbe4ca150eb98b49

See more details on using hashes here.

File details

Details for the file docnav-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: docnav-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 12.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for docnav-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2593a1dde5c0b5d678be8cadf8bcc190ed0980798f2acec162c0bc31da46cec4
MD5 53e9ea6b9943a58ab6a35a6a5b4a12b6
BLAKE2b-256 502fc853f593e538a5539c7da938ccb6a122d6fa983bef3e606894371fe7f4a5

See more details on using hashes here.

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