Skip to main content

AI-powered metadata enrichment for Stache (standard features)

Project description

stache-ai-enrichment

AI-powered metadata enrichment for Stache (standard features).

Features

Automatically enriches document metadata with:

  • Summary: 2-3 sentence summary of document content and purpose
  • Document Type: Classification (article, guide, tutorial, reference, etc.)
  • Chunking Strategy: Recommended chunking strategy based on document structure

Installation

pip install stache-ai-enrichment

The enricher automatically registers via entry points - no configuration needed.

Cost

Approximately $0.0005 per document using Nova Lite (default model).

Requirements

  • stache-ai>=0.1.6 (includes BaseAIEnricher and LLM structured output support)
  • Bedrock LLM provider with Nova or Claude models

Coexistence with Enterprise Plugin

This plugin can coexist with stache-ai-enrichment-enterprise:

  • Standard plugin: priority=80, extracts basic fields
  • Enterprise plugin: priority=85, extracts advanced fields (concepts, entities, relationships)
  • Enterprise plugin detects standard plugin and avoids duplicate LLM calls

License

MIT

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

stache_ai_enrichment-0.1.1.tar.gz (7.1 kB view details)

Uploaded Source

Built Distribution

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

stache_ai_enrichment-0.1.1-py3-none-any.whl (5.1 kB view details)

Uploaded Python 3

File details

Details for the file stache_ai_enrichment-0.1.1.tar.gz.

File metadata

  • Download URL: stache_ai_enrichment-0.1.1.tar.gz
  • Upload date:
  • Size: 7.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for stache_ai_enrichment-0.1.1.tar.gz
Algorithm Hash digest
SHA256 e974eef6c401c3ed0f4ad55703058aeba38e3b29cd011d11045e2be8cfb65ece
MD5 f226780d0eed5f4d11414bd717a9dcfb
BLAKE2b-256 87704af5c318bd3b5f3d3a8fdcebf6e6d02ff4de001d3b53deab7b5c929a3582

See more details on using hashes here.

File details

Details for the file stache_ai_enrichment-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for stache_ai_enrichment-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 16e4e98fbec849c570fe080052a6232311a4d6b5b2fdb75e22ed3aa4f43e1f1b
MD5 3c78dc06e082a42302b16e323ef069f7
BLAKE2b-256 44dd4f98d78ae189b9c079b2aab8086ae0bd77b4e15c97f1be0ece58719a7950

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