Skip to main content

Deterministic, agent-free ingestion tool for Open Knowledge Format (OKF) bundles — validate, load into a portable DuckDB catalog, render, graph, and semantically search, from R or Python.

Project description

okf (Python binding)

Python binding of okf-ingest — a unified ingestion tool for Open Knowledge Format (OKF) bundles. Validate a bundle, load it into a portable DuckDB catalog, and semantically search it.

pip install okf-ingest
okf validate ./bundle
okf ingest   ./bundle --db catalog.duckdb
okf embed    catalog.duckdb            # uses local Ollama nomic-embed-text by default
okf rag      catalog.duckdb --query "how is revenue computed?" -k 5
import okf
con, summary = okf.ingest("./bundle", db_path="catalog.duckdb")
okf.embed(con)                         # pluggable embedder
okf.rag_search(con, "revenue", k=5)

The catalog format is shared with the R binding (okf on CRAN-style install), so you can ingest/embed in one language and query from the other. See the project README and docs/ for the full spec-conformance notes and architecture.

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

okf_ingest-0.4.0.tar.gz (21.3 kB view details)

Uploaded Source

Built Distribution

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

okf_ingest-0.4.0-py3-none-any.whl (23.5 kB view details)

Uploaded Python 3

File details

Details for the file okf_ingest-0.4.0.tar.gz.

File metadata

  • Download URL: okf_ingest-0.4.0.tar.gz
  • Upload date:
  • Size: 21.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.10

File hashes

Hashes for okf_ingest-0.4.0.tar.gz
Algorithm Hash digest
SHA256 20d52aec0010cadefefdfdecd1298ada5b1eeb3e1524bfd2a38b4a984d0ecaf8
MD5 72452db1c34cecb1f4da9389d273dafa
BLAKE2b-256 17e66ef6d48a785ad944a77d4af7f880febbc3e6546f1d1714b79e1231ee7f02

See more details on using hashes here.

File details

Details for the file okf_ingest-0.4.0-py3-none-any.whl.

File metadata

  • Download URL: okf_ingest-0.4.0-py3-none-any.whl
  • Upload date:
  • Size: 23.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.10

File hashes

Hashes for okf_ingest-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 54e0c40baaaa23bfd485f68099d46fe2fc746684d6f47e18d8b124eca08cfd29
MD5 92dab32ad89526f2f380035ab9a4913c
BLAKE2b-256 68aadc353a2a027b485a08f19e7fac76acfd97d5f8b5d13d14cc9ae6477ce863

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