Skip to main content

Graph RAG

Project description

Knwl

A clean Graph RAG implementation.

The current implementation is rather old and there is a major effort ongoing in the v2 branch.

Query modes

Local

  • low-level keywords are matched against nodes, called the primary nodes

  • relationship neighborhood around these primary nodes is considered

The context consists of:

  • primary node records/table consisting of name, type, and description
  • relationship records/table consisting of source, target, type, and description
  • chunks taken from the primary nodes

Global

  • high-level keywords are matched against edges

The context consists of:

  • node endpoints of the edges
  • edge records/table consisting of source, target, type, and description
  • chunks taken from the edges

Naive

The simply gives the question to the chunks and is added as context.

Hybrid

The hybrid mode is a combination of the local and global modes. It takes the local and global contexts, combines it as augmentation.

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

knwl-0.4.0.tar.gz (398.8 kB view details)

Uploaded Source

Built Distribution

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

knwl-0.4.0-py3-none-any.whl (47.9 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: knwl-0.4.0.tar.gz
  • Upload date:
  • Size: 398.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for knwl-0.4.0.tar.gz
Algorithm Hash digest
SHA256 a13488e93e0741f1d5897224d2f3c4f659a320501c433d23ef80fd02813f4283
MD5 fbe99692269fecb3f16b6d3cb20388d5
BLAKE2b-256 9d7164b3855332ff2d8caedd14cfdcbf2952c77d7a85e5df884436e82f06f6cc

See more details on using hashes here.

Provenance

The following attestation bundles were made for knwl-0.4.0.tar.gz:

Publisher: publish.yml on Orbifold/knwl

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

File details

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

File metadata

  • Download URL: knwl-0.4.0-py3-none-any.whl
  • Upload date:
  • Size: 47.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for knwl-0.4.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6f1905848f44529e2eb5c69a0fe0f93a9a1a0a565d846336d467cb418996dba8
MD5 64a9c83555117310ba4e9ad074f2d426
BLAKE2b-256 5907c5c0e3da83f594fa0a0f75638535c4c6c0e1609116104308bc8ad472723c

See more details on using hashes here.

Provenance

The following attestation bundles were made for knwl-0.4.0-py3-none-any.whl:

Publisher: publish.yml on Orbifold/knwl

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