Knowledge graphs using Ollama and Embeddings to answer and visualizing queries

punnerud1 pts0 comments

GitHub - punnerud/Local_Knowledge_Graph · GitHub

/" data-turbo-transient="true" />

Skip to content

Type / to search

Sign in<br>Sign upAppearance settings

You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

{{ message }}

punnerud

Local_Knowledge_Graph

Public

Notifications<br>You must be signed in to change notification settings

Fork<br>49

Star<br>550

main

BranchesTags

Go to file

CodeOpen more actions menu

Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit

History<br>26 Commits<br>26 Commits

.github/workflows

.github/workflows

dev

dev

docs

docs

src/mpe_lkg

src/mpe_lkg

.gitignore

.gitignore

LICENSE

LICENSE

Makefile

Makefile

README.md

README.md

app.py

app.py

pyproject.toml

pyproject.toml

View all files

Repository files navigation

Local Knowledge Graph

Ask a local model a question, watch it reason step by step, and see the steps drawn as a<br>graph. Blue edges are embedding similarity — association. Green is what an exact<br>evaluator settled — sums and unit conversions, in fractions, via<br>mpeqs. Everything runs on your machine.

Run it

pip install mpe-lkg<br>mpe-lkg

Open http://localhost:5100. It talks to a local model through<br>Ollama and will tell you what is missing and the one command that<br>fixes it. The model matters more than anything else here — measured, qwen3:4b-instruct-2507<br>answers 82.5% of the arithmetic battery against llama3.2:3b's 40%:

ollama pull qwen3:4b-instruct-2507-q4_K_M

Ask harder questions with mode=explore (each sub-question answered by its own run) or<br>mode=settle (explored twice, finished only when two independent runs agree), and take any<br>run as RDF:

/rdf">curl -sX POST localhost:5100/jobs -H 'content-type: application/json' \<br>-d '{"query":"How many seconds are there in 23 weeks?","mode":"settle"}'<br>curl -s localhost:5100/jobs/id>/rdf

More

Modes, jobs and RDF<br>reason / explore / settle, the vote, the probes, the vocabulary

Models and configuration<br>Choosing models, every environment variable, troubleshooting

Embeddings from inside a model<br>Reading a chosen layer instead of an embedding endpoint

How it works<br>The modules, the strongest-path search, why there is no ANN index

Development<br>Tests, and the gate that checks this documentation against measured data

Licence

The mpedb License 1.0 — the same licence as<br>mpedb and MPEqs,<br>byte for byte.

Free of charge for every person and every organization, with one exception: a group whose<br>revenue or valuation exceeds five billion dollars owes a one-time fee of seven US cents per<br>device. Not an OSI-approved licence.

Published to PyPI as mpe-lkg — M orten P unnerud-E ngelstad L ocal<br>K nowledge G raph.

About<br>No description, website, or topics provided.<br>Resources<br>Readme<br>License<br>Activity<br>Stars<br>550 stars<br>Watchers<br>5 watching<br>Forks<br>49 forks<br>Report repository

Releases

Packages

Used by

Contributors

Languages

You can’t perform that action at this time.

github license model ollama signed another

Related Articles