Local Knowledge Graph
Ask a local model a question, watch it reason step by step, and see the steps drawn as a graph. Blue edges are embedding similarity — association. Green is what an exact evaluator settled — sums and unit conversions, in fractions, via mpeqs. Everything runs on your machine.
Run it
pip install mpe-lkg
mpe-lkg
Open http://localhost:5100. It talks to a local model through
Ollama and will tell you what is missing and the one command that
fixes it. The model matters more than anything else here — measured, qwen3:4b-instruct-2507
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
mode=settle (explored twice, finished only when two independent runs agree), and take any
run as RDF:
curl -sX POST localhost:5100/jobs -H 'content-type: application/json' \
-d '{"query":"How many seconds are there in 23 weeks?","mode":"settle"}'
curl -s localhost:5100/jobs/<id>/rdf
More
| Modes, jobs and RDF | reason / explore / settle, the vote, the probes, the vocabulary |
| Models and configuration | Choosing models, every environment variable, troubleshooting |
| Embeddings from inside a model | Reading a chosen layer instead of an embedding endpoint |
| How it works | The modules, the strongest-path search, why there is no ANN index |
| Development | Tests, and the gate that checks this documentation against measured data |
Licence
The mpedb License 1.0 — the same licence as mpedb and MPEqs, byte for byte.
Free of charge for every person and every organization, with one exception: a group whose revenue or valuation exceeds five billion dollars owes a one-time fee of seven US cents per device. Not an OSI-approved licence.
Published to PyPI as mpe-lkg — Morten Punnerud-Engelstad Local
Knowledge Graph.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mpe_lkg-0.8.0.tar.gz.
File metadata
- Download URL: mpe_lkg-0.8.0.tar.gz
- Upload date:
- Size: 778.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/7.0.0 CPython/3.12.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0bdc7260ce64a464061808b7083f9b7c2f91883eccfd32cc8511e28ef48d7014
|
|
| MD5 |
4392148a9431d9cbc9f212fb91e74b28
|
|
| BLAKE2b-256 |
6edad93635b10b99174deaaea996f5602b4baa48150b8d0eb1b662fb5cc2d3b7
|
File details
Details for the file mpe_lkg-0.8.0-py3-none-any.whl.
File metadata
- Download URL: mpe_lkg-0.8.0-py3-none-any.whl
- Upload date:
- Size: 283.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/7.0.0 CPython/3.12.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4f7d5b26067db2d470e33d395c398d6dd36af698bb9f67752e7ec5a204ddf8bc
|
|
| MD5 |
79cd3a682138d11704ecdbcf32111a19
|
|
| BLAKE2b-256 |
07d0c4e2d5267e5305669f3f1007924733b4a6bf13ca68bdb4122d5e13ed0ccc
|
