Graphviz DOT diagram of the arborist pipeline as the answer to the Google L5 system-design prompt 'design a RAG pipeline for 10M docs with zero hallucination'. Maps our components onto the canonical 10-box RAG design and shows the three extensions that buy zero-hallucination + near-zero cost: deterministic verifier (not a model confidence score) -> honest UNGROUNDED; Merkle-bound cache that skips the GPU; measured energy COGS (~$0.07-0.16/1k answers, non-reasoning). Includes the mapping table + the 3.47M->10M scaling math (+77GB, sourcing/storage not redesign). Enables sphinx.ext.graphviz (SVG output) + graphviz apt package on the RTD build; adds the page to the Summary-pages toctree. Builds clean (page renders, DOT validates via dot -Tsvg).
60 lines
837 B
ReStructuredText
60 lines
837 B
ReStructuredText
Arborist API Reference
|
|
======================
|
|
|
|
Generated from docstrings. Replaces the static modules.md.
|
|
|
|
Contents:
|
|
|
|
.. toctree::
|
|
:maxdepth: 1
|
|
:caption: Summary pages
|
|
|
|
arborist-one-pager
|
|
arborist-two-pager
|
|
google-l5-rag-10m
|
|
|
|
.. toctree::
|
|
:maxdepth: 2
|
|
:caption: Getting started
|
|
|
|
quickstart
|
|
concepts
|
|
cookbook
|
|
|
|
.. toctree::
|
|
:maxdepth: 2
|
|
:caption: Substrate
|
|
|
|
merkle-agi-dag-v7
|
|
merkle-agi-v7w-spatial-temporal
|
|
merkle-agi-v8-consensus
|
|
v8-fork-score
|
|
pi-star
|
|
bench
|
|
|
|
.. toctree::
|
|
:maxdepth: 3
|
|
:caption: API Modules
|
|
|
|
api/makefile
|
|
api/substrate
|
|
api/storage
|
|
api/retrieval
|
|
api/qa
|
|
api/distill
|
|
api/mesh
|
|
api/cli
|
|
|
|
.. toctree::
|
|
:maxdepth: 1
|
|
:caption: Project
|
|
|
|
license
|
|
|
|
|
|
Indices and tables
|
|
==================
|
|
|
|
* :ref:`genindex`
|
|
* :ref:`modindex`
|
|
* :ref:`search`
|