v0.4.0: local embeddings via quantized Gemma 4 (no API cost) #7

Summary

Add an optional local embedding pass using a quantized model — leading candidate is Gemma 4 (Q4/Q8 via llama.cpp or ollama) — to generate semantically_similar_to edges across all nodes without any API calls.

Motivation

Currently, semantic similarity edges come from Claude's judgment during extraction — one pass per file, subjective, and costs API tokens. A local embedding pass would:

• Generate embeddings for every node (label + docstring) after the AST and semantic passes
• Add cosine-similarity edges above a configurable threshold, marked INFERRED
• Make cross-file concept linking exhaustive rather than sampled
• Work fully offline, cached per-node alongside the existing SHA256 file cache
• Cost zero API tokens after the initial model download

The two approaches complement rather than replace each other — Claude finds the interesting cross-cutting edges, local embeddings find the exhaustive ones. Both end up in the same graph.

Design

Model: Gemma 4 Q4 or Q8 via llama.cpp or ollama. Produces strong semantic embeddings for code + text at ~2-4GB RAM, no GPU required.

Pipeline position: after Part C (build + cluster), before export. Reads all node labels + docstrings, generates embeddings in batch, computes pairwise cosine similarity, adds edges above threshold.

Threshold: configurable, default ~0.82. Exposed as --embed-threshold 0.82.

Backend: support both llama-cpp-python and ollama client, auto-detect which is available.

Caching: store embedding vectors in graphify-out/cache/embeddings.json keyed by node ID + content hash. Re-embedding only runs for new or changed nodes.

Skill flag: /graphify ./raw --embeddings to enable the pass. Off by default.

Install

pip install graphifyy[embeddings]   # pulls llama-cpp-python
# or: ollama pull gemma4 && /graphify ./raw --embeddings

Acceptance criteria

• --embeddings flag triggers embedding pass after graph build
• Edges added as semantically_similar_to, confidence INFERRED, with confidence_score = cosine similarity value
• Embedding cache works — re-run on unchanged corpus adds zero new embeddings
• Works with both llama-cpp-python and ollama backends (auto-detected)
• pip install graphifyy[embeddings] installs the right deps
• Benchmark: show how many additional similarity edges embeddings find vs Claude-only extraction on the Karpathy corpus