# Embed

Generate, inspect, and use node/text embeddings in Semantica, compute Node2Vec...

- Repository: https://github.com/semantica-agi/semantica (14373 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add semantica-agi/semantica --skill embed -g -a claude-code -y`
Codex: `npx skills add semantica-agi/semantica --skill embed -g -a codex -y`
Cursor: `npx skills add semantica-agi/semantica --skill embed -g -a cursor -y`
Gemini CLI: `npx skills add semantica-agi/semantica --skill embed -g -a gemini-cli -y`

## Description

Generate, inspect, and use node/text embeddings in Semantica, compute Node2Vec embeddings, find similar nodes, score link predictions, batch similarity, and pairwise similarity. Uses NodeEmbedder, SimilarityCalculator, LinkPredictor, and AgentContext. Sub-commands: compute, similar, similarity, predict-link, top-links, batch, pairwise.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# /semantica:embed

Generate and inspect graph embeddings. Usage: `/semantica:embed <sub-command> [args]`

`$ARGUMENTS` = sub-command + arguments.

---

## `compute [--labels <t1,t2>] [--rels <r1,r2>] [--dim N] [--walks N]`

Generate Node2Vec embeddings for graph nodes.

```python
from semantica.kg.node_embeddings import NodeEmbedder
from semantica.context import ContextGraph

graph = ContextGraph()
embedder = NodeEmbedder()

node_labels = labels_arg.split(",") if labels_arg else graph.get_all_node_types()
rel_types = rels_arg.split(",") if rels_arg else []

# All positional args required: graph_store, node_labels, relationship_types
embeddings = embedder.compute_embeddings(
    graph_store=graph,
    node_labels=node_labels,
    relationship_types=rel_types,
    embedding_dimension=int(dim_arg) if dim_arg else None,
    num_walks=int(walks_arg) if walks_arg else None,
)

# Store embeddings back on nodes
embedder.store_embeddings(
    graph_store=graph,
    embeddings=embeddings,
    property_name="node2vec_embedding",
)
```

Output:
```
Embeddings computed and stored.
  Nodes embedded:     N
  Embedding dim:      128
  Node types covered: [type1, type2, ...]
  
Sample (first 5 nodes):
  | Node | Type | Embedding dim | Stored |
```

---

## `similar <node_id> [--top N]`

Find the most similar nodes to a given node in embedding space.

```python
from semantica.kg.node_embeddings import NodeEmbedder
from semantica.context import ContextGraph, AgentContext

graph = ContextGraph()
embedder = NodeEmbedder()

# NodeEmbedder.find_similar_nodes uses the stored node2vec_embedding property
neighbors = embedder.find_similar_nodes(
    graph_store=graph,
    node_id=node_id,
    top_k=int(top_n) if top_n else 10,
    embedding_property="node2vec_embedding",
)

The rest: https://github.com/semantica-agi/semantica/blob/HEAD/plugins/skills/embed/SKILL.md