mcpField
P
pygraphistry-ai

pygraphistry-ai

github.com/graphistryData & databases337 installsUpdated today
Repository

About pygraphistry-ai

pygraphistry-ai is a skill for using PyGraphistry’s graph-AI features. It guides workflows for embedding, clustering, semantic search, and consistent projections on new data, with practical notes on engines and sampling.

Key features

  1. 01Graph feature and embedding workflows
  2. 02UMAP projection and batch transforms
  3. 03DBSCAN clustering and semantic search
  4. 04Guidance on engines and sampling

Use cases

  1. 01Explore patterns in graph features
  2. 02Search text-derived graph embeddings
  3. 03Project new batches consistently

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/graphistry/graphistry-skills --skill pygraphistry-ai

After installing, type/pygraphistry-aiin Claude Code to confirm it loaded.

Details

From the project README

PyGraphistry AI

Doc routing (local + canonical)

  • First route with ../pygraphistry/references/pygraphistry-readthedocs-toc.md.
  • Use ../pygraphistry/references/pygraphistry-readthedocs-top-level.tsv for section-level shortcuts.
  • Only scan ../pygraphistry/references/pygraphistry-readthedocs-sitemap.xml when a needed page is missing.
  • Use one batched discovery read before deep-page reads; avoid cat * and serial micro-reads.
  • In user-facing answers, prefer canonical https://pygraphistry.readthedocs.io/en/latest/... links.

Typical workflow

  1. Build graph from nodes/edges.
  2. Run feature/embedding method (umap, embed, optional dbscan).
  3. Inspect derived columns/features and visualize.
  4. Iterate on feature columns and sampling strategy.

Baseline examples

# Similarity embedding / projection
g2 = graphistry.nodes(df, 'id').umap(X=['f1', 'f2', 'f3'])
g2.plot()

# Fit/transform flow for consistent projection on new batches
g_train = graphistry.nodes(df_train, 'id').umap(X=['f1', 'f2'])
g_batch = g_train.transform_umap(df_batch, return_graph=True)
g_batch.plot()

# Semantic search over embedded features
g2 = graphistry.nodes(df, 'id').umap(X=['text_col'])
results_df, query_vector = g2.search('suspicious login pattern')

# Text-first workflow: featurize then search/cluster
g2 = graphistry.nodes(df, 'id').featurize(kind='nodes', X=['title', 'body']).umap(kind='nodes').dbscan()
hits, qv = g2.search('credential stuffing campaign')

# Precomputed embedding columns
embedding_cols = [c for c in df.columns if c.startswith('emb_')]
g2 = graphistry.nodes(df, 'id').umap(X=embedding_cols)
g_new = g2.transform_umap(df_new, return_graph=True)

Practical guardrails

  • Start with small/representative samples before full runs.
  • Keep explicit feature lists (X=...) for reproducibility.
  • Track engine/dataframe type for CPU vs GPU behavior. Polars input is supported; use engine='polars'/'polars-gpu' for GFQL row/traversal work when preserving a Polars result matters.
  • UMAP, hypergraph, layout, and other whole-graph analytics are not native Polars operations. Under a Polars GFQL engine, use the default bridge knowingly or set call_mode='strict' to reject off-engine execution.
  • For anomaly workflows, document thresholds and false-positive assumptions.
  • For graph ML tasks, route deeper model workflows to RGCN/link-prediction references.
  • For text workflows, prefer featurize(...).umap(...).search(...) when queries are natural language.
  • If users already have embeddings, reuse them via explicit embedding column lists (X=[...]) before recomputing.
  • When user asks for a concise workflow snippet, prefer one short code block and avoid long narrative wrappers.

Canonical docs

Comments

Markdown supported