pycode-kg 0.16.0__tar.gz → 0.17.1__tar.gz

{pycode_kg-0.16.0 → pycode_kg-0.17.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pycode-kg
-Version: 0.16.0
+Version: 0.17.1
 Summary: A tool to build a searchable knowledge graph from Python repositories
 License-Expression: Elastic-2.0
 License-File: LICENSE
@@ -27,7 +27,7 @@ Requires-Dist: detect-secrets (>=1.5.0) ; extra == "all"
 Requires-Dist: detect-secrets (>=1.5.0) ; extra == "dev"
 Requires-Dist: doc-kg (>=0.11.0) ; extra == "dev"
 Requires-Dist: doc-kg (>=0.11.0) ; extra == "kgdeps"
-Requires-Dist: kg-snapshot (>=0.3.0)
+Requires-Dist: kgmodule-utils (>=0.2.1)
 Requires-Dist: lancedb (>=0.29.0)
 Requires-Dist: markdown (>=3.6) ; extra == "all"
 Requires-Dist: markdown (>=3.6) ; extra == "viz3d"

{pycode_kg-0.16.0 → pycode_kg-0.17.1}/pyproject.toml

@@ -51,12 +51,22 @@ priority = "supplemental"
 [tool.poetry]
 packages = [{ include = "pycode_kg", from = "src" }]
 
+[tool.poetry.group.dev.dependencies]
+detect-secrets = ">=1.5.0"
+mypy = ">=1.10.0"
+pdoc = ">=14.0.0"
+pre-commit = ">=4.5.1"
+pylint = ">=4.0.5"
+pytest = ">=8.0.0"
+pytest-cov = ">=5.0.0"
+ruff = ">=0.4.0"
+
 # ---------------------------------------------------------------------------
 # PEP 621 project metadata
 # ---------------------------------------------------------------------------
 [project]
 name = "pycode-kg"
-version = "0.16.0"
+version = "0.17.1"
 description = "A tool to build a searchable knowledge graph from Python repositories"
 readme = "README.md"
 license = "Elastic-2.0"
@@ -85,7 +95,7 @@ dependencies = [
     "sentence-transformers>=5.4.1",
     "torch>=2.5.1",
     "transformers>=4.57.6",
-    "kg-snapshot>=0.3.0",
+    "kgmodule-utils>=0.2.1",
 ]
 
 [project.optional-dependencies]
@@ -183,6 +193,10 @@ explicit_package_bases = true
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 addopts   = "-v --tb=short"
+markers = [
+    "slow: marks tests as slow (deselect with '-m not slow')",
+    "integration: marks tests that exercise real external dependencies (model, LanceDB)",
+]
 
 [tool.pylint.messages_control]
 disable = ["all"]

{pycode_kg-0.16.0 → pycode_kg-0.17.1}/src/pycode_kg/__init__.py

@@ -32,7 +32,7 @@ KGModule SDK (build new domain KGs)::
     from pycode_kg import KGModule, KGExtractor, PyCodeKGExtractor, NodeSpec, EdgeSpec
 """
 
-__version__ = "0.16.0"
+__version__ = "0.17.1"
 __author__ = "Eric G. Suchanek, PhD"
 
 # Low-level primitives (locked v0 contract)

{pycode_kg-0.16.0 → pycode_kg-0.17.1}/src/pycode_kg/cli/cmd_init.py

@@ -10,6 +10,7 @@ CLI command for initializing PyCodeKG in a repository:
 
 from __future__ import annotations
 
+import importlib.metadata
 import stat
 import subprocess
 import time
@@ -18,6 +19,8 @@ from pathlib import Path
 
 import click
 
+from pycode_kg.cli.cmd_build_full import _run_pipeline
+from pycode_kg.cli.cmd_hooks import _PRE_COMMIT_HOOK
 from pycode_kg.cli.main import cli
 from pycode_kg.cli.options import (
     exclude_option,
@@ -26,6 +29,10 @@ from pycode_kg.cli.options import (
     repo_option,
 )
 from pycode_kg.index import _local_model_path
+from pycode_kg.kg import PyCodeKG
+from pycode_kg.pycodekg_thorough_analysis import PyCodeKGAnalyzer
+from pycode_kg.snapshots import SnapshotManager
+from pycode_kg.store import GraphStore
 
 
 def _has_pycodekg_config(repo_root: Path) -> bool:
@@ -109,13 +116,6 @@ def init(
 
         pycodekg init --repo .
     """
-    from pycode_kg.cli.cmd_build_full import (
-        _run_pipeline,  # noqa: PLC0415  # pylint: disable=import-outside-toplevel
-    )
-    from pycode_kg.cli.cmd_hooks import (
-        _PRE_COMMIT_HOOK,  # noqa: PLC0415  # pylint: disable=import-outside-toplevel
-    )
-
     repo_root = Path(repo).resolve()
     t_total = time.monotonic()
 
@@ -229,21 +229,6 @@ def init(
             branch = "unknown"
 
         try:
-            import importlib.metadata  # noqa: PLC0415  # pylint: disable=import-outside-toplevel
-
-            from pycode_kg.kg import (
-                PyCodeKG,  # noqa: PLC0415  # pylint: disable=import-outside-toplevel
-            )
-            from pycode_kg.pycodekg_thorough_analysis import (
-                PyCodeKGAnalyzer,  # noqa: PLC0415  # pylint: disable=import-outside-toplevel
-            )
-            from pycode_kg.snapshots import (
-                SnapshotManager,  # noqa: PLC0415  # pylint: disable=import-outside-toplevel
-            )
-            from pycode_kg.store import (
-                GraphStore,  # noqa: PLC0415  # pylint: disable=import-outside-toplevel
-            )
-
             db_path = repo_root / ".pycodekg" / "graph.sqlite"
             snapshots_path = repo_root / ".pycodekg" / "snapshots"
             lancedb_dir = repo_root / ".pycodekg" / "lancedb"

{pycode_kg-0.16.0 → pycode_kg-0.17.1}/src/pycode_kg/index.py

@@ -23,7 +23,47 @@ from typing import TYPE_CHECKING
 
 import numpy as np
 
-from pycode_kg.pycodekg import DEFAULT_MODEL
+# ---------------------------------------------------------------------------
+# Vendored from kg_utils.embed (pure stdlib — no PyPI package available yet)
+# ---------------------------------------------------------------------------
+
+DEFAULT_MODEL: str = "BAAI/bge-small-en-v1.5"
+
+_KNOWN_MODELS: dict[str, str] = {
+    "default": "BAAI/bge-small-en-v1.5",
+    "bge-small": "BAAI/bge-small-en-v1.5",
+    "bge-small-en-v1.5": "BAAI/bge-small-en-v1.5",
+    "bge-large": "BAAI/bge-large-en-v1.5",
+    "bge-large-en-v1.5": "BAAI/bge-large-en-v1.5",
+    "all-MiniLM-L6-v2": "sentence-transformers/all-MiniLM-L6-v2",
+    "all-mpnet-base-v2": "sentence-transformers/all-mpnet-base-v2",
+    "nomic": "nomic-ai/nomic-embed-text-v1.5",
+    "nomic-v1.5": "nomic-ai/nomic-embed-text-v1.5",
+}
+
+
+def _kg_model_cache_dir() -> Path:
+    env = os.environ.get("KGRAG_MODEL_DIR")
+    if env:
+        return Path(env).resolve()
+    return Path.home() / ".kgrag" / "models"
+
+
+def resolve_model_path(model_name: str, local_fallback: Path | None = None) -> Path:
+    """Return the local cache path for *model_name*.
+
+    Checks ``KGRAG_MODEL_DIR`` first (system-wide override), then
+    *local_fallback* if provided, otherwise ``~/.kgrag/models/``.
+
+    :param model_name: HuggingFace model identifier or short alias.
+    :param local_fallback: Per-module fallback when no env var is set.
+    :return: Absolute :class:`~pathlib.Path` to the model directory.
+    """
+    resolved = _KNOWN_MODELS.get(model_name, model_name)
+    if os.environ.get("KGRAG_MODEL_DIR") or local_fallback is None:
+        return _kg_model_cache_dir() / resolved.replace("/", os.sep)
+    return local_fallback / resolved.replace("/", "--")
+
 
 # ---------------------------------------------------------------------------
 # Local model cache
@@ -33,22 +73,13 @@ from pycode_kg.pycodekg import DEFAULT_MODEL
 def _local_model_path(model_name: str) -> Path:
     """Return the local cache path for *model_name*.
 
-    Defaults to ``.pycodekg/models/<model>`` under the current working directory
-    so the cache lives alongside the rest of the PyCodeKG artefacts.
-    Override via the ``PYCODEKG_MODEL_DIR`` environment variable.
-
-    Slashes in the model name (e.g. ``org/model``) are replaced with ``--``
-    so the path is always a single directory level under the cache root.
+    Checks ``KGRAG_MODEL_DIR`` first (system-wide override), then falls back
+    to ``.pycodekg/models/`` under the current working directory.
 
-    :param model_name: HuggingFace model identifier or short name.
+    :param model_name: HuggingFace model identifier or short alias.
     :return: Absolute :class:`~pathlib.Path` to the cached model directory.
     """
-    import os  # pylint: disable=import-outside-toplevel
-
-    default = str(Path.cwd() / ".pycodekg" / "models")
-    cache_root = Path(os.environ.get("PYCODEKG_MODEL_DIR", default))
-    safe_name = model_name.replace("/", "--")
-    return cache_root / safe_name
+    return resolve_model_path(model_name, local_fallback=Path.cwd() / ".pycodekg" / "models")
 
 
 if TYPE_CHECKING:
@@ -79,6 +110,7 @@ def suppress_ingestion_logging() -> None:
         import transformers  # pylint: disable=import-outside-toplevel
 
         transformers.logging.set_verbosity_error()
+        transformers.logging.disable_progress_bar()
     except (ImportError, AttributeError):
         pass
 
@@ -145,6 +177,7 @@ class SentenceTransformerEmbedder(Embedder):
         from transformers import logging as hf_logging  # pylint: disable=import-outside-toplevel
 
         hf_logging.set_verbosity_error()
+        hf_logging.disable_progress_bar()
 
         local_path = _local_model_path(model_name)
         _prev_tqdm = os.environ.get("TQDM_DISABLE")

{pycode_kg-0.16.0 → pycode_kg-0.17.1}/src/pycode_kg/pycodekg.py

@@ -34,16 +34,12 @@ from collections.abc import Iterable
 from dataclasses import dataclass
 from pathlib import Path
 
-from pycode_kg.utils import node_id, rel_module_path
-from pycode_kg.visitor import PyCodeKGVisitor
-
 # ============================================================================
 # Configuration
 # ============================================================================
-
-#: Default sentence-transformer model.  Override via the ``PYCODEKG_MODEL``
-#: environment variable, e.g. ``export PYCODEKG_MODEL=BAAI/bge-small-en-v1.5``.
-DEFAULT_MODEL: str = os.environ.get("PYCODEKG_MODEL", "BAAI/bge-small-en-v1.5")
+from pycode_kg.index import DEFAULT_MODEL as DEFAULT_MODEL  # noqa: F401 — re-exported
+from pycode_kg.utils import node_id, rel_module_path
+from pycode_kg.visitor import PyCodeKGVisitor
 
 # ============================================================================
 # Graph primitives (LOCKED v0 CONTRACT)