Jon/several improvements (#174)

Apply project setup improvements related to pre-commit and mypy

* Add TYPE_CHECKING for pinecone and weviate

* Ruff format

* Remove redundant check

* Fix end-of-file-fixer

* Improve pre-commit config

* Improve pr.yaml

* Fix pinecone type

* Add CODEOWNERS

Author: jonbesga

.github/CODEOWNERS

@@ -0,0 +1 @@
+* @neo4j/team-gen-ai

.github/workflows/pr.yaml

@@ -32,14 +32,13 @@ jobs:
           key: venv-${{ runner.os }}-${{ matrix.python-version }}-${{ hashFiles('**/poetry.lock') }}
       - name: Install dependencies
         if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
-        run: poetry install --no-interaction --extras external_clients
+        run: poetry install --no-interaction
       - name: Check format and linting
         run: |
-          poetry run ruff check --select I .
           poetry run ruff check .
           poetry run ruff format --check .
       - name: Run strict mypy check
-        run: poetry run mypy --strict --ignore-missing-imports --allow-subclassing-any --allow-untyped-calls .
+        run: poetry run mypy .
       - name: Run unit tests and check coverage
         run: |
           poetry run coverage run -m pytest tests/unit

.pre-commit-config.yaml

@@ -4,33 +4,31 @@ repos:
     hooks:
     - id: trailing-whitespace
     - id: end-of-file-fixer
-  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.10.0
-    hooks:
-      - id: mypy
-        name: Mypy Type Check
-        entry: mypy
-        language: python
-        types: [ python ]
-        stages: [ commit, push ]
-        args: [--strict, --ignore-missing-imports, --allow-subclassing-any, --allow-untyped-calls]
-        additional_dependencies:
-          - pytest
-          - pydantic
-          - neo4j
-          - langchain_community
-          - langchain_openai
   - repo: local
     hooks:
       - id: ruff-lint-isort
         name: Ruff Lint Sort Imports
-        entry: poetry run ruff check --select I .
+        entry: poetry run ruff check .
         language: system
         types: [ python ]
         stages: [ commit, push ]
       - id: ruff-lint
         name: Ruff Lint Check
-        entry: poetry run ruff format --check
+        entry: poetry run ruff format --check .
+        language: system
+        types: [ python ]
+        stages: [ commit, push ]
+      - id: mypy
+        name: Mypy Type Check
+        entry: mypy .
         language: system
         types: [ python ]
         stages: [ commit, push ]
+        pass_filenames: false
+        args: [
+          --strict,
+          --ignore-missing-imports,
+          --allow-untyped-calls,
+          --allow-subclassing-any,
+          --exclude='./docs/'
+        ]

docs/Makefile

@@ -191,4 +191,4 @@ xml:
 pseudoxml:
 	$(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
 	@echo
-	@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."
+	@echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."

docs/source/types.rst

@@ -81,4 +81,4 @@ SchemaRelation
 SchemaConfig
 ============
 
-.. autoclass:: neo4j_graphrag.experimental.components.schema.SchemaConfig
+.. autoclass:: neo4j_graphrag.experimental.components.schema.SchemaConfig

docs/source/user_guide_pipeline.rst

@@ -130,4 +130,4 @@ can be added to the canvas by setting `hide_unused_outputs` to `False`:
 Here is an example of final result:
 
 .. image:: images/pipeline_full.png
-  :alt: Pipeline visualisation
+  :alt: Pipeline visualisation

src/neo4j_graphrag/retrievers/external/pinecone/pinecone.py

@@ -15,10 +15,9 @@
 from __future__ import annotations
 
 import logging
-from typing import Any, Callable, Optional
+from typing import TYPE_CHECKING, Any, Callable, Optional
 
 import neo4j
-from pinecone import Pinecone
 from pydantic import ValidationError
 
 from neo4j_graphrag.embeddings.base import Embedder
@@ -41,6 +40,9 @@
     RetrieverResultItem,
 )
 
+if TYPE_CHECKING:
+    from pinecone import Pinecone
+
 logger = logging.getLogger(__name__)
 
 

src/neo4j_graphrag/retrievers/external/pinecone/types.py

@@ -17,7 +17,10 @@
 from typing import Any, Callable, Optional, Union
 
 import neo4j
+
+
 from pinecone import Pinecone
+
 from pydantic import (
     BaseModel,
     ConfigDict,

src/neo4j_graphrag/retrievers/external/weaviate/weaviate.py

@@ -15,12 +15,11 @@
 from __future__ import annotations
 
 import logging
-from typing import Any, Callable, Optional
+from typing import Any, Callable, Optional, TYPE_CHECKING
 
 import neo4j
 import weaviate.classes as wvc
 from pydantic import ValidationError
-from weaviate.client import WeaviateClient
 
 from neo4j_graphrag.embeddings.base import Embedder
 from neo4j_graphrag.exceptions import (
@@ -43,6 +42,9 @@
 
 logger = logging.getLogger(__name__)
 
+if TYPE_CHECKING:
+    from weaviate.client import WeaviateClient
+
 
 class WeaviateNeo4jRetriever(ExternalRetriever):
     """