Run mypy/black on commit (#56)

Run the following on commit
- ``mypy``
- ``black``
- ``isort``

Also lots of fixes to satisfy mypy

Author: Sam Partee

.github/workflows/lint.yml

@@ -0,0 +1,48 @@
+
+name: check
+
+on:
+  pull_request:
+  push:
+    branches:
+      - main
+
+jobs:
+  check:
+    name: Style-check ${{ matrix.python-version }}
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        # Only lint on the min and max supported Python versions.
+        # It's extremely unlikely that there's a lint issue on any version in between
+        # that doesn't show up on the min or max versions.
+        #
+        # GitHub rate-limits how many jobs can be running at any one time.
+        # Starting new jobs is also relatively slow,
+        # so linting on fewer versions makes CI faster.
+        python-version:
+          - "3.8"
+          - "3.11"
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install .[dev,all]
+
+    - name: check-sort-import
+      run: |
+        make check-sort-imports
+
+    - name: check-black-format
+      run: |
+        make check-format
+
+    - name: check-mypy
+      run: |
+        make mypy

Makefile

@@ -19,27 +19,32 @@ help:
 # help: Style
 # help: -------
 
-# help: style                          - Sort imports and format with black
-.PHONY: style
-style: sort-imports format
-
-
-# help: check-style                    - check code style compliance
-.PHONY: check-style
-check-style: check-sort-imports check-format
-
+# help: check                          - run all checks for a commit
+.PHONY: check
+check: check-format check-sort-imports mypy
 
 # help: format                         - perform code style format
 .PHONY: format
-format:
+format: sort-imports
 	@black ./redisvl ./tests/
 
 
+# help: check-format                   - check code format compliance
+.PHONY: check-format
+check-format:
+	@black --check ./redisvl
+
+
 # help: sort-imports                   - apply import sort ordering
 .PHONY: sort-imports
 sort-imports:
 	@isort ./redisvl ./tests/ --profile black
 
+# help: check-sort-imports             - check imports are sorted
+.PHONY: check-sort-imports
+check-sort-imports:
+	@isort ./redisvl --check-only --profile black
+
 
 # help: check-lint                     - run static analysis checks
 .PHONY: check-lint

redisvl/index.py

@@ -29,7 +29,7 @@ def __init__(
         self,
         name: str,
         prefix: str = "rvl",
-        storage_type: Optional[str] = "hash",
+        storage_type: str = "hash",
         fields: Optional[List["Field"]] = None,
     ):
         self._name = name
@@ -62,7 +62,7 @@ def search(self, *args, **kwargs) -> List["Result"]:
         Returns:
             List[Result]: A list of search results
         """
-        results: List["Result"] = self._redis_conn.ft(self._name).search(
+        results: List["Result"] = self._redis_conn.ft(self._name).search(  # type: ignore
             *args, **kwargs
         )
         return results
@@ -148,7 +148,7 @@ def disconnect(self):
         """Disconnect from the Redis instance"""
         self._redis_conn = None
 
-    def _get_key(self, record: Dict[str, Any], key_field: str = None) -> str:
+    def _get_key(self, record: Dict[str, Any], key_field: Optional[str] = None) -> str:
         """Construct the Redis HASH top level key.
 
         Args:
@@ -236,7 +236,7 @@ def __init__(
         self,
         name: str,
         prefix: str = "rvl",
-        storage_type: Optional[str] = "hash",
+        storage_type: str = "hash",
         fields: Optional[List["Field"]] = None,
     ):
         super().__init__(name, prefix, storage_type, fields)
@@ -313,7 +313,7 @@ def create(self, overwrite: Optional[bool] = False):
         # set storage_type, default to hash
         storage_type = IndexType.HASH
         if self._storage.lower() == "json":
-            self._storage = IndexType.JSON
+            storage_type = IndexType.JSON
 
         # Create Index
         # will raise correct response error if index already exists
@@ -358,7 +358,7 @@ def load(
 
             # Check if outer interface passes in TTL on load
             ttl = kwargs.get("ttl")
-            with self._redis_conn.pipeline(transaction=False) as pipe:
+            with self._redis_conn.pipeline(transaction=False) as pipe:  # type: ignore
                 for record in data:
                     key = self._get_key(record, key_field)
                     pipe.hset(key, mapping=record)  # type: ignore
@@ -394,7 +394,7 @@ def __init__(
         self,
         name: str,
         prefix: str = "rvl",
-        storage_type: Optional[str] = "hash",
+        storage_type: str = "hash",
         fields: Optional[List["Field"]] = None,
     ):
         super().__init__(name, prefix, storage_type, fields)
@@ -467,7 +467,7 @@ async def create(self, overwrite: Optional[bool] = False):
         # set storage_type, default to hash
         storage_type = IndexType.HASH
         if self._storage.lower() == "json":
-            self._storage = IndexType.JSON
+            storage_type = IndexType.JSON
 
         # Create Index
         await self._redis_conn.ft(self._name).create_index(  # type: ignore
@@ -516,7 +516,7 @@ async def _load(record: dict):
                 key = self._get_key(record, key_field)
                 await self._redis_conn.hset(key, mapping=record)  # type: ignore
                 if ttl:
-                    await self._redis_conn.expire(key, ttl)
+                    await self._redis_conn.expire(key, ttl)  # type: ignore
 
         # gather with concurrency
         await asyncio.gather(*[_load(record) for record in data])

redisvl/llmcache/semantic.py

@@ -1,6 +1,6 @@
 from typing import List, Optional, Union
 
-from redis.commands.search.field import VectorField
+from redis.commands.search.field import Field, VectorField
 
 from redisvl.index import SearchIndex
 from redisvl.llmcache.base import BaseLLMCache
@@ -14,8 +14,8 @@ class SemanticCache(BaseLLMCache):
     """Cache for Large Language Models."""
 
     # TODO allow for user to change default fields
-    _vector_field_name = "prompt_vector"
-    _default_fields = [
+    _vector_field_name: str = "prompt_vector"
+    _default_fields: List[Field] = [
         VectorField(
             _vector_field_name,
             "FLAT",
@@ -25,27 +25,27 @@ class SemanticCache(BaseLLMCache):
 
     def __init__(
         self,
-        index_name: Optional[str] = "cache",
-        prefix: Optional[str] = "llmcache",
-        threshold: Optional[float] = 0.9,
+        index_name: str = "cache",
+        prefix: str = "llmcache",
+        threshold: float = 0.9,
         ttl: Optional[int] = None,
-        vectorizer: Optional[BaseVectorizer] = HFTextVectorizer(
+        vectorizer: BaseVectorizer = HFTextVectorizer(
             "sentence-transformers/all-mpnet-base-v2"
         ),
-        redis_url: Optional[str] = "redis://localhost:6379",
+        redis_url: str = "redis://localhost:6379",
         connection_args: Optional[dict] = None,
         index: Optional[SearchIndex] = None,
     ):
         """Semantic Cache for Large Language Models.
 
         Args:
-            index_name (Optional[str], optional): The name of the index. Defaults to "cache".
-            prefix (Optional[str], optional): The prefix for the index. Defaults to "llmcache".
-            threshold (Optional[float], optional): Semantic threshold for the cache. Defaults to 0.9.
+            index_name (str, optional): The name of the index. Defaults to "cache".
+            prefix (str, optional): The prefix for the index. Defaults to "llmcache".
+            threshold (float, optional): Semantic threshold for the cache. Defaults to 0.9.
             ttl (Optional[int], optional): The TTL for the cache. Defaults to None.
-            vectorizer (Optional[BaseVectorizer], optional): The vectorizer for the cache.
+            vectorizer (BaseVectorizer, optional): The vectorizer for the cache.
                 Defaults to HFTextVectorizer("sentence-transformers/all-mpnet-base-v2").
-            redis_url (Optional[str], optional): The redis url. Defaults to "redis://localhost:6379".
+            redis_url (str, optional): The redis url. Defaults to "redis://localhost:6379".
             connection_args (Optional[dict], optional): The connection arguments for the redis client. Defaults to None.
             index (Optional[SearchIndex], optional): The underlying search index to use for the semantic cache. Defaults to None.
 

redisvl/query/__init__.py

@@ -1,3 +1,3 @@
-from redisvl.query.query import FilterQuery, VectorQuery, RangeQuery
+from redisvl.query.query import FilterQuery, RangeQuery, VectorQuery
 
 __all__ = ["VectorQuery", "FilterQuery", "RangeQuery"]