fixed unittest and lint

Author: Fangrui Liu

docs/modules/indexes/retrievers/examples/qdrant_self_query.ipynb

@@ -1,6 +1,7 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "13afcae7",
    "metadata": {},
@@ -13,12 +14,13 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "68e75fb9",
    "metadata": {},
    "source": [
     "## Creating a Qdrant vectorstore\n",
-    "First we'll want to create a Chroma VectorStore and seed it with some data. We've created a small demo set of documents that contain summaries of movies.\n",
+    "First we'll want to create a Qdrant VectorStore and seed it with some data. We've created a small demo set of documents that contain summaries of movies.\n",
     "\n",
     "NOTE: The self-query retriever requires you to have `lark` installed (`pip install lark`). We also need the `qdrant-client` package."
    ]
@@ -36,6 +38,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "83811610-7df3-4ede-b268-68a6a83ba9e2",
    "metadata": {},
@@ -100,6 +103,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "5ecaab6d",
    "metadata": {},
@@ -149,6 +153,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "ea9df8d4",
    "metadata": {},
@@ -309,6 +314,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "39bd1de1-b9fe-4a98-89da-58d8a7a6ae51",
    "metadata": {},

langchain/retrievers/self_query/myscale.py

@@ -12,18 +12,17 @@
 )
 
 
-def DEFAULT_COMPOSER(op: Union[Comparator, Operator]) -> Callable:
+def DEFAULT_COMPOSER(op_name: str) -> Callable:
     def f(*args: Any) -> str:
-        args = map(str, args)
-        return f" {op} ".join(args)
+        args: Tuple[str] = map(str, args)
+        return f" {op_name} ".join(args)
     return f
 
 
-def FUNCTION_COMPOSER(op: Union[Comparator, Operator]) -> Callable:
+def FUNCTION_COMPOSER(op_name: str) -> Callable:
     def f(*args: Any) -> str:
-        args = map(str, args)
-        return f"{op}({','.join(args)})"
-
+        args: Tuple[str] = map(str, args)
+        return f"{op_name}({','.join(args)})"
     return f
 
 
@@ -50,8 +49,8 @@ class MyScaleTranslator(Visitor):
         Comparator.EQ: DEFAULT_COMPOSER("="),
         Comparator.GT: DEFAULT_COMPOSER(">"),
         Comparator.GTE: DEFAULT_COMPOSER(">="),
-        Comparator.LT: DEFAULT_COMPOSER("<="),
-        Comparator.LTE: DEFAULT_COMPOSER("<"),
+        Comparator.LT: DEFAULT_COMPOSER("<"),
+        Comparator.LTE: DEFAULT_COMPOSER("<="),
         Comparator.CONTAIN: FUNCTION_COMPOSER("has"),
         Comparator.LIKE: DEFAULT_COMPOSER("ILIKE"),
     }

langchain/vectorstores/mongodb_atlas.py

@@ -9,6 +9,8 @@
     Iterable,
     List,
     Optional,
+    Sequence,
+    Mapping,
     Tuple,
     TypeVar,
     Union,
@@ -129,7 +131,7 @@ def _insert_texts(self, texts: List[str], metadatas: List[Dict[str, Any]]) -> Li
             return []
         # Embed and create the documents
         embeddings = self._embedding.embed_documents(texts)
-        to_insert = [
+        to_insert: List[MongoDBDocumentType] = [
             {self._text_key: t, self._embedding_key: embedding, **m}
             for t, m, embedding in zip(texts, metadatas, embeddings)
         ]
@@ -172,7 +174,7 @@ def similarity_search_with_score(
         }
         if pre_filter:
             knn_beta["filter"] = pre_filter
-        pipeline = [
+        pipeline: Sequence[Mapping[str, Any]] = [
             {
                 "$search": {
                     "index": self._index_name,