Feat: implemented vector store service

typings/langchain_community/embeddings/__init__.pyi

@@ -0,0 +1,14 @@
+from __future__ import annotations
+
+from collections.abc import Sequence
+
+from langchain_core.embeddings import Embeddings
+
+class FakeEmbeddings(Embeddings):
+    """Deterministic embeddings generator used for testing."""
+
+    def __init__(self, *, size: int = ...) -> None: ...
+    def embed_documents(self, texts: Sequence[str]) -> list[list[float]]: ...
+    def embed_query(self, text: str) -> list[float]: ...
+
+__all__ = ["FakeEmbeddings"]

typings/langchain_community/vectorstores/faiss.pyi

@@ -0,0 +1,44 @@
+from __future__ import annotations
+
+from collections.abc import Sequence
+from typing import Any, Protocol
+
+from langchain_core.embeddings import Embeddings
+
+class _VectorDocument(Protocol):
+    metadata: dict[str, Any]
+    page_content: str
+
+class FAISS:
+    """Subset of the FAISS vector store methods used in CleverAgents."""
+
+    @classmethod
+    def from_texts(
+        cls,
+        texts: Sequence[str],
+        embedding: Embeddings,
+        metadatas: Sequence[dict[str, Any]] | None = ...,
+        ids: Sequence[str] | None = ...,
+        **kwargs: Any,
+    ) -> FAISS: ...
+    def save_local(self, folder_path: str) -> None: ...
+    @classmethod
+    def load_local(
+        cls,
+        folder_path: str,
+        embeddings: Embeddings,
+        *,
+        allow_dangerous_deserialization: bool = ...,
+        **kwargs: Any,
+    ) -> FAISS: ...
+    def similarity_search_with_score(
+        self,
+        query: str,
+        *,
+        k: int = ...,
+        filter: Any = ...,
+        fetch_k: int = ...,
+        **kwargs: Any,
+    ) -> list[tuple[_VectorDocument, float]]: ...
+
+__all__ = ["FAISS"]

typings/langchain_core/embeddings/__init__.pyi

@@ -0,0 +1,9 @@
+from __future__ import annotations
+
+from collections.abc import Sequence
+
+class Embeddings:
+    """Minimal embeddings protocol used for typing."""
+
+    def embed_documents(self, texts: Sequence[str]) -> list[list[float]]: ...
+    def embed_query(self, text: str) -> list[float]: ...

typings/langchain_openai/__init__.pyi

@@ -1,7 +1,9 @@
 """Type stubs for langchain_openai package."""
 
+from collections.abc import Sequence
 from typing import Any
 
+from langchain_core.embeddings import Embeddings as _Embeddings
 from langchain_core.language_models import BaseLanguageModel
 
 class ChatOpenAI(BaseLanguageModel):
@@ -43,4 +45,18 @@ class AzureChatOpenAI(BaseLanguageModel):
         **kwargs: Any,
     ) -> None: ...
 
-__all__ = ["ChatOpenAI", "AzureChatOpenAI"]
+class OpenAIEmbeddings(_Embeddings):
+    """OpenAI embeddings wrapper used for vector stores."""
+
+    def __init__(
+        self,
+        *,
+        model: str = ...,
+        dimensions: int | None = None,
+        api_key: Any = None,
+        **kwargs: Any,
+    ) -> None: ...
+    def embed_documents(self, texts: Sequence[str]) -> list[list[float]]: ...
+    def embed_query(self, text: str) -> list[float]: ...
+
+__all__ = ["AzureChatOpenAI", "ChatOpenAI", "OpenAIEmbeddings"]