core[minor]: moved fake llms and embeddings to core (#19226)

- [ ] **PR title**: "core: moved fake llms and embeddings to core"


- [ ] **PR message**:
 - **Description:** moved fake llms and embeddings to core"

libs/core/langchain_core/embeddings/__init__.py

@@ -0,0 +1,4 @@
+from langchain_core.embeddings.embeddings import Embeddings
+from langchain_core.embeddings.fake import DeterministicFakeEmbedding, FakeEmbeddings
+
+__all__ = ["DeterministicFakeEmbedding", "Embeddings", "FakeEmbeddings"]

libs/core/langchain_core/embeddings/embeddings.py

@@ -0,0 +1,25 @@
+"""**Embeddings** interface."""
+from abc import ABC, abstractmethod
+from typing import List
+
+from langchain_core.runnables.config import run_in_executor
+
+
+class Embeddings(ABC):
+    """Interface for embedding models."""
+
+    @abstractmethod
+    def embed_documents(self, texts: List[str]) -> List[List[float]]:
+        """Embed search docs."""
+
+    @abstractmethod
+    def embed_query(self, text: str) -> List[float]:
+        """Embed query text."""
+
+    async def aembed_documents(self, texts: List[str]) -> List[List[float]]:
+        """Asynchronous Embed search docs."""
+        return await run_in_executor(None, self.embed_documents, texts)
+
+    async def aembed_query(self, text: str) -> List[float]:
+        """Asynchronous Embed query text."""
+        return await run_in_executor(None, self.embed_query, text)

libs/core/langchain_core/embeddings/fake.py

@@ -0,0 +1,52 @@
+import hashlib
+from typing import List
+
+from langchain_core.embeddings import Embeddings
+from langchain_core.pydantic_v1 import BaseModel
+
+
+class FakeEmbeddings(Embeddings, BaseModel):
+    """Fake embedding model."""
+
+    size: int
+    """The size of the embedding vector."""
+
+    def _get_embedding(self) -> List[float]:
+        import numpy as np  # type: ignore[import-not-found, import-untyped]
+
+        return list(np.random.normal(size=self.size))
+
+    def embed_documents(self, texts: List[str]) -> List[List[float]]:
+        return [self._get_embedding() for _ in texts]
+
+    def embed_query(self, text: str) -> List[float]:
+        return self._get_embedding()
+
+
+class DeterministicFakeEmbedding(Embeddings, BaseModel):
+    """
+    Fake embedding model that always returns
+    the same embedding vector for the same text.
+    """
+
+    size: int
+    """The size of the embedding vector."""
+
+    def _get_embedding(self, seed: int) -> List[float]:
+        import numpy as np  # type: ignore[import-not-found, import-untyped]
+
+        # set the seed for the random generator
+        np.random.seed(seed)
+        return list(np.random.normal(size=self.size))
+
+    def _get_seed(self, text: str) -> int:
+        """
+        Get a seed for the random generator, using the hash of the text.
+        """
+        return int(hashlib.sha256(text.encode("utf-8")).hexdigest(), 16) % 10**8
+
+    def embed_documents(self, texts: List[str]) -> List[List[float]]:
+        return [self._get_embedding(seed=self._get_seed(_)) for _ in texts]
+
+    def embed_query(self, text: str) -> List[float]:
+        return self._get_embedding(seed=self._get_seed(text))