From 3610ef2830851f639a3dc241e37c018fbb0f319a Mon Sep 17 00:00:00 2001
From: Harrison Chase <hw.chase.17@gmail.com>
Date: Tue, 7 Mar 2023 15:23:46 -0800
Subject: [PATCH] add fake embeddings class (#1503)

---
 .../modules/indexes/examples/embeddings.ipynb | 60 ++++++++++++++++++-
 langchain/embeddings/__init__.py              |  2 +
 langchain/embeddings/fake.py                  | 19 ++++++
 3 files changed, 80 insertions(+), 1 deletion(-)
 create mode 100644 langchain/embeddings/fake.py

diff --git a/docs/modules/indexes/examples/embeddings.ipynb b/docs/modules/indexes/examples/embeddings.ipynb
index bac1a35c..080441c1 100644
--- a/docs/modules/indexes/examples/embeddings.ipynb
+++ b/docs/modules/indexes/examples/embeddings.ipynb
@@ -463,6 +463,64 @@
    "source": [
     "query_result = embeddings.embed_query(text)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f9c02c78",
+   "metadata": {},
+   "source": [
+    "## Fake Embeddings\n",
+    "\n",
+    "LangChain also provides a fake embedding class. You can use this to test your pipelines."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "2ffc2e4b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import FakeEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "80777571",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = FakeEmbeddings(size=1352)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "3ec9d8f0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_result = embeddings.embed_query(\"foo\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "3b9ae9e1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc_results = embeddings.embed_documents([\"foo\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88d366bd",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -481,7 +539,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {
diff --git a/langchain/embeddings/__init__.py b/langchain/embeddings/__init__.py
index 403616c5..261447b1 100644
--- a/langchain/embeddings/__init__.py
+++ b/langchain/embeddings/__init__.py
@@ -3,6 +3,7 @@ import logging
 from typing import Any
 
 from langchain.embeddings.cohere import CohereEmbeddings
+from langchain.embeddings.fake import FakeEmbeddings
 from langchain.embeddings.huggingface import (
     HuggingFaceEmbeddings,
     HuggingFaceInstructEmbeddings,
@@ -28,6 +29,7 @@ __all__ = [
     "SelfHostedEmbeddings",
     "SelfHostedHuggingFaceEmbeddings",
     "SelfHostedHuggingFaceInstructEmbeddings",
+    "FakeEmbeddings",
 ]
 
 
diff --git a/langchain/embeddings/fake.py b/langchain/embeddings/fake.py
new file mode 100644
index 00000000..9328f927
--- /dev/null
+++ b/langchain/embeddings/fake.py
@@ -0,0 +1,19 @@
+from typing import List
+
+import numpy as np
+from pydantic import BaseModel
+
+from langchain.embeddings.base import Embeddings
+
+
+class FakeEmbeddings(Embeddings, BaseModel):
+    size: int
+
+    def _get_embedding(self) -> List[float]:
+        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()