Add embeddings for LocalAI (#8134)

Description:

This PR adds embeddings for LocalAI (
https://github.com/go-skynet/LocalAI ), a self-hosted OpenAI drop-in
replacement. As LocalAI can re-use OpenAI clients it is mostly following
the lines of the OpenAI embeddings, however when embedding documents, it
just uses string instead of sending tokens as sending tokens is
best-effort depending on the model being used in LocalAI. Sending tokens
is also tricky as token id's can mismatch with the model - so it's safer
to just send strings in this case.

Partly related to: #5256

Dependencies: No new dependencies

Twitter: @mudler_it
---------

Signed-off-by: mudler <mudler@localai.io>
Co-authored-by: Bagatur <baskaryan@gmail.com>

docs/extras/integrations/text_embedding/localai.ipynb

@@ -0,0 +1,161 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "278b6c63",
+   "metadata": {},
+   "source": [
+    "# LocalAI\n",
+    "\n",
+    "Let's load the LocalAI Embedding class. In order to use the LocalAI Embedding class, you need to have the LocalAI service hosted somewhere and configure the embedding models. See the documentation at https://localai.io/basics/getting_started/index.html and https://localai.io/features/embeddings/index.html."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "0be1af71",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import LocalAIEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2c66e5da",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = LocalAIEmbeddings(openai_api_base=\"http://localhost:8080\", model=\"embedding-model-name\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "01370375",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text = \"This is a test document.\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "bfb6142c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_result = embeddings.embed_query(text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "0356c3b7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc_result = embeddings.embed_documents([text])"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "bb61bbeb",
+   "metadata": {},
+   "source": [
+    "Let's load the LocalAI Embedding class with first generation models (e.g. text-search-ada-doc-001/text-search-ada-query-001). Note: These are not recommended models - see [here](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c0b072cc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import LocalAIEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a56b70f5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = LocalAIEmbeddings(openai_api_base=\"http://localhost:8080\", model=\"embedding-model-name\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "14aefb64",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text = \"This is a test document.\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3c39ed33",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_result = embeddings.embed_query(text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e3221db6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc_result = embeddings.embed_documents([text])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aaad49f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# if you are behind an explicit proxy, you can use the OPENAI_PROXY environment variable to pass through\n",
+    "os.environ[\"OPENAI_PROXY\"] = \"http://proxy.yourcompany.com:8080\""
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.11.1 64-bit",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.1"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "e971737741ff4ec9aff7dc6155a1060a59a8a6d52c757dbbe66bf8ee389494b1"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

libs/langchain/langchain/embeddings/__init__.py

@@ -23,6 +23,7 @@
 from langchain.embeddings.huggingface_hub import HuggingFaceHubEmbeddings
 from langchain.embeddings.jina import JinaEmbeddings
 from langchain.embeddings.llamacpp import LlamaCppEmbeddings
+from langchain.embeddings.localai import LocalAIEmbeddings
 from langchain.embeddings.minimax import MiniMaxEmbeddings
 from langchain.embeddings.mlflow_gateway import MlflowAIGatewayEmbeddings
 from langchain.embeddings.modelscope_hub import ModelScopeEmbeddings
@@ -76,6 +77,7 @@
     "SpacyEmbeddings",
     "NLPCloudEmbeddings",
     "GPT4AllEmbeddings",
+    "LocalAIEmbeddings",
 ]