community[minor]: Add ITREX optimized Embeddings (langchain-ai#18474)

Introduction [Intel® Extension for Transformers](https://github.com/intel/intel-extension-for-transformers) is an innovative toolkit designed to accelerate GenAI/LLM everywhere with the optimal performance of Transformer-based models on various Intel platforms Description adding ITREX runtime embeddings using intel-extension-for-transformers. added mdx documentation and example notebooks added embedding import testing. --------- Signed-off-by: yuwenzho <[email protected]> Co-authored-by: Bagatur <[email protected]>
billytrend-cohere · Mar 27, 2024 · 3a7d2cf · 3a7d2cf
1 parent 1fe10a3
commit 3a7d2cf
Show file tree

Hide file tree

Showing 7 changed files with 365 additions and 26 deletions.
diff --git a/docs/docs/integrations/providers/intel.mdx b/docs/docs/integrations/providers/intel.mdx
@@ -0,0 +1,60 @@
+# Intel
+
+>[Optimum Intel](https://github.com/huggingface/optimum-intel?tab=readme-ov-file#optimum-intel) is the interface between the 🤗 Transformers and Diffusers libraries and the different tools and libraries provided by Intel to accelerate end-to-end pipelines on Intel architectures.
+
+>[Intel® Extension for Transformers](https://github.com/intel/intel-extension-for-transformers?tab=readme-ov-file#intel-extension-for-transformers) (ITREX) is an innovative toolkit designed to accelerate GenAI/LLM everywhere with the optimal performance of Transformer-based models on various Intel platforms, including Intel Gaudi2, Intel CPU, and Intel GPU.
+
+This page covers how to use optimum-intel and ITREX with LangChain.
+
+## Optimum-intel
+
+All functionality related to the [optimum-intel](https://github.com/huggingface/optimum-intel.git) and [IPEX](https://github.com/intel/intel-extension-for-pytorch).
+
+### Installation
+
+Install using optimum-intel and ipex using:
+
+```bash
+pip install optimum[neural-compressor]
+pip install intel_extension_for_pytorch
+```
+
+Please follow the installation instructions as specified below:
+
+* Install optimum-intel as shown [here](https://github.com/huggingface/optimum-intel).
+* Install IPEX as shown [here](https://intel.github.io/intel-extension-for-pytorch/index.html#installation?platform=cpu&version=v2.2.0%2Bcpu).
+
+### Embedding Models
+
+See a [usage example](/docs/integrations/text_embedding/optimum_intel).
+We also offer a full tutorial notebook "rag_with_quantized_embeddings.ipynb" for using the embedder in a RAG pipeline in the cookbook dir.
+
+```python
+from langchain_community.embeddings import QuantizedBiEncoderEmbeddings
+```
+
+## Intel® Extension for Transformers (ITREX)
+
+All functionality related to the [intel-extension-for-transformers](https://github.com/intel/intel-extension-for-transformers).
+
+### Installation
+
+Install intel-extension-for-transformers. For system requirements and other installation tips, please refer to [Installation Guide](https://github.com/intel/intel-extension-for-transformers/blob/main/docs/installation.md)
+
+```bash
+pip install intel-extension-for-transformers
+```
+
+Install other required packages.
+
+```bash
+pip install -U torch onnx accelerate datasets
+```
+
+### Embedding Models
+
+See a [usage example](/docs/integrations/text_embedding/itrex).
+
+```python
+from langchain_community.embeddings import QuantizedBgeEmbeddings
+```
diff --git a/docs/docs/integrations/providers/optimum_intel.mdx b/docs/docs/integrations/providers/optimum_intel.mdx
diff --git a/docs/docs/integrations/text_embedding/itrex.ipynb b/docs/docs/integrations/text_embedding/itrex.ipynb
@@ -0,0 +1,85 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Intel® Extension for Transformers Quantized Text Embeddings\n",
+    "\n",
+    "Load quantized BGE embedding models generated by [Intel® Extension for Transformers](https://github.com/intel/intel-extension-for-transformers) (ITREX) and use ITREX [Neural Engine](https://github.com/intel/intel-extension-for-transformers/blob/main/intel_extension_for_transformers/llm/runtime/deprecated/docs/Installation.md), a high-performance NLP backend, to accelerate the inference of models without compromising accuracy.\n",
+    "\n",
+    "Refer to our blog of [Efficient Natural Language Embedding Models with Intel Extension for Transformers](https://medium.com/intel-analytics-software/efficient-natural-language-embedding-models-with-intel-extension-for-transformers-2b6fcd0f8f34) and [BGE optimization example](https://github.com/intel/intel-extension-for-transformers/tree/main/examples/huggingface/pytorch/text-embedding/deployment/mteb/bge) for more details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/yuwenzho/.conda/envs/bge/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n",
+      "2024-03-04 10:17:17 [INFO] Start to extarct onnx model ops...\n",
+      "2024-03-04 10:17:17 [INFO] Extract onnxruntime model done...\n",
+      "2024-03-04 10:17:17 [INFO] Start to implement Sub-Graph matching and replacing...\n",
+      "2024-03-04 10:17:18 [INFO] Sub-Graph match and replace done...\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain_community.embeddings import QuantizedBgeEmbeddings\n",
+    "\n",
+    "model_name = \"Intel/bge-small-en-v1.5-sts-int8-static-inc\"\n",
+    "encode_kwargs = {\"normalize_embeddings\": True}  # set True to compute cosine similarity\n",
+    "\n",
+    "model = QuantizedBgeEmbeddings(\n",
+    "    model_name=model_name,\n",
+    "    encode_kwargs=encode_kwargs,\n",
+    "    query_instruction=\"Represent this sentence for searching relevant passages: \",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text = \"This is a test document.\"\n",
+    "query_result = model.embed_query(text)\n",
+    "doc_result = model.embed_documents([text])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "yuwen",
+   "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": "3.9.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/docs/vercel.json b/docs/vercel.json
@@ -1,5 +1,9 @@
 {
   "redirects": [
+    {
+      "source": "/docs/integrations/providers/optimum_intel",
+      "destination": "/docs/integrations/providers/intel"
+    },
     {
       "source": "/docs/integrations/providers/facebook_chat",
       "destination": "/docs/integrations/providers/facebook"

diff --git a/libs/community/langchain_community/embeddings/__init__.py b/libs/community/langchain_community/embeddings/__init__.py
@@ -67,6 +67,7 @@
     "OllamaEmbeddings": "langchain_community.embeddings.ollama",
     "OpenAIEmbeddings": "langchain_community.embeddings.openai",
     "QianfanEmbeddingsEndpoint": "langchain_community.embeddings.baidu_qianfan_endpoint",  # noqa: E501
+    "QuantizedBgeEmbeddings": "langchain_community.embeddings.itrex",
     "QuantizedBiEncoderEmbeddings": "langchain_community.embeddings.optimum_intel",
     "SagemakerEndpointEmbeddings": "langchain_community.embeddings.sagemaker_endpoint",
     "SelfHostedEmbeddings": "langchain_community.embeddings.self_hosted",