Class for Optimum-Intel Embedding Model (#10500)

* Initial commit for integrating Optimum Intel with v0.10

Based on the Optimum integration.

* Test

* Dependencies

* Neural compressor code

* Notebook example

* Lock file

docs/examples/embeddings/optimum_intel.ipynb

@@ -0,0 +1,87 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/examples/embeddings/huggingface.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Optimized Embedding Model using Optimum-Intel\n",
+    "\n",
+    "LlamaIndex has support for loading quantized embedding models for Intel, using the [Optimum-Intel library](https://huggingface.co/docs/optimum/main/en/intel/index). \n",
+    "\n",
+    "Optimized models are smaller and faster, with minimal accuracy loss, see the [documentation](https://huggingface.co/docs/optimum/main/en/intel/optimization_inc) and an [optimization guide](https://huggingface.co/docs/optimum/main/en/intel/optimization_inc) using the IntelLabs/fastRAG library. \n",
+    "\n",
+    "In order to be able to load and use the quantized models, install the required dependency `pip install optimum[exporters] optimum-intel neural-compressor`. \n",
+    "\n",
+    "Loading is done using the class `IntelEmbedding`; usage is similar to any HuggingFace local embedding model. See example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index-embeddings-huggingface-optimum-intel"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.embeddings.huggingface_optimum_intel import IntelEmbedding\n",
+    "\n",
+    "embed_model = IntelEmbedding(\"Intel/bge-small-en-v1.5-rag-int8-static\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "384\n",
+      "[-0.0032782123889774084, -0.013396517373621464, 0.037944991141557693, -0.04642259329557419, 0.027709005400538445]\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = embed_model.get_text_embedding(\"Hello World!\")\n",
+    "print(len(embeddings))\n",
+    "print(embeddings[:5])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

llama-index-integrations/embeddings/llama-index-embeddings-huggingface-optimum-intel/.gitignore

@@ -0,0 +1,153 @@
+llama_index/_static
+.DS_Store
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+bin/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+etc/
+include/
+lib/
+lib64/
+parts/
+sdist/
+share/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+.ruff_cache
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+notebooks/
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+pyvenv.cfg
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Jetbrains
+.idea
+modules/
+*.swp
+
+# VsCode
+.vscode
+
+# pipenv
+Pipfile
+Pipfile.lock
+
+# pyright
+pyrightconfig.json

llama-index-integrations/embeddings/llama-index-embeddings-huggingface-optimum-intel/BUILD

@@ -0,0 +1,3 @@
+poetry_requirements(
+    name="poetry",
+)

llama-index-integrations/embeddings/llama-index-embeddings-huggingface-optimum-intel/Makefile

@@ -0,0 +1,17 @@
+GIT_ROOT ?= $(shell git rev-parse --show-toplevel)
+
+help:	## Show all Makefile targets.
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[33m%-30s\033[0m %s\n", $$1, $$2}'
+
+format:	## Run code autoformatters (black).
+	pre-commit install
+	git ls-files | xargs pre-commit run black --files
+
+lint:	## Run linters: pre-commit (black, ruff, codespell) and mypy
+	pre-commit install && git ls-files | xargs pre-commit run --show-diff-on-failure --files
+
+test:	## Run tests via pytest.
+	pytest tests
+
+watch-docs:	## Build and watch documentation.
+	sphinx-autobuild docs/ docs/_build/html --open-browser --watch $(GIT_ROOT)/llama_index/

llama-index-integrations/embeddings/llama-index-embeddings-huggingface-optimum-intel/README.md

@@ -0,0 +1 @@
+# LlamaIndex Embeddings Integration: Huggingface Optimum Intel

llama-index-integrations/embeddings/llama-index-embeddings-huggingface-optimum-intel/llama_index/embeddings/huggingface_optimum_intel/BUILD

@@ -0,0 +1 @@
+python_sources()

llama-index-integrations/embeddings/llama-index-embeddings-huggingface-optimum-intel/llama_index/embeddings/huggingface_optimum_intel/__init__.py

@@ -0,0 +1,3 @@
+from llama_index.embeddings.huggingface_optimum_intel.base import IntelEmbedding
+
+__all__ = ["IntelEmbedding"]