add optimum intel with ipex backend to llama-index-integration (#14553)

run-llama · Jul 6, 2024 · 2a43f06 · 2a43f06
1 parent fc56ce8
commit 2a43f06
Show file tree

Hide file tree

Showing 9 changed files with 607 additions and 0 deletions.
diff --git a/docs/docs/examples/llm/optimum_intel.ipynb b/docs/docs/examples/llm/optimum_intel.ipynb
@@ -0,0 +1,223 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "978146e2",
+   "metadata": {},
+   "source": [
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/docs/examples/llm/openvino.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f717d3d4-942b-4d86-9435-fc44b3ac6d39",
+   "metadata": {},
+   "source": [
+    "# Optimum Intel LLMs optimized with IPEX backend\n",
+    "\n",
+    "[Optimum Intel](https://github.com/rbrugaro/optimum-intel) accelerates Hugging Face pipelines on Intel architectures leveraging [Intel Extension for Pytorch, (IPEX)](https://github.com/intel/intel-extension-for-pytorch) optimizations\n",
+    "\n",
+    "Optimum Intel models can be run locally through `OptimumIntelLLM` entitiy wrapped by LlamaIndex :"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "90cf0f2e-8d8d-4e42-81bf-866c759221e1",
+   "metadata": {},
+   "source": [
+    "In the below line, we install the packages necessary for this demo:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f413f179",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index-llms-optimum-intel"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3dac8f9f-7136-43f7-9e9f-de679e74d66e",
+   "metadata": {},
+   "source": [
+    "Now that we're set up, let's play around:"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "2c577674",
+   "metadata": {},
+   "source": [
+    "If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "86028752",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install llama-index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0465029c-fe69-454a-9561-55f7a382b2e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.llms.optimum_intel import OptimumIntelLLM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "49122583",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def messages_to_prompt(messages):\n",
+    "    prompt = \"\"\n",
+    "    for message in messages:\n",
+    "        if message.role == \"system\":\n",
+    "            prompt += f\"<|system|>\\n{message.content}</s>\\n\"\n",
+    "        elif message.role == \"user\":\n",
+    "            prompt += f\"<|user|>\\n{message.content}</s>\\n\"\n",
+    "        elif message.role == \"assistant\":\n",
+    "            prompt += f\"<|assistant|>\\n{message.content}</s>\\n\"\n",
+    "\n",
+    "    # ensure we start with a system prompt, insert blank if needed\n",
+    "    if not prompt.startswith(\"<|system|>\\n\"):\n",
+    "        prompt = \"<|system|>\\n</s>\\n\" + prompt\n",
+    "\n",
+    "    # add final assistant prompt\n",
+    "    prompt = prompt + \"<|assistant|>\\n\"\n",
+    "\n",
+    "    return prompt\n",
+    "\n",
+    "\n",
+    "def completion_to_prompt(completion):\n",
+    "    return f\"<|system|>\\n</s>\\n<|user|>\\n{completion}</s>\\n<|assistant|>\\n\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d3e21cef-b3c3-4ddd-a70c-728de440648e",
+   "metadata": {},
+   "source": [
+    "### Model Loading\n",
+    "\n",
+    "Models can be loaded by specifying the model parameters using the `OptimumIntelLLM` method."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a27feba3-d027-4d10-b1af-1e130e764a67",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "oi_llm = OptimumIntelLLM(\n",
+    "    model_name=\"Intel/neural-chat-7b-v3-3\",\n",
+    "    tokenizer_name=\"Intel/neural-chat-7b-v3-3\",\n",
+    "    context_window=3900,\n",
+    "    max_new_tokens=256,\n",
+    "    generate_kwargs={\"temperature\": 0.7, \"top_k\": 50, \"top_p\": 0.95},\n",
+    "    messages_to_prompt=messages_to_prompt,\n",
+    "    completion_to_prompt=completion_to_prompt,\n",
+    "    device_map=\"cpu\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e25c7162",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = oi_llm.complete(\"What is the meaning of life?\")\n",
+    "print(str(response))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dda1be10",
+   "metadata": {},
+   "source": [
+    "### Streaming\n",
+    "\n",
+    "Using `stream_complete` endpoint "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "12e0f3c0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response = oi_llm.stream_complete(\"Who is Mother Teresa?\")\n",
+    "for r in response:\n",
+    "    print(r.delta, end=\"\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2c87c383",
+   "metadata": {},
+   "source": [
+    "Using `stream_chat` endpoint"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2db801a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.llms import ChatMessage\n",
+    "\n",
+    "messages = [\n",
+    "    ChatMessage(\n",
+    "        role=\"system\",\n",
+    "        content=\"You are an American chef in a small restaurant in New Orleans\",\n",
+    "    ),\n",
+    "    ChatMessage(role=\"user\", content=\"What is your dish of the day?\"),\n",
+    "]\n",
+    "resp = oi_llm.stream_chat(messages)\n",
+    "\n",
+    "for r in resp:\n",
+    "    print(r.delta, end=\"\")"
+   ]
+  }
+ ],
+ "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": 5
+}
diff --git a/llama-index-integrations/llms/llama-index-llms-optimum-intel/.gitignore b/llama-index-integrations/llms/llama-index-llms-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
diff --git a/llama-index-integrations/llms/llama-index-llms-optimum-intel/BUILD b/llama-index-integrations/llms/llama-index-llms-optimum-intel/BUILD
@@ -0,0 +1,3 @@
+poetry_requirements(
+    name="poetry",
+)
diff --git a/llama-index-integrations/llms/llama-index-llms-optimum-intel/Makefile b/llama-index-integrations/llms/llama-index-llms-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/