Add llm integration with Intel Gaudi in llama-index-llms-gaudi (#16308)

llama-index-integrations/llms/llama-index-llms-gaudi/.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/llms/llama-index-llms-gaudi/BUILD

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

llama-index-integrations/llms/llama-index-llms-gaudi/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/llms/llama-index-llms-gaudi/README.md

@@ -0,0 +1,55 @@
+# LlamaIndex Llms Integration with Intel Gaudi
+
+## Installation
+
+```bash
+pip install --upgrade-strategy eager optimum[habana]
+pip install llama-index-llms-gaudi
+pip install llama-index-llms-huggingface
+```
+
+## Usage
+
+```python
+import argparse
+import os, logging
+from llama_index.llms.gaudi import GaudiLLM
+
+
+def setup_parser(parser):
+    parser.add_argument(...)
+    args = parser.parse_args()
+    return args
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="GaudiLLM Basic Usage Example"
+    )
+    args = setup_parser(parser)
+    args.model_name_or_path = "HuggingFaceH4/zephyr-7b-alpha"
+
+    llm = GaudiLLM(
+        args=args,
+        logger=logger,
+        model_name="HuggingFaceH4/zephyr-7b-alpha",
+        tokenizer_name="HuggingFaceH4/zephyr-7b-alpha",
+        query_wrapper_prompt=PromptTemplate(
+            "<|system|>\n</s>\n<|user|>\n{query_str}</s>\n<|assistant|>\n"
+        ),
+        context_window=3900,
+        max_new_tokens=256,
+        generate_kwargs={"temperature": 0.7, "top_k": 50, "top_p": 0.95},
+        messages_to_prompt=messages_to_prompt,
+        device_map="auto",
+    )
+
+    query = "Is the ocean blue?"
+    print("\n----------------- Complete ------------------")
+    completion_response = llm.complete(query)
+    print(completion_response.text)
+```
+
+## Examples
+
+- [More Examples](https://github.com/run-llama/llama_index/tree/main/llama-index-integrations/llms/llama-index-llms-gaudi/examples)

llama-index-integrations/llms/llama-index-llms-gaudi/examples/BUILD

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

llama-index-integrations/llms/llama-index-llms-gaudi/examples/README.md

@@ -0,0 +1,29 @@
+# GaudiLLM Examples
+
+This folder contains examples showcasing how to use LlamaIndex with `gaudi` LLM integration `llama_index.llms.gaudi.GaudiLLM`.
+
+## Installation
+
+### On Intel Gaudi
+
+Install `llama-index-llms-gaudi`. This will also install `gaudi` and its dependencies.
+
+```bash
+pip install --upgrade-strategy eager optimum[habana]
+```
+
+## List of Examples
+
+### Basic Example
+
+The example [basic.py](./basic.py) shows how to run `GaudiLLM` on Intel Gaudi and conduct tasks such as text completion. Run the example as following:
+
+```bash
+python basic.py
+```
+
+> Please note that in this example we'll use [HuggingFaceH4/zephyr-7b-alpha](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha) model for demonstration. It requires `transformers` and `tokenizers` packages.
+>
+> ```bash
+> pip install -U transformers tokenizers
+> ```