[WIP] Add support for OPEA LLMs in Llama-Index (#16666)

Author: logan-markewich

llama-index-integrations/embeddings/llama-index-embeddings-opea/.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-opea/BUILD

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

llama-index-integrations/embeddings/llama-index-embeddings-opea/Makefile

@@ -0,0 +1,16 @@
+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).
+	git ls-files | black
+
+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-opea/README.md

@@ -0,0 +1,29 @@
+# LlamaIndex Embeddings Integration: OPEA Embeddings
+
+OPEA (Open Platform for Enterprise AI) is a platform for building, deploying, and scaling AI applications. As part of this platform, many core gen-ai components are available for deployment as microservices, including LLMs.
+
+Visit [https://opea.dev](https://opea.dev) for more information, and their [GitHub](https://github.com/opea-project/GenAIComps) for the source code of the OPEA components.
+
+## Installation
+
+1. Install the required Python packages:
+
+```bash
+%pip install llama-index-embeddings-opea
+```
+
+## Usage
+
+```python
+from llama_index.embeddings.opea import OPEAEmbedding
+
+embed_model = OPEAEmbedding(
+    model="<model_name>",
+    api_base="http://localhost:8080/v1",
+    embed_batch_size=10,
+)
+
+embeddings = embed_model.get_text_embedding("text")
+
+embeddings = embed_model.get_text_embedding_batch(["text1", "text2"])
+```

llama-index-integrations/embeddings/llama-index-embeddings-opea/llama_index/embeddings/opea/BUILD

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

llama-index-integrations/embeddings/llama-index-embeddings-opea/llama_index/embeddings/opea/__init__.py

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

llama-index-integrations/embeddings/llama-index-embeddings-opea/llama_index/embeddings/opea/base.py

@@ -0,0 +1,67 @@
+import httpx
+from typing import Any, Dict, Optional
+
+from llama_index.core.base.embeddings.base import (
+    DEFAULT_EMBED_BATCH_SIZE,
+)
+from llama_index.core.callbacks import CallbackManager
+from llama_index.embeddings.openai import OpenAIEmbedding
+
+
+class OPEAEmbedding(OpenAIEmbedding):
+    """
+    OPEA class for embeddings.
+
+    Args:
+        model (str): Model for embedding.
+        api_base (str): The base URL for OPEA Embeddings microservice.
+        additional_kwargs (Dict[str, Any]): Additional kwargs for the OpenAI API.
+
+    Examples:
+        `pip install llama-index-embeddings-opea`
+
+        ```python
+        from llama_index.embeddings.opea import OPEAEmbedding
+
+        embed_model = OPEAEmbedding(
+            model_name="...",
+            api_base="http://localhost:8080",
+        )
+        ```
+    """
+
+    def __init__(
+        self,
+        model_name: str,
+        api_base: str,
+        dimensions: Optional[int] = None,
+        embed_batch_size: int = DEFAULT_EMBED_BATCH_SIZE,
+        additional_kwargs: Optional[Dict[str, Any]] = None,
+        max_retries: int = 10,
+        timeout: float = 60.0,
+        reuse_client: bool = True,
+        callback_manager: Optional[CallbackManager] = None,
+        default_headers: Optional[Dict[str, str]] = None,
+        http_client: Optional[httpx.Client] = None,
+        api_key: Optional[str] = "fake",
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            model_name=model_name,
+            dimensions=dimensions,
+            embed_batch_size=embed_batch_size,
+            additional_kwargs=additional_kwargs,
+            api_key=api_key,
+            api_base=api_base,
+            max_retries=max_retries,
+            timeout=timeout,
+            reuse_client=reuse_client,
+            callback_manager=callback_manager,
+            default_headers=default_headers,
+            http_client=http_client,
+            **kwargs,
+        )
+
+    @classmethod
+    def class_name(cls) -> str:
+        return "OPEAEmbedding"

llama-index-integrations/embeddings/llama-index-embeddings-opea/pyproject.toml

@@ -0,0 +1,63 @@
+[build-system]
+build-backend = "poetry.core.masonry.api"
+requires = ["poetry-core"]
+
+[tool.codespell]
+check-filenames = true
+check-hidden = true
+skip = "*.csv,*.html,*.json,*.jsonl,*.pdf,*.txt,*.ipynb"
+
+[tool.llamahub]
+contains_example = false
+import_path = "llama_index.embeddings.opea"
+
+[tool.llamahub.class_authors]
+OPEAEmbedding = "llama-index"
+
+[tool.mypy]
+disallow_untyped_defs = true
+exclude = ["_static", "build", "examples", "notebooks", "venv"]
+ignore_missing_imports = true
+python_version = "3.8"
+
+[tool.poetry]
+authors = ["logan-markewich"]
+description = "llama-index embeddings opea integration"
+exclude = ["**/BUILD"]
+license = "MIT"
+name = "llama-index-embeddings-opea"
+readme = "README.md"
+version = "0.1.0"
+
+[tool.poetry.dependencies]
+python = ">=3.8.1,<4.0"
+llama-index-llms-openai = "^0.2.0"
+llama-index-core = "^0.11.0"
+
+[tool.poetry.group.dev.dependencies]
+ipython = "8.10.0"
+jupyter = "^1.0.0"
+mypy = "0.991"
+pre-commit = "3.2.0"
+pylint = "2.15.10"
+pytest = "7.2.1"
+pytest-mock = "3.11.1"
+ruff = "0.0.292"
+tree-sitter-languages = "^1.8.0"
+types-Deprecated = ">=0.1.0"
+types-PyYAML = "^6.0.12.12"
+types-protobuf = "^4.24.0.4"
+types-redis = "4.5.5.0"
+types-requests = "2.28.11.8"
+types-setuptools = "67.1.0.0"
+
+[tool.poetry.group.dev.dependencies.black]
+extras = ["jupyter"]
+version = "<=23.9.1,>=23.7.0"
+
+[tool.poetry.group.dev.dependencies.codespell]
+extras = ["toml"]
+version = ">=v2.2.6"
+
+[[tool.poetry.packages]]
+include = "llama_index/"