Add support for LiteLLM Proxy Server (#14523)

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

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

llama-index-integrations/embeddings/llama-index-embeddings-litellm/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-litellm/README.md

@@ -0,0 +1 @@
+# LlamaIndex Embeddings Integration: LiteLLM

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

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

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

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

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

@@ -0,0 +1,69 @@
+from typing import List
+from litellm import embedding
+
+from llama_index.core.bridge.pydantic import Field
+from llama_index.core.embeddings import BaseEmbedding
+
+
+def get_embeddings(api_key: str, api_base: str, model_name: str, input: List[str]):
+    if not api_key:
+        # If key is not provided, we assume the consumer has configured
+        # their LiteLLM proxy server with their API key.
+        api_key = "some key"
+
+    response = embedding(
+        api_key=api_key,
+        api_base=api_base,
+        model=model_name,
+        input=input,
+    )
+    return [result["embedding"] for result in response.data]
+
+
+class LiteLLMEmbedding(BaseEmbedding):
+    model_name: str = Field(
+        default="unknown", description="The name of the embedding model."
+    )
+    api_key: str = Field(
+        default="unknown",
+        description="OpenAI key. If not provided, the proxy server must be configured with the key.",
+    )
+    api_base: str = Field(
+        default="unknown", description="The base URL of the LiteLLM proxy."
+    )
+
+    @classmethod
+    def class_name(cls) -> str:
+        return "lite-llm"
+
+    async def _aget_query_embedding(self, query: str) -> List[float]:
+        return self._get_query_embedding(query)
+
+    async def _aget_text_embedding(self, text: str) -> List[float]:
+        return self._get_text_embedding(text)
+
+    def _get_query_embedding(self, query: str) -> List[float]:
+        embeddings = get_embeddings(
+            api_key=self.api_key,
+            api_base=self.api_base,
+            model_name=self.model_name,
+            input=[query],
+        )
+        return embeddings[0]
+
+    def _get_text_embedding(self, text: str) -> List[float]:
+        embeddings = get_embeddings(
+            api_key=self.api_key,
+            api_base=self.api_base,
+            model_name=self.model_name,
+            input=[text],
+        )
+        return embeddings[0]
+
+    def _get_text_embeddings(self, texts: List[str]) -> List[List[float]]:
+        return get_embeddings(
+            api_key=self.api_key,
+            api_base=self.api_base,
+            model_name=self.model_name,
+            input=texts,
+        )