Add nemo retriever embeddings integration

docs/examples/embeddings/nemo.ipynb

@@ -0,0 +1,91 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Nvidia NeMo embeddings"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Connect to NVIDIA's embedding service using the NeMoEmbeddings class."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install llama-index-embeddings-nemo"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install llama-index"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# imports\n",
+    "from llama_index.embeddings.nemo import NeMoEmbedding"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "batch_size = 16\n",
+    "model = \"NV-Embed-QA-003\"\n",
+    "api_endpoint_url = \"http://localhost:8080/v1/embeddings\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embedding_model = NeMoEmbedding(\n",
+    "    batch_size=batch_size, model=model, api_endpoint_url=api_endpoint_url\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embedding_model.embed_query(\"Hello world\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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

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

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

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

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

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

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

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

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

@@ -0,0 +1,83 @@
+"""NeMo embeddings file."""
+
+import json
+import requests
+import aiohttp
+from typing import Any, List, Optional
+
+from llama_index.core.base.embeddings.base import (
+    DEFAULT_EMBED_BATCH_SIZE,
+    BaseEmbedding,
+)
+from llama_index.core.callbacks.base import CallbackManager
+
+
+class NeMoEmbedding(BaseEmbedding):
+    """Nvidia NeMo embeddings."""
+
+    def __init__(
+        self,
+        model_name: str = "NV-Embed-QA-003",
+        api_endpoint_url: str = "http://localhost:8088/v1/embeddings",
+        embed_batch_size: int = DEFAULT_EMBED_BATCH_SIZE,
+        callback_manager: Optional[CallbackManager] = None,
+        **kwargs: Any,
+    ):
+        self.api_endpoint_url = api_endpoint_url
+
+        super().__init__(
+            model_name=model_name,
+            embed_batch_size=embed_batch_size,
+            callback_manager=callback_manager,
+            **kwargs,
+        )
+
+    @classmethod
+    def class_name(cls) -> str:
+        return "NeMoEmbedding"
+
+    def _get_embedding(self, text: str, input_type: str) -> List[float]:
+        payload = json.dumps(
+            {"input": text, "model": self.model_name, "input_type": input_type}
+        )
+        headers = {"Content-Type": "application/json"}
+
+        response = requests.request(
+            "POST", self.api_endpoint_url, headers=headers, data=payload
+        )
+        response = json.loads(response.text)
+
+        return response["data"][0]["embedding"]
+
+    async def _aget_embedding(self, session: Any, text: str, input_type: str) -> List[float]:
+
+        headers = {"Content-Type": "application/json"}
+
+        async with session.post(
+            self.api_endpoint_url,
+            json={"input": text, "model": self.model, "input_type": input_type},
+            headers=headers,
+        ) as response:
+            response.raise_for_status()
+            answer = await response.text()
+            answer = json.loads(answer)
+            return answer["data"][0]["embedding"]
+
+    def _get_query_embedding(self, query: str) -> List[float]:
+        return self._get_embedding(query, input_type="query")
+
+    def _get_text_embedding(self, text: str) -> List[float]:
+        return self._get_embedding(text, input_type="passage")
+
+    def _get_text_embeddings(self, texts: List[str]) -> List[List[float]]:
+        return [self._get_embedding(text, input_type="passage") for text in texts]
+
+    def _aget_query_embedding(self, query: str) -> List[float]:
+        async with aiohttp.ClientSession() as session:
+            embedding = await self._aget_embedding(session, query, "query")
+            return embedding
+
+    def _aget_text_embedding(self, text: str) -> List[float]:
+        async with aiohttp.ClientSession() as session:
+            embedding = await self._aget_embedding(session, text, "passage")
+            return embedding