Google genai embeddings (#18079)

e861ccbe · Logan · GitHub · ddcf5a39 · e861ccbe · e861ccbe
Unverified Commit e861ccbe authored 6 days ago by Logan Committed by GitHub 6 days ago
--- a/docs/docs/examples/embeddings/gemini.ipynb
+++ b/docs/docs/examples/embeddings/gemini.ipynb
@@ -11,7 +11,9 @@
   "cell_type": "markdown",
   "metadata": {},
   "source": [
-    "# Google Gemini Embeddings"
+    "# Google Gemini Embeddings\n",
+    "\n",
+    "**NOTE:** This example is deprecated. Please use the `GoogleGenAIEmbedding` class instead, detailed [here](https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/embeddings/google_genai.ipynb)."
   ]
  },
  {

 %% Cell type:markdown id: tags:
 <a href="https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/docs/examples/embeddings/gemini.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
 %% Cell type:markdown id: tags:
 # Google Gemini Embeddings
+**NOTE:** This example is deprecated. Please use the `GoogleGenAIEmbedding` class instead, detailed [here](https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/embeddings/google_genai.ipynb).
 %% Cell type:markdown id: tags:
 If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙.
 %% Cell type:code id: tags:
 ``` python
 %pip install llama-index-embeddings-gemini
 ```
 %% Cell type:code id: tags:
 ``` python
 !pip install llama-index 'google-generativeai>=0.3.0' matplotlib
 ```
 %% Cell type:code id: tags:
 ``` python
 import os
 GOOGLE_API_KEY = ""  # add your GOOGLE API key here
 os.environ["GOOGLE_API_KEY"] = GOOGLE_API_KEY
 ```
 %% Cell type:code id: tags:
 ``` python
 # imports
 from llama_index.embeddings.gemini import GeminiEmbedding
 ```
 %% Cell type:code id: tags:
 ``` python
 # get API key and create embeddings
 model_name = "models/embedding-001"
 embed_model = GeminiEmbedding(
    model_name=model_name, api_key=GOOGLE_API_KEY, title="this is a document"
 )
 embeddings = embed_model.get_text_embedding("Google Gemini Embeddings.")
 ```
 %% Output
    /Users/haotianzhang/llama_index/venv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
      from .autonotebook import tqdm as notebook_tqdm
 %% Cell type:code id: tags:
 ``` python
 print(f"Dimension of embeddings: {len(embeddings)}")
 ```
 %% Output
    Dimension of embeddings: 768
 %% Cell type:code id: tags:
 ``` python
 embeddings[:5]
 ```
 %% Output
    [0.028174246, -0.0290093, -0.013280814, 0.008629, 0.025442218]
 %% Cell type:code id: tags:
 ``` python
 embeddings = embed_model.get_query_embedding("Google Gemini Embeddings.")
 embeddings[:5]
 ```
 %% Output
    [0.028174246, -0.0290093, -0.013280814, 0.008629, 0.025442218]
 %% Cell type:code id: tags:
 ``` python
 embeddings = embed_model.get_text_embedding(
    ["Google Gemini Embeddings.", "Google is awesome."]
 )
 ```
 %% Cell type:code id: tags:
 ``` python
 print(f"Dimension of embeddings: {len(embeddings)}")
 print(embeddings[0][:5])
 print(embeddings[1][:5])
 ```
 %% Output
    Dimension of embeddings: 2
    [0.028174246, -0.0290093, -0.013280814, 0.008629, 0.025442218]
    [0.009427786, -0.009968997, -0.03341217, -0.025396815, 0.03210592]
 %% Cell type:code id: tags:
 ``` python
 embedding = await embed_model.aget_text_embedding("Google Gemini Embeddings.")
 print(embedding[:5])
 ```
 %% Output
    [0.028174246, -0.0290093, -0.013280814, 0.008629, 0.025442218]
 %% Cell type:code id: tags:
 ``` python
 embeddings = await embed_model.aget_text_embedding_batch(
    [
        "Google Gemini Embeddings.",
        "Google is awesome.",
        "Llamaindex is awesome.",
    ]
 )
 print(embeddings[0][:5])
 print(embeddings[1][:5])
 print(embeddings[2][:5])
 ```
 %% Output
    [0.028174246, -0.0290093, -0.013280814, 0.008629, 0.025442218]
    [0.009427786, -0.009968997, -0.03341217, -0.025396815, 0.03210592]
    [0.013159992, -0.021570021, -0.060150445, -0.042500723, 0.041159637]
 %% Cell type:code id: tags:
 ``` python
 embedding = await embed_model.aget_query_embedding("Google Gemini Embeddings.")
 print(embedding[:5])
 ```
 %% Output
    [0.028174246, -0.0290093, -0.013280814, 0.008629, 0.025442218]

--- a/docs/docs/examples/embeddings/google_genai.ipynb
+++ b/docs/docs/examples/embeddings/google_genai.ipynb
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<a href=\"https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/docs/examples/embeddings/gemini.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Google GenAI Embeddings\n",
+    "\n",
+    "Using Google's `google-genai` package, LlamaIndex provides a `GoogleGenAIEmbedding` class that allows you to embed text using Google's GenAI models from both the Gemini and Vertex AI APIs."
+   ]
+  },
+  {
+   "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-google-genai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"GOOGLE_API_KEY\"] = \"...\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "`GoogleGenAIEmbedding` is a wrapper around the `google-genai` package, which means it supports both Gemini and Vertex AI APIs out of that box.\n",
+    "\n",
+    "You can pass in the `api_key` directly, or pass in a `vertexai_config` to use the Vertex AI API.\n",
+    "\n",
+    "Other options include `embed_batch_size`, `model_name`, and `embedding_config`.\n",
+    "\n",
+    "The default model is `text-embedding-004`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.embeddings.google_genai import GoogleGenAIEmbedding\n",
+    "from google.genai.types import EmbedContentConfig\n",
+    "\n",
+    "embed_model = GoogleGenAIEmbedding(\n",
+    "    model_name=\"text-embedding-004\",\n",
+    "    embed_batch_size=100,\n",
+    "    # can pass in the api key directly\n",
+    "    # api_key=\"...\",\n",
+    "    # or pass in a vertexai_config\n",
+    "    # vertexai_config={\n",
+    "    #     \"project\": \"...\",\n",
+    "    #     \"location\": \"...\",\n",
+    "    # }\n",
+    "    # can also pass in an embedding_config\n",
+    "    # embedding_config=EmbedContentConfig(...)\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Usage"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Sync"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[0.031099992, 0.02192731, -0.06523498, 0.016788177, 0.0392835]\n",
+      "Dimension of embeddings: 768\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = embed_model.get_text_embedding(\"Google Gemini Embeddings.\")\n",
+    "print(embeddings[:5])\n",
+    "print(f\"Dimension of embeddings: {len(embeddings)}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[0.022199392, 0.03671178, -0.06874573, 0.02195774, 0.05475164]\n",
+      "Dimension of embeddings: 768\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = embed_model.get_query_embedding(\"Query Google Gemini Embeddings.\")\n",
+    "print(embeddings[:5])\n",
+    "print(f\"Dimension of embeddings: {len(embeddings)}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Got 3 embeddings\n",
+      "Dimension of embeddings: 768\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = embed_model.get_text_embedding_batch(\n",
+    "    [\n",
+    "        \"Google Gemini Embeddings.\",\n",
+    "        \"Google is awesome.\",\n",
+    "        \"Llamaindex is awesome.\",\n",
+    "    ]\n",
+    ")\n",
+    "print(f\"Got {len(embeddings)} embeddings\")\n",
+    "print(f\"Dimension of embeddings: {len(embeddings[0])}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Async"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[0.031099992, 0.02192731, -0.06523498, 0.016788177, 0.0392835]\n",
+      "Dimension of embeddings: 768\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = await embed_model.aget_text_embedding(\"Google Gemini Embeddings.\")\n",
+    "print(embeddings[:5])\n",
+    "print(f\"Dimension of embeddings: {len(embeddings)}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[0.022199392, 0.03671178, -0.06874573, 0.02195774, 0.05475164]\n",
+      "Dimension of embeddings: 768\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = await embed_model.aget_query_embedding(\n",
+    "    \"Query Google Gemini Embeddings.\"\n",
+    ")\n",
+    "print(embeddings[:5])\n",
+    "print(f\"Dimension of embeddings: {len(embeddings)}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Got 3 embeddings\n",
+      "Dimension of embeddings: 768\n"
+     ]
+    }
+   ],
+   "source": [
+    "embeddings = await embed_model.aget_text_embedding_batch(\n",
+    "    [\n",
+    "        \"Google Gemini Embeddings.\",\n",
+    "        \"Google is awesome.\",\n",
+    "        \"Llamaindex is awesome.\",\n",
+    "    ]\n",
+    ")\n",
+    "print(f\"Got {len(embeddings)} embeddings\")\n",
+    "print(f\"Dimension of embeddings: {len(embeddings[0])}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "b0fa6594d8f4cbf19f97940f81e996739fb7646882a419484c72d19e05852a7e"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
+%% Cell type:markdown id: tags:
+<a href="https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/docs/examples/embeddings/gemini.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
+%% Cell type:markdown id: tags:
+# Google GenAI Embeddings
+Using Google's `google-genai` package, LlamaIndex provides a `GoogleGenAIEmbedding` class that allows you to embed text using Google's GenAI models from both the Gemini and Vertex AI APIs.
+%% Cell type:markdown id: tags:
+If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙.
+%% Cell type:code id: tags:
+``` python
+%pip install llama-index-embeddings-google-genai
+```
+%% Cell type:code id: tags:
+``` python
+import os
+os.environ["GOOGLE_API_KEY"] = "..."
+```
+%% Cell type:markdown id: tags:
+## Setup
+`GoogleGenAIEmbedding` is a wrapper around the `google-genai` package, which means it supports both Gemini and Vertex AI APIs out of that box.
+You can pass in the `api_key` directly, or pass in a `vertexai_config` to use the Vertex AI API.
+Other options include `embed_batch_size`, `model_name`, and `embedding_config`.
+The default model is `text-embedding-004`.
+%% Cell type:code id: tags:
+``` python
+from llama_index.embeddings.google_genai import GoogleGenAIEmbedding
+from google.genai.types import EmbedContentConfig
+embed_model = GoogleGenAIEmbedding(
+    model_name="text-embedding-004",
+    embed_batch_size=100,
+    # can pass in the api key directly
+    # api_key="...",
+    # or pass in a vertexai_config
+    # vertexai_config={
+    #     "project": "...",
+    #     "location": "...",
+    # }
+    # can also pass in an embedding_config
+    # embedding_config=EmbedContentConfig(...)
+)
+```
+%% Cell type:markdown id: tags:
+## Usage
+%% Cell type:markdown id: tags:
+### Sync
+%% Cell type:code id: tags:
+``` python
+embeddings = embed_model.get_text_embedding("Google Gemini Embeddings.")
+print(embeddings[:5])
+print(f"Dimension of embeddings: {len(embeddings)}")
+```
+%% Output
+    [0.031099992, 0.02192731, -0.06523498, 0.016788177, 0.0392835]
+    Dimension of embeddings: 768
+%% Cell type:code id: tags:
+``` python
+embeddings = embed_model.get_query_embedding("Query Google Gemini Embeddings.")
+print(embeddings[:5])
+print(f"Dimension of embeddings: {len(embeddings)}")
+```
+%% Output
+    [0.022199392, 0.03671178, -0.06874573, 0.02195774, 0.05475164]
+    Dimension of embeddings: 768
+%% Cell type:code id: tags:
+``` python
+embeddings = embed_model.get_text_embedding_batch(
+    [
+        "Google Gemini Embeddings.",
+        "Google is awesome.",
+        "Llamaindex is awesome.",
+    ]
+)
+print(f"Got {len(embeddings)} embeddings")
+print(f"Dimension of embeddings: {len(embeddings[0])}")
+```
+%% Output
+    Got 3 embeddings
+    Dimension of embeddings: 768
+%% Cell type:markdown id: tags:
+### Async
+%% Cell type:code id: tags:
+``` python
+embeddings = await embed_model.aget_text_embedding("Google Gemini Embeddings.")
+print(embeddings[:5])
+print(f"Dimension of embeddings: {len(embeddings)}")
+```
+%% Output
+    [0.031099992, 0.02192731, -0.06523498, 0.016788177, 0.0392835]
+    Dimension of embeddings: 768
+%% Cell type:code id: tags:
+``` python
+embeddings = await embed_model.aget_query_embedding(
+    "Query Google Gemini Embeddings."
+)
+print(embeddings[:5])
+print(f"Dimension of embeddings: {len(embeddings)}")
+```
+%% Output
+    [0.022199392, 0.03671178, -0.06874573, 0.02195774, 0.05475164]
+    Dimension of embeddings: 768
+%% Cell type:code id: tags:
+``` python
+embeddings = await embed_model.aget_text_embedding_batch(
+    [
+        "Google Gemini Embeddings.",
+        "Google is awesome.",
+        "Llamaindex is awesome.",
+    ]
+)
+print(f"Got {len(embeddings)} embeddings")
+print(f"Dimension of embeddings: {len(embeddings[0])}")
+```
+%% Output
+    Got 3 embeddings
+    Dimension of embeddings: 768
--- a/docs/docs/examples/embeddings/google_palm.ipynb
+++ b/docs/docs/examples/embeddings/google_palm.ipynb
@@ -11,7 +11,9 @@
   "cell_type": "markdown",
   "metadata": {},
   "source": [
-    "# Google PaLM Embeddings"
+    "# Google PaLM Embeddings\n",
+    "\n",
+    "**NOTE:** This example is deprecated. Please use the `GoogleGenAIEmbedding` class instead, detailed [here](https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/embeddings/google_genai.ipynb)."
   ]
  },
  {

 %% Cell type:markdown id: tags:
 <a href="https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/docs/examples/embeddings/google_palm.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
 %% Cell type:markdown id: tags:
 # Google PaLM Embeddings
+**NOTE:** This example is deprecated. Please use the `GoogleGenAIEmbedding` class instead, detailed [here](https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/embeddings/google_genai.ipynb).
 %% Cell type:markdown id: tags:
 If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙.
 %% Cell type:code id: tags:
 ``` python
 %pip install llama-index-embeddings-google
 ```
 %% Cell type:code id: tags:
 ``` python
 !pip install llama-index
 ```
 %% Cell type:code id: tags:
 ``` python
 # imports
 from llama_index.embeddings.google import GooglePaLMEmbedding
 ```
 %% Cell type:code id: tags:
 ``` python
 # get API key and create embeddings
 model_name = "models/embedding-gecko-001"
 api_key = "YOUR API KEY"
 embed_model = GooglePaLMEmbedding(model_name=model_name, api_key=api_key)
 embeddings = embed_model.get_text_embedding("Google PaLM Embeddings.")
 ```
 %% Output
    /opt/homebrew/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
      from .autonotebook import tqdm as notebook_tqdm
 %% Cell type:code id: tags:
 ``` python
 print(f"Dimension of embeddings: {len(embeddings)}")
 ```
 %% Output
    Dimension of embeddings: 768
 %% Cell type:code id: tags:
 ``` python
 embeddings[:5]
 ```
 %% Output
    [0.028517298, -0.0028859433, -0.035110522, 0.021982985, -0.0039763353]

--- a/llama-index-integrations/embeddings/llama-index-embeddings-gemini/README.md
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-gemini/README.md
 # LlamaIndex Embeddings Integration: Gemini
+**NOTE:** This package is deprecated. Please use the `GoogleGenAIEmbedding` class instead, detailed [here](https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/embeddings/google_genai.ipynb).
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/.gitignore
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/.gitignore
+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
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/BUILD
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/BUILD
+poetry_requirements(
+    name="poetry",
+)
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/LICENSE
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/LICENSE
+The MIT License
+Copyright (c) Jerry Liu
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/Makefile
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/Makefile
+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/
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/README.md
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/README.md
+# Google GenAI Embeddings
+This package provides a wrapper around the Google GenAI API, allowing you to use Gemini and Vertex AI embeddings in your projects.
+## Installation
+```bash
+pip install llama-index-embeddings-google-genai
+```
+## Usage
+```python
+from llama_index.embeddings.google_genai import GoogleGenAIEmbedding
+embed_model = GoogleGenAIEmbedding(model_name="text-embedding-004")
+embeddings = embed_model.get_text_embedding("Hello, world!")
+print(embeddings)
+```
+## Vertex AI
+```python
+embed_model = GoogleGenAIEmbedding(
+    model_name="text-embedding-004",
+    vertexai_config={
+        "project": "your-project-id",
+        "location": "your-location",
+    },
+)
+```
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/llama_index/embeddings/google_genai/BUILD
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/llama_index/embeddings/google_genai/BUILD
+python_sources()
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/llama_index/embeddings/google_genai/__init__.py
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/llama_index/embeddings/google_genai/__init__.py
+from llama_index.embeddings.google_genai.base import GoogleGenAIEmbedding
+__all__ = ["GoogleGenAIEmbedding"]
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/llama_index/embeddings/google_genai/base.py
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/llama_index/embeddings/google_genai/base.py
+"""Gemini embeddings file."""
+import os
+from typing import Any, Dict, List, Optional, TypedDict
+from llama_index.core.base.embeddings.base import (
+    DEFAULT_EMBED_BATCH_SIZE,
+    BaseEmbedding,
+)
+from llama_index.core.bridge.pydantic import Field, PrivateAttr
+from llama_index.core.callbacks.base import CallbackManager
+import google.genai
+import google.auth.credentials
+import google.genai.types as types
+class VertexAIConfig(TypedDict):
+    credentials: Optional[google.auth.credentials.Credentials] = None
+    project: Optional[str] = None
+    location: Optional[str] = None
+class GoogleGenAIEmbedding(BaseEmbedding):
+    """Google GenAI embeddings.
+    Args:
+        model_name (str): Model for embedding.
+            Defaults to "text-embedding-005".
+        api_key (Optional[str]): API key to access the model. Defaults to None.
+        embedding_config (Optional[types.EmbedContentConfigOrDict]): Embedding config to access the model. Defaults to None.
+        vertexai_config (Optional[VertexAIConfig]): Vertex AI config to access the model. Defaults to None.
+        http_options (Optional[types.HttpOptions]): HTTP options to access the model. Defaults to None.
+        debug_config (Optional[google.genai.client.DebugConfig]): Debug config to access the model. Defaults to None.
+        embed_batch_size (int): Batch size for embedding. Defaults to 100.
+        callback_manager (Optional[CallbackManager]): Callback manager to access the model. Defaults to None.
+    Examples:
+        `pip install llama-index-embeddings-google-genai`
+        ```python
+        from llama_index.embeddings.google_genai import GoogleGenAIEmbedding
+        embed_model = GoogleGenAIEmbedding(model_name="text-embedding-005", api_key="...")
+        ```
+    """
+    _client: google.genai.Client = PrivateAttr()
+    _embedding_config: types.EmbedContentConfigOrDict = PrivateAttr()
+    embedding_config: Optional[types.EmbedContentConfigOrDict] = Field(
+        default=None, description="""Used to override embedding config."""
+    )
+    def __init__(
+        self,
+        model_name: str = "text-embedding-004",
+        api_key: Optional[str] = None,
+        embedding_config: Optional[types.EmbedContentConfigOrDict] = None,
+        vertexai_config: Optional[VertexAIConfig] = None,
+        http_options: Optional[types.HttpOptions] = None,
+        debug_config: Optional[google.genai.client.DebugConfig] = None,
+        embed_batch_size: int = DEFAULT_EMBED_BATCH_SIZE,
+        callback_manager: Optional[CallbackManager] = None,
+        **kwargs: Any,
+    ):
+        super().__init__(
+            model_name=model_name,
+            embedding_config=embedding_config,
+            embed_batch_size=embed_batch_size,
+            callback_manager=callback_manager,
+            **kwargs,
+        )
+        # API keys are optional. The API can be authorised via OAuth (detected
+        # environmentally) or by the GOOGLE_API_KEY environment variable.
+        api_key = api_key or os.getenv("GOOGLE_API_KEY", None)
+        vertexai = vertexai_config is not None or os.getenv(
+            "GOOGLE_GENAI_USE_VERTEXAI", False
+        )
+        project = (vertexai_config or {}).get("project") or os.getenv(
+            "GOOGLE_CLOUD_PROJECT", None
+        )
+        location = (vertexai_config or {}).get("location") or os.getenv(
+            "GOOGLE_CLOUD_LOCATION", None
+        )
+        config_params: Dict[str, Any] = {
+            "api_key": api_key,
+        }
+        if vertexai_config is not None:
+            config_params.update(vertexai_config)
+            config_params["api_key"] = None
+            config_params["vertexai"] = True
+        elif vertexai:
+            config_params["project"] = project
+            config_params["location"] = location
+            config_params["api_key"] = None
+            config_params["vertexai"] = True
+        if http_options:
+            config_params["http_options"] = http_options
+        if debug_config:
+            config_params["debug_config"] = debug_config
+        self._client = google.genai.Client(**config_params)
+    @classmethod
+    def class_name(cls) -> str:
+        return "GeminiEmbedding"
+    def _embed_texts(
+        self, texts: List[str], task_type: Optional[str] = None
+    ) -> List[List[float]]:
+        """Embed texts."""
+        # Set the task type if it is not already set
+        if task_type and not self.embedding_config:
+            self.embedding_config = types.EmbedContentConfig(task_type=task_type)
+        results = self._client.models.embed_content(
+            model=self.model_name,
+            contents=texts,
+            config=self.embedding_config,
+        )
+        return [result.values for result in results.embeddings]
+    async def _aembed_texts(
+        self, texts: List[str], task_type: Optional[str] = None
+    ) -> List[List[float]]:
+        """Asynchronously embed texts."""
+        # Set the task type if it is not already set
+        if task_type and not self.embedding_config:
+            self.embedding_config = types.EmbedContentConfig(task_type=task_type)
+        results = await self._client.aio.models.embed_content(
+            model=self.model_name,
+            contents=texts,
+            config=self.embedding_config,
+        )
+        return [result.values for result in results.embeddings]
+    def _get_query_embedding(self, query: str) -> List[float]:
+        """Get query embedding."""
+        return self._embed_texts([query], task_type="RETRIEVAL_QUERY")[0]
+    def _get_text_embedding(self, text: str) -> List[float]:
+        """Get text embedding."""
+        return self._embed_texts([text], task_type="RETRIEVAL_DOCUMENT")[0]
+    def _get_text_embeddings(self, texts: List[str]) -> List[List[float]]:
+        """Get text embeddings."""
+        return self._embed_texts(texts, task_type="RETRIEVAL_DOCUMENT")
+    async def _aget_query_embedding(self, query: str) -> List[float]:
+        """The asynchronous version of _get_query_embedding."""
+        return (await self._aembed_texts([query], task_type="RETRIEVAL_QUERY"))[0]
+    async def _aget_text_embedding(self, text: str) -> List[float]:
+        """Asynchronously get text embedding."""
+        return (await self._aembed_texts([text], task_type="RETRIEVAL_DOCUMENT"))[0]
+    async def _aget_text_embeddings(self, texts: List[str]) -> List[List[float]]:
+        """Asynchronously get text embeddings."""
+        return await self._aembed_texts(texts, task_type="RETRIEVAL_DOCUMENT")
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/pyproject.toml
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/pyproject.toml
+[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.google_genai"
+[tool.llamahub.class_authors]
+GoogleGenAIEmbedding = "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 = ["Your Name <you@example.com>"]
+description = "llama-index embeddings google genai integration"
+exclude = ["**/BUILD"]
+license = "MIT"
+name = "llama-index-embeddings-google-genai"
+readme = "README.md"
+version = "0.1.0"
+[tool.poetry.dependencies]
+python = ">=3.9,<4.0"
+google-genai = ">=1.4.0"
+llama-index-core = "^0.12.0"
+[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/"
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/tests/BUILD
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/tests/BUILD
+python_tests(
+    interpreter_constraints=[">=3.10"],
+    dependencies=[
+        "llama-index-integrations/embeddings/llama-index-embeddings-google-genai:poetry",
+    ],
+)
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/tests/__init__.py
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/tests/__init__.py
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/tests/test_embeddings_gemini.py
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google-genai/tests/test_embeddings_gemini.py
+from llama_index.core.base.embeddings.base import BaseEmbedding
+from llama_index.embeddings.google_genai import GoogleGenAIEmbedding
+def test_embedding_class():
+    emb = GoogleGenAIEmbedding(api_key="...")
+    assert isinstance(emb, BaseEmbedding)
--- a/llama-index-integrations/embeddings/llama-index-embeddings-google/README.md
+++ b/llama-index-integrations/embeddings/llama-index-embeddings-google/README.md
 # LlamaIndex Embeddings Integration: Google
+**NOTE:** This package is deprecated. Please use the `GoogleGenAIEmbedding` class instead, detailed [here](https://github.com/run-llama/llama_index/blob/main/docs/docs/examples/embeddings/google_genai.ipynb).