{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Google Vertex AI PaLM \n",
    "\n",
    "**Note:** This is separate from the `Google PaLM` integration, it exposes [Vertex AI PaLM API](https://cloud.google.com/vertex-ai/docs/generative-ai/learn/overview) on `Google Cloud`. \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setting up"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "By default, Google Cloud [does not use](https://cloud.google.com/vertex-ai/docs/generative-ai/data-governance#foundation_model_development) customer data to train its foundation models as part of Google Cloud's AI/ML Privacy Commitment. More details about how Google processes data can also be found in [Google's Customer Data Processing Addendum (CDPA)](https://cloud.google.com/terms/data-processing-addendum).\n",
    "\n",
    "To use `Vertex AI PaLM` you must have the `google-cloud-aiplatform` Python package installed and either:\n",
    "- Have credentials configured for your environment (gcloud, workload identity, etc...)\n",
    "- Store the path to a service account JSON file as the GOOGLE_APPLICATION_CREDENTIALS environment variable\n",
    "\n",
    "This codebase uses the `google.auth` library which first looks for the application credentials variable mentioned above, and then looks for system-level auth.\n",
    "\n",
    "For more information, see: \n",
    "- https://cloud.google.com/docs/authentication/application-default-credentials#GAC\n",
    "- https://googleapis.dev/python/google-auth/latest/reference/google.auth.html#module-google.auth"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "#!pip install google-cloud-aiplatform"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.llms import VertexAI"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Question-answering example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain import PromptTemplate, LLMChain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "template = \"\"\"Question: {question}\n",
    "\n",
    "Answer: Let's think step by step.\"\"\"\n",
    "\n",
    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = VertexAI()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Justin Bieber was born on March 1, 1994. The Super Bowl in 1994 was won by the San Francisco 49ers.\\nThe final answer: San Francisco 49ers.'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
    "\n",
    "llm_chain.run(question)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Code generation example"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can now leverage the `Codey API` for code generation within `Vertex AI`. \n",
    "\n",
    "The model names are:\n",
    "- `code-bison`: for code suggestion\n",
    "- `code-gecko`: for code completion"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-17T21:16:53.149438Z",
     "iopub.status.busy": "2023-06-17T21:16:53.149065Z",
     "iopub.status.idle": "2023-06-17T21:16:53.421824Z",
     "shell.execute_reply": "2023-06-17T21:16:53.421136Z",
     "shell.execute_reply.started": "2023-06-17T21:16:53.149415Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "llm = VertexAI(model_name=\"code-bison\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-17T21:17:11.179077Z",
     "iopub.status.busy": "2023-06-17T21:17:11.178686Z",
     "iopub.status.idle": "2023-06-17T21:17:11.182499Z",
     "shell.execute_reply": "2023-06-17T21:17:11.181895Z",
     "shell.execute_reply.started": "2023-06-17T21:17:11.179052Z"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-06-17T21:18:47.024785Z",
     "iopub.status.busy": "2023-06-17T21:18:47.024230Z",
     "iopub.status.idle": "2023-06-17T21:18:49.352249Z",
     "shell.execute_reply": "2023-06-17T21:18:49.351695Z",
     "shell.execute_reply.started": "2023-06-17T21:18:47.024762Z"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'```python\\ndef is_prime(n):\\n  \"\"\"\\n  Determines if a number is prime.\\n\\n  Args:\\n    n: The number to be tested.\\n\\n  Returns:\\n    True if the number is prime, False otherwise.\\n  \"\"\"\\n\\n  # Check if the number is 1.\\n  if n == 1:\\n    return False\\n\\n  # Check if the number is 2.\\n  if n == 2:\\n    return True\\n\\n'"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "question = \"Write a python function that identifies if the number is a prime number?\"\n",
    "\n",
    "llm_chain.run(question)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Using models deployed on Vertex Model Garden"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Vertex Model Garden [exposes](https://cloud.google.com/vertex-ai/docs/start/explore-models) open-sourced models that can be deployed and served on Vertex AI. If you have successfully deployed a model from Vertex Model Garden, you can find a corresponding Vertex AI [endpoint](https://cloud.google.com/vertex-ai/docs/general/deployment#what_happens_when_you_deploy_a_model) in the console or via API."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.llms import VertexAIModelGarden"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = VertexAIModelGarden(\n",
    "    project=\"YOUR PROJECT\",\n",
    "    endpoint_id=\"YOUR ENDPOINT_ID\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm(\"What is the meaning of life?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Like all LLMs, we can then compose it with other components:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.prompts import PromptTemplate\n",
    "\n",
    "prompt = PromptTemplate.from_template(\"What is the meaning of {thing}?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm_oss_chain = prompt | llm\n",
    "\n",
    "llm_oss_chain.invoke({\"thing\": \"life\"})"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "poetry-venv",
   "language": "python",
   "name": "poetry-venv"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.1"
  },
  "vscode": {
   "interpreter": {
    "hash": "cc99336516f23363341912c6723b01ace86f02e26b4290be1efc0677e2e2ec24"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}