Merge pull request #477 from shekharchavan1990/oda_rag_poc

Oda rag poc

LLM/oda_examples/oda-oci-data-science-oracledb-23ai-llm/Load Documents.ipynb

@@ -0,0 +1,163 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "193f1d45-bb87-4602-9ebe-35c4e98f7f66",
+   "metadata": {},
+   "source": [
+    "### OCI Data Science - Useful Tips\n",
+    "<details>\n",
+    "<summary><font size=\"2\">Check for Public Internet Access</font></summary>\n",
+    "\n",
+    "```python\n",
+    "import requests\n",
+    "response = requests.get(\"https://oracle.com\")\n",
+    "assert response.status_code==200, \"Internet connection failed\"\n",
+    "```\n",
+    "</details>\n",
+    "<details>\n",
+    "<summary><font size=\"2\">Helpful Documentation </font></summary>\n",
+    "<ul><li><a href=\"https://docs.cloud.oracle.com/en-us/iaas/data-science/using/data-science.htm\">Data Science Service Documentation</a></li>\n",
+    "<li><a href=\"https://docs.cloud.oracle.com/iaas/tools/ads-sdk/latest/index.html\">ADS documentation</a></li>\n",
+    "</ul>\n",
+    "</details>\n",
+    "<details>\n",
+    "<summary><font size=\"2\">Typical Cell Imports and Settings for ADS</font></summary>\n",
+    "\n",
+    "```python\n",
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "%matplotlib inline\n",
+    "\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')\n",
+    "\n",
+    "import logging\n",
+    "logging.basicConfig(format='%(levelname)s:%(message)s', level=logging.ERROR)\n",
+    "\n",
+    "import ads\n",
+    "from ads.dataset.factory import DatasetFactory\n",
+    "from ads.automl.provider import OracleAutoMLProvider\n",
+    "from ads.automl.driver import AutoML\n",
+    "from ads.evaluations.evaluator import ADSEvaluator\n",
+    "from ads.common.data import ADSData\n",
+    "from ads.explanations.explainer import ADSExplainer\n",
+    "from ads.explanations.mlx_global_explainer import MLXGlobalExplainer\n",
+    "from ads.explanations.mlx_local_explainer import MLXLocalExplainer\n",
+    "from ads.catalog.model import ModelCatalog\n",
+    "from ads.common.model_artifact import ModelArtifact\n",
+    "```\n",
+    "</details>\n",
+    "<details>\n",
+    "<summary><font size=\"2\">Useful Environment Variables</font></summary>\n",
+    "\n",
+    "```python\n",
+    "import os\n",
+    "print(os.environ[\"NB_SESSION_COMPARTMENT_OCID\"])\n",
+    "print(os.environ[\"PROJECT_OCID\"])\n",
+    "print(os.environ[\"USER_OCID\"])\n",
+    "print(os.environ[\"TENANCY_OCID\"])\n",
+    "print(os.environ[\"NB_REGION\"])\n",
+    "```\n",
+    "</details>"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7f46ded9-ff40-455d-9722-4e2a07ad738b",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from create_save_embeddings import load_documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e857ddf5-74ef-446b-a581-98fa612f6816",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d4b43e87df1f4f4884ceb3c3968b738a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "loop1:   0%|          | 0/4 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "WARNING:ads.common:In the future model input will be serialized by `cloudpickle` by default. Currently, model input are serialized into a dictionary containing serialized input data and original data type information.Set `model_input_serializer=\"cloudpickle\"` to use cloudpickle model input serializer.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from ads.model.generic_model import GenericModel\n",
+    "import ads\n",
+    "\n",
+    "ads.set_auth(\"resource_principal\")\n",
+    "\n",
+    "embedding_model = GenericModel.from_model_deployment(\n",
+    "    \"ocid1.datasciencemodeldeployment.oc1.<ocid>\"\n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "702e1e22-cca2-4b82-a1ac-570e1d0f2e2f",
+   "metadata": {
+    "tags": [],
+    "pycharm": {
+     "is_executing": true
+    }
+   },
+   "outputs": [],
+   "source": [
+    "load_documents(embed_model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "926009ba-9fec-4ede-87c4-ea2282bc5857",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:root] *",
+   "language": "python",
+   "name": "conda-root-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}