feat: add `AI_session_overview_generator`notebook

notebooks/AI_session_overview_generator.ipynb

@@ -0,0 +1,232 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Generating Session Summary with LLMs\n",
+    "\n",
+    "This project utilizes LlamaIndex and AI technology to analyze Formula 1 car data and generate session summaries. It is particularly beneficial for race engineers seeking detailed insights and performance analysis during races.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from dotenv import load_dotenv\n",
+    "load_dotenv()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Optional: Setup Observability\n",
+    "\n",
+    "Here we will use our Arize Phoenix integration to view traces through the query engine. It will be available at http://localhost:6006\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNI [opentelemetry.instrumentation.instrumentor] Attempting to instrument while already instrumented\n"
+     ]
+    }
+   ],
+   "source": [
+    "from openinference.instrumentation.llama_index import LlamaIndexInstrumentor\n",
+    "from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter\n",
+    "from opentelemetry.sdk import trace as trace_sdk\n",
+    "from opentelemetry.sdk.trace.export import SimpleSpanProcessor\n",
+    "\n",
+    "endpoint = \"http://127.0.0.1:6006/v1/traces\"  # Phoenix receiver address\n",
+    "\n",
+    "tracer_provider = trace_sdk.TracerProvider()\n",
+    "tracer_provider.add_span_processor(\n",
+    "    SimpleSpanProcessor(OTLPSpanExporter(endpoint)))\n",
+    "\n",
+    "LlamaIndexInstrumentor().instrument(tracer_provider=tracer_provider)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Start SQL Database\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sqlalchemy import create_engine\n",
+    "from llama_index.core import SQLDatabase\n",
+    "\n",
+    "engine = create_engine('sqlite:///spain_practice_1.db')\n",
+    "\n",
+    "sql_database = SQLDatabase(engine, include_tables=[\"mercedes\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Define the LLM and the Embedding\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.embeddings.openai import OpenAIEmbedding\n",
+    "from llama_index.llms.openai import OpenAI\n",
+    "from llama_index.core import Settings\n",
+    "\n",
+    "Settings.llm = OpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
+    "Settings.embed_model = OpenAIEmbedding(model=\"text-embedding-ada-002\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Define the Retriever and the Query Engine\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_index.core.retrievers import NLSQLRetriever\n",
+    "from llama_index.core.query_engine import RetrieverQueryEngine\n",
+    "\n",
+    "nl_sql_retriever = NLSQLRetriever(\n",
+    "    sql_database, tables=[\"mercedes\"], return_raw=True\n",
+    ")\n",
+    "\n",
+    "query_engine = RetrieverQueryEngine.from_args(nl_sql_retriever)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Start retrieving information to construct the report\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
+      "I0000 00:00:1723244252.910416 2380678 fork_posix.cc:77] Other threads are currently calling into gRPC, skipping fork() handlers\n"
+     ]
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\n",
+    "    \"Which driver was faster on average on sector 1?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      ">>>  RUS was faster on average on sector 1.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\">>> \", str(response))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      ">>>  HAM\n"
+     ]
+    }
+   ],
+   "source": [
+    "response2 = query_engine.query(\n",
+    "    \"Which driver was faster on average on sector 2?\"\n",
+    ")\n",
+    "\n",
+    "print(\">>> \", str(response2))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      ">>>  The driver HAM is 28 years old and has a lap time of 98.0705652173913 seconds with a top speed of 289.0 km/h.\n"
+     ]
+    }
+   ],
+   "source": [
+    "response3 = query_engine.query(\n",
+    "    \"Write a summary about the driver HAM\"\n",
+    ")\n",
+    "\n",
+    "print(\">>> \", str(response3))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama",
+   "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",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}