added langsmith demo

Author: jjmachan

Langchain/imgs/smith-getstarted.png

@@ -0,0 +1,110 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "59d9c713",
+   "metadata": {},
+   "source": [
+    "# Langsmith\n",
+    "**The companion tool I've been waiting for**\n",
+    "![viusalize your runs with langsmith](https://docs.smith.langchain.com/assets/images/run_details-f579aef109cb8f576e7a4a864e405143.png)\n",
+    "\n",
+    "debugging is a pain when building complicated LLM application. There is a lot of text to parse from each step, each input and output is different and if there is an a step mid-way, it is hard to change just that value and run it again. Basically when developing I want a tool that\n",
+    "- shows me exactly what the input/outputs are from the LLM, tools etc (visualisation)\n",
+    "- allows me to edit prompts at each step and see how it affects the output (live debugging)\n",
+    "- show the exact sequence of events, the time taken at each step, tokens used\n",
+    "- share the my debug traces with other (honestly I didn't know I needed this until I saw langsmith has support for it 😂)\n",
+    "\n",
+    "and boy does langsmith solve these problems. In-face I've changed my workflow to always have langsmith open in the side, logging everything, ready to be help me visualize what is happening with my apps.\n",
+    "\n",
+    "Langsmith also has a few more features and you can see the whole list [here](https://docs.smith.langchain.com/overview)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0e43ec44",
+   "metadata": {},
+   "source": [
+    "## Getting Started"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "296878ac",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"LANGCHAIN_TRACING_V2\"]=\"true\"\n",
+    "os.environ[\"LANGCHAIN_ENDPOINT\"]=\"https://api.smith.langchain.com\"\n",
+    "os.environ[\"LANGCHAIN_API_KEY\"]=\"<your-api-key>\"\n",
+    "os.environ[\"LANGCHAIN_PROJECT\"]=\"<your-project>\"  # if not specified, defaults to \"default\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c8d70977",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Hello! How can I assist you today?'"
+      ]
+     },
+     "execution_count": 1,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI()\n",
+    "llm.predict(\"Hello, world!\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cb6bddf0",
+   "metadata": {},
+   "source": [
+    "and this is the output of the run in langsmith's dashboard\n",
+    "\n",
+    "![](imgs/smith-getstarted.png)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2988c6d1",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}