diff --git a/docs/use_cases/evaluation/evaluating_traced_examples.ipynb b/docs/use_cases/evaluation/evaluating_traced_examples.ipynb
index e54bbc9c373..15d785f50ad 100644
--- a/docs/use_cases/evaluation/evaluating_traced_examples.ipynb
+++ b/docs/use_cases/evaluation/evaluating_traced_examples.ipynb
@@ -1,327 +1,335 @@
 {
-    "cells": [{
-            "cell_type": "markdown",
-            "id": "1a4596ea-a631-416d-a2a4-3577c140493d",
-            "metadata": {},
-            "source": [
-                "## Running Chains on Traced Datasets\n",
-                "\n",
-                "Developing applications with language models can be uniquely challenging. To manage this complexity and ensure reliable performance, LangChain provides tracing and evaluation functionality through . This notebook demonstrates how to run Chains, which are language model functions, on previously captured datasets or traces. Some common use cases for this approach include:\n",
-                "\n",
-                "- Running an evaluation chain to grade previous runs.\n",
-                "- Comparing different chains, LLMs, and agents on traced datasets.\n",
-                "- Executing a stochastic chain multiple times over a dataset to generate metrics before deployment.\n",
-                "\n",
-                "Please note that this notebook assumes you have LangChain+ tracing running in the background. To set it up, follow the [tracing directions here](..\\/..\\/tracing\\/local_installation.md).\n"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 1,
-            "id": "904db9a5-f387-4a57-914c-c8af8d39e249",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.client import LangChainClient\n",
-                "\n",
-                "client = LangChainClient()"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "db79dea2-fbaa-4c12-9083-f6154b51e2d3",
-            "metadata": {},
-            "source": [
-                "## Seed an example dataset\n",
-                "\n",
-                "If you have been using LangChainPlus already, you may have datasets available. You can generate these from `Run`'s captured through the LangChain tracing API.\n",
-                "\n",
-                "```\n",
-                "datasets = client.list_datasets()\n",
-                "datasets\n",
-                "```\n",
-                "\n",
-                "Assuming you're running locally for the first time, you may not have runs stored, so we'll first upload an example evaluation dataset."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 2,
-            "id": "1baa677c-5642-4378-8e01-3aa1647f19d6",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "# !pip install datasets > /dev/null\n",
-                "# !pip install pandas > /dev/null"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 3,
-            "id": "60d14593-c61f-449f-a38f-772ca43707c2",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [{
-                    "name": "stderr",
-                    "output_type": "stream",
-                    "text": [
-                        "Found cached dataset json (/Users/wfh/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--agent-search-calculator-8a025c0ce5fb99d2/0.0.0/e347ab1c932092252e717ff3f949105a4dd28b27e842dd53157d2f72e276c2e4)\n"
-                    ]
-                },
-                {
-                    "data": {
-                        "application/vnd.jupyter.widget-view+json": {
-                            "model_id": "e84b657581c0444ebfb677a5644c4f79",
-                            "version_major": 2,
-                            "version_minor": 0
-                        },
-                        "text/plain": [
-                            "  0%|          | 0/1 [00:00<?, ?it/s]"
-                        ]
-                    },
-                    "metadata": {},
-                    "output_type": "display_data"
-                },
-                {
-                    "data": {
-                        "text/html": [
-                            "<div>\n",
-                            "<style scoped>\n",
-                            "    .dataframe tbody tr th:only-of-type {\n",
-                            "        vertical-align: middle;\n",
-                            "    }\n",
-                            "\n",
-                            "    .dataframe tbody tr th {\n",
-                            "        vertical-align: top;\n",
-                            "    }\n",
-                            "\n",
-                            "    .dataframe thead th {\n",
-                            "        text-align: right;\n",
-                            "    }\n",
-                            "</style>\n",
-                            "<table border=\"1\" class=\"dataframe\">\n",
-                            "  <thead>\n",
-                            "    <tr style=\"text-align: right;\">\n",
-                            "      <th></th>\n",
-                            "      <th>input</th>\n",
-                            "      <th>output</th>\n",
-                            "    </tr>\n",
-                            "  </thead>\n",
-                            "  <tbody>\n",
-                            "    <tr>\n",
-                            "      <th>0</th>\n",
-                            "      <td>How many people live in canada as of 2023?</td>\n",
-                            "      <td>approximately 38,625,801</td>\n",
-                            "    </tr>\n",
-                            "    <tr>\n",
-                            "      <th>1</th>\n",
-                            "      <td>who is dua lipa's boyfriend? what is his age r...</td>\n",
-                            "      <td>her boyfriend is Romain Gravas. his age raised...</td>\n",
-                            "    </tr>\n",
-                            "    <tr>\n",
-                            "      <th>2</th>\n",
-                            "      <td>what is dua lipa's boyfriend age raised to the...</td>\n",
-                            "      <td>her boyfriend is Romain Gravas. his age raised...</td>\n",
-                            "    </tr>\n",
-                            "    <tr>\n",
-                            "      <th>3</th>\n",
-                            "      <td>how far is it from paris to boston in miles</td>\n",
-                            "      <td>approximately 3,435 mi</td>\n",
-                            "    </tr>\n",
-                            "    <tr>\n",
-                            "      <th>4</th>\n",
-                            "      <td>what was the total number of points scored in ...</td>\n",
-                            "      <td>approximately 2.682651500990882</td>\n",
-                            "    </tr>\n",
-                            "  </tbody>\n",
-                            "</table>\n",
-                            "</div>"
-                        ],
-                        "text/plain": [
-                            "                                               input  \\\n",
-                            "0         How many people live in canada as of 2023?   \n",
-                            "1  who is dua lipa's boyfriend? what is his age r...   \n",
-                            "2  what is dua lipa's boyfriend age raised to the...   \n",
-                            "3        how far is it from paris to boston in miles   \n",
-                            "4  what was the total number of points scored in ...   \n",
-                            "\n",
-                            "                                              output  \n",
-                            "0                           approximately 38,625,801  \n",
-                            "1  her boyfriend is Romain Gravas. his age raised...  \n",
-                            "2  her boyfriend is Romain Gravas. his age raised...  \n",
-                            "3                             approximately 3,435 mi  \n",
-                            "4                    approximately 2.682651500990882  "
-                        ]
-                    },
-                    "execution_count": 3,
-                    "metadata": {},
-                    "output_type": "execute_result"
-                }
-            ],
-            "source": [
-                "import pandas as pd\n",
-                "from langchain.evaluation.loading import load_dataset\n",
-                "\n",
-                "dataset = load_dataset(\"agent-search-calculator\")\n",
-                "df = pd.DataFrame(dataset, columns=[\"question\", \"answer\"])\n",
-                "df.columns = [\"input\", \"output\"] # The chain we want to evaluate below expects inputs with the \"input\" key \n",
-                "df.head()"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 4,
-            "id": "f27e45f1-e299-4de8-a538-ee1272ac5024",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "dataset_name = f\"calculator_example.csv\""
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 5,
-            "id": "52a7ea76-79ca-4765-abf7-231e884040d6",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "if dataset_name not in set([dataset.name for dataset in client.list_datasets()]):\n",
-                "    dataset = client.upload_dataframe(df, \n",
-                "                            name=dataset_name,\n",
-                "                            description=\"Acalculator example dataset\",\n",
-                "                            input_keys=[\"input\"],\n",
-                "                            output_keys=[\"output\"],\n",
-                "                   )"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "07885b10",
-            "metadata": {
-                "tags": []
-            },
-            "source": [
-                "## Running a Chain on a Traced Dataset\n",
-                "\n",
-                "Once you have a dataset, you can run a chain over it to see its results. The run traces will automatically be associated with the dataset for easy attribution and analysis.\n",
-                "\n",
-                "**First, we'll define the chain we wish to run over the dataset.**\n",
-                "\n",
-                "In this case, we're using an agent, but it can be any simple chain."
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 6,
-            "id": "c2b59104-b90e-466a-b7ea-c5bd0194263b",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [],
-            "source": [
-                "from langchain.chat_models import ChatOpenAI\n",
-                "from langchain.agents import initialize_agent, load_tools\n",
-                "from langchain.agents import AgentType\n",
-                "\n",
-                "llm = ChatOpenAI(temperature=0)\n",
-                "tools = load_tools(['serpapi', 'llm-math'], llm=llm)\n",
-                "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=False)"
-            ]
-        },
-        {
-            "cell_type": "markdown",
-            "id": "84094a4a-1d76-461c-bc37-8c537939b466",
-            "metadata": {},
-            "source": [
-                "**Now we're ready to run the chain!**"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 7,
-            "id": "a8088b7d-3ab6-4279-94c8-5116fe7cee33",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [{
-                "name": "stderr",
-                "output_type": "stream",
-                "text": [
-                    "Chain failed for example e290c4f5-0d56-4848-91e6-d794cfeed276. Error: 'age'. Please try again with a valid numerical expression\n",
-                    "Chain failed for example a933211c-83c0-43c4-b22f-40e088263849. Error: invalid syntax. Perhaps you forgot a comma? (<expr>, line 1). Please try again with a valid numerical expression\n"
-                ]
-            }],
-            "source": [
-                "chain_results = await client.arun_chain_on_dataset(\n",
-                "    dataset_name=dataset_name,\n",
-                "    chain=agent,\n",
-                "    batch_size=5, # Optional, sets the number of examples to run at a time\n",
-                "    session_name=\"Calculator Dataset Runs\", # Optional. Will be sent to the 'default' session otherwise\n",
-                ")"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": 9,
-            "id": "136db492-d6ca-4215-96f9-439c23538241",
-            "metadata": {
-                "tags": []
-            },
-            "outputs": [{
-                "data": {
-                    "text/markdown": [
-                        "[Click here to visit the local LangChain+ Server](http://localhost/)"
-                    ],
-                    "text/plain": [
-                        "<IPython.core.display.Markdown object>"
-                    ]
-                },
-                "metadata": {},
-                "output_type": "display_data"
-            }],
-            "source": [
-                "from IPython.display import display, Markdown\n",
-                "\n",
-                "display(Markdown('[Click here to visit the local LangChain+ Server](http://localhost/)'))"
-            ]
-        },
-        {
-            "cell_type": "code",
-            "execution_count": null,
-            "id": "e5583cf2-0bc9-44d0-987a-b429f8f4e67d",
-            "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": "3.11.2"
-        }
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1a4596ea-a631-416d-a2a4-3577c140493d",
+   "metadata": {},
+   "source": [
+    "## Running Chains on Traced Datasets\n",
+    "\n",
+    "Developing applications with language models can be uniquely challenging. To manage this complexity and ensure reliable performance, LangChain provides tracing and evaluation functionality through . This notebook demonstrates how to run Chains, which are language model functions, on previously captured datasets or traces. Some common use cases for this approach include:\n",
+    "\n",
+    "- Running an evaluation chain to grade previous runs.\n",
+    "- Comparing different chains, LLMs, and agents on traced datasets.\n",
+    "- Executing a stochastic chain multiple times over a dataset to generate metrics before deployment.\n",
+    "\n",
+    "Please note that this notebook assumes you have LangChain+ tracing running in the background. To set it up, follow the [tracing directions here](..\\/..\\/tracing\\/local_installation.md).\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "904db9a5-f387-4a57-914c-c8af8d39e249",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.client import LangChainClient\n",
+    "\n",
+    "client = LangChainClient()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "db79dea2-fbaa-4c12-9083-f6154b51e2d3",
+   "metadata": {},
+   "source": [
+    "## Seed an example dataset\n",
+    "\n",
+    "If you have been using LangChainPlus already, you may have datasets available. You can generate these from `Run`'s captured through the LangChain tracing API.\n",
+    "\n",
+    "```\n",
+    "datasets = client.list_datasets()\n",
+    "datasets\n",
+    "```\n",
+    "\n",
+    "Assuming you're running locally for the first time, you may not have runs stored, so we'll first upload an example evaluation dataset."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "1baa677c-5642-4378-8e01-3aa1647f19d6",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# !pip install datasets > /dev/null\n",
+    "# !pip install pandas > /dev/null"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "60d14593-c61f-449f-a38f-772ca43707c2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Found cached dataset json (/Users/vwp/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--agent-search-calculator-8a025c0ce5fb99d2/0.0.0/e347ab1c932092252e717ff3f949105a4dd28b27e842dd53157d2f72e276c2e4)\n"
+     ]
     },
-    "nbformat": 4,
-    "nbformat_minor": 5
-}
\ No newline at end of file
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9d623c0e9719474a96241657e50ee6cc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>input</th>\n",
+       "      <th>output</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>How many people live in canada as of 2023?</td>\n",
+       "      <td>approximately 38,625,801</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>who is dua lipa's boyfriend? what is his age r...</td>\n",
+       "      <td>her boyfriend is Romain Gravas. his age raised...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>what is dua lipa's boyfriend age raised to the...</td>\n",
+       "      <td>her boyfriend is Romain Gravas. his age raised...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>how far is it from paris to boston in miles</td>\n",
+       "      <td>approximately 3,435 mi</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>what was the total number of points scored in ...</td>\n",
+       "      <td>approximately 2.682651500990882</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                               input  \\\n",
+       "0         How many people live in canada as of 2023?   \n",
+       "1  who is dua lipa's boyfriend? what is his age r...   \n",
+       "2  what is dua lipa's boyfriend age raised to the...   \n",
+       "3        how far is it from paris to boston in miles   \n",
+       "4  what was the total number of points scored in ...   \n",
+       "\n",
+       "                                              output  \n",
+       "0                           approximately 38,625,801  \n",
+       "1  her boyfriend is Romain Gravas. his age raised...  \n",
+       "2  her boyfriend is Romain Gravas. his age raised...  \n",
+       "3                             approximately 3,435 mi  \n",
+       "4                    approximately 2.682651500990882  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "from langchain.evaluation.loading import load_dataset\n",
+    "\n",
+    "dataset = load_dataset(\"agent-search-calculator\")\n",
+    "df = pd.DataFrame(dataset, columns=[\"question\", \"answer\"])\n",
+    "df.columns = [\"input\", \"output\"] # The chain we want to evaluate below expects inputs with the \"input\" key \n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "f27e45f1-e299-4de8-a538-ee1272ac5024",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "dataset_name = f\"calculator_example.csv\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "52a7ea76-79ca-4765-abf7-231e884040d6",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "if dataset_name not in set([dataset.name for dataset in client.list_datasets()]):\n",
+    "    dataset = client.upload_dataframe(df, \n",
+    "                            name=dataset_name,\n",
+    "                            description=\"Acalculator example dataset\",\n",
+    "                            input_keys=[\"input\"],\n",
+    "                            output_keys=[\"output\"],\n",
+    "                   )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "07885b10",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## Running a Chain on a Traced Dataset\n",
+    "\n",
+    "Once you have a dataset, you can run a chain over it to see its results. The run traces will automatically be associated with the dataset for easy attribution and analysis.\n",
+    "\n",
+    "**First, we'll define the chain we wish to run over the dataset.**\n",
+    "\n",
+    "In this case, we're using an agent, but it can be any simple chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "c2b59104-b90e-466a-b7ea-c5bd0194263b",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.agents import initialize_agent, load_tools\n",
+    "from langchain.agents import AgentType\n",
+    "\n",
+    "llm = ChatOpenAI(temperature=0)\n",
+    "tools = load_tools(['serpapi', 'llm-math'], llm=llm)\n",
+    "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "84094a4a-1d76-461c-bc37-8c537939b466",
+   "metadata": {},
+   "source": [
+    "**Now we're ready to run the chain!**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a8088b7d-3ab6-4279-94c8-5116fe7cee33",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Chain failed for example e290c4f5-0d56-4848-91e6-d794cfeed276. Error: 'age'. Please try again with a valid numerical expression\n",
+      "Chain failed for example ec590bea-8b5b-429b-a9f4-7d035e66853e. Error: unknown format from LLM: It is impossible to accurately predict the total number of points scored in a future event. Therefore, a mathematical expression cannot be provided.\n",
+      "Chain failed for example a933211c-83c0-43c4-b22f-40e088263849. Error: invalid syntax. Perhaps you forgot a comma? (<expr>, line 1). Please try again with a valid numerical expression\n",
+      "Chain failed for example b925eaa0-6b63-45c1-a3c3-c11ad53ca0eb. Error: 'VariableNode' object is not callable. Please try again with a valid numerical expression\n"
+     ]
+    }
+   ],
+   "source": [
+    "chain_results = await client.arun_chain_on_dataset(\n",
+    "    dataset_name=dataset_name,\n",
+    "    chain=agent,\n",
+    "    batch_size=5, # Optional, sets the number of examples to run at a time\n",
+    "    session_name=\"Calculator Dataset Runs\", # Optional. Will be sent to the 'default' session otherwise\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "136db492-d6ca-4215-96f9-439c23538241",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/markdown": [
+       "[Click here to visit the local LangChain+ Server](http://localhost/)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.Markdown object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from IPython.display import display, Markdown\n",
+    "\n",
+    "display(Markdown('[Click here to visit the local LangChain+ Server](http://localhost/)'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e5583cf2-0bc9-44d0-987a-b429f8f4e67d",
+   "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": "3.11.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}