fix langsmith evaluation related issues

Author: DjangoPeng

langchain/langsmith/evaluation.ipynb

@@ -17,6 +17,16 @@
     "本教程展示一个非常简单的 LLM 应用（分类器）的评估流程，该应用会将输入数据标记为“有毒（Toxic）”或“无毒（Not Toxic）”。"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4913e104-82e6-4932-8e80-2b8bd57553c3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip show langsmith"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "9c8c8225-42bd-4c9b-adeb-62c83f80c9d3",
@@ -157,19 +167,33 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 4,
    "id": "eeec0c29-5e85-46e1-915b-619b68627d63",
    "metadata": {},
    "outputs": [
     {
-     "ename": "ImportError",
-     "evalue": "cannot import name 'evaluate' from 'langsmith.evaluation' (/home/ubuntu/miniconda3/envs/langchain/lib/python3.10/site-packages/langsmith/evaluation/__init__.py)",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mImportError\u001b[0m                               Traceback (most recent call last)",
-      "Cell \u001b[0;32mIn[20], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mlangsmith\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mevaluation\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m evaluate\n\u001b[1;32m      3\u001b[0m \u001b[38;5;66;03m# 数据集名称\u001b[39;00m\n\u001b[1;32m      4\u001b[0m dataset_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mToxic Queries\u001b[39m\u001b[38;5;124m\"\u001b[39m\n",
-      "\u001b[0;31mImportError\u001b[0m: cannot import name 'evaluate' from 'langsmith.evaluation' (/home/ubuntu/miniconda3/envs/langchain/lib/python3.10/site-packages/langsmith/evaluation/__init__.py)"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/ubuntu/miniconda3/envs/langchain/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "View the evaluation results for experiment: 'Toxic Queries-465b0ea2' at:\n",
+      "https://smith.langchain.com/o/3d35c1a5-b729-4d18-b06d-db0f06a30bc1/datasets/e1df55ff-b66c-4bcf-b5fd-7c63a847136e/compare?selectedSessions=2900c5b7-9dd5-482a-ab79-32888be3d5b9\n",
+      "\n",
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "6it [00:01,  4.71it/s]\n"
      ]
     }
    ],
@@ -218,7 +242,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 5,
    "id": "46817304-1e17-4ca1-a5ba-faebd80c3728",
    "metadata": {},
    "outputs": [],
@@ -251,7 +275,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "096e3129-8e5e-42b9-8c42-d59f072f20c5",
    "metadata": {},
    "outputs": [],
@@ -308,17 +332,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 7,
    "id": "431bbdb3-d4a3-445a-9cfc-2e62adff3ad0",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "\"To build a RAG (Retrieval-Augmented Generation) chain in LangChain Expression Language (LCEL), you integrate components that handle retrieval (searching for relevant information from a database or document collection) and generation (creating responses based on the retrieved information). The LCEL document provided doesn't go into specifics about a RAG chain configuration, but based on the principles of LCEL, I can guide you through constructing a simplified RAG chain using hypothetical LCEL com\""
+       "\"To build a Retrieval-Augmented Generation (RAG) chain in LCEL, you would need to compose a chain that includes a retriever component to fetch relevant documents or data based on a query, and then pass that retrieved data to a generator model to produce a final output. In LCEL, this would typically involve using `Retriever` and `Generator` components, which you can easily piece together thanks to LCEL's composable nature.\\n\\nThe following example is a simplified step-by-step guide to building a bas\""
       ]
      },
-     "execution_count": 32,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -331,7 +355,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1b4ca951-0ed8-41c5-adb9-694776a7a2e7",
+   "id": "3a974aa5-7f2e-42f0-bcc4-05ad35cc10d7",
    "metadata": {},
    "outputs": [],
    "source": []

requirements.txt

@@ -5,7 +5,7 @@ langchain-core==0.2.1
 langchain-community==0.2.0
 langchain-experimental==0.0.59
 langchain-text-splitters==0.2.0
-langsmith==0.1.62
+langsmith==0.1.65
 chromadb==0.4.24
 faiss-cpu==1.8.0
 gradio==4.22.0