2 Revize f037e13884 ... 29129466b6

Autor SHA1 Zpráva Datum
  lixin 29129466b6 解决rag.ipynb合并冲突,使用本地完整可运行作业代码 před 2 měsíci
  lixin 0e25128969 02 RAG作业完整可运行代码,PDF解析+文本分割+向量库+问答 před 2 měsíci

+ 4 - 0
.env

@@ -0,0 +1,4 @@
+BASE_URL = "https://api.moonshot.cn/v1/"
+OPENAI_API_KEY = "sk-a1Twi2bgye9dTJZdkP53ZBHApMDIRFTF8RFhT7IcYcvAb75b" 
+DS_API_KEY = "sk-5e02bc3ee39147ac9308491fcccf9dfd"
+DASHSCOPE_API_KEY = "sk-ws-H.RXRYLPY.WPz3.MEUCIAH2a0MyONT_Fc-E4OOzzrE64pvoS6S5-ksgW8UXBK0wAiEA2uBcyn5EMwDxxAEhupmjtwUOf2sTMWb2p3IC47ogABc"

binární
02_project/Chroma_db/2b3e4779-68dc-4216-a04d-ecb1c9e533b3/data_level0.bin


binární
02_project/Chroma_db/2b3e4779-68dc-4216-a04d-ecb1c9e533b3/header.bin


binární
02_project/Chroma_db/2b3e4779-68dc-4216-a04d-ecb1c9e533b3/length.bin


+ 0 - 0
02_project/Chroma_db/2b3e4779-68dc-4216-a04d-ecb1c9e533b3/link_lists.bin


binární
02_project/Chroma_db/chroma.sqlite3


+ 48 - 34
02_project/rag.ipynb

@@ -2,25 +2,17 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 10,
    "id": "0b0a2b15",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "C:\\Users\\Lenovo\\AppData\\Local\\Temp\\ipykernel_44776\\589161505.py:2: DeprecationWarning: `langchain-community` is being sunset and is no longer actively maintained. See https://github.com/langchain-ai/langchain-community/issues/674 for details and migration guidance toward standalone integration packages.\n",
-      "  from langchain_community.document_loaders import PyMuPDFLoader\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "文档类型:<class 'list'>\n",
       "PDF 共:26 页\n",
-      "元数据:{'producer': 'Microsoft® Word 2010', 'creator': 'Microsoft® Word 2010', 'creationdate': '2017-10-17T10:20:42+08:00', 'source': './国标 儿心量表 II.pdf', 'file_path': './国标 儿心量表 II.pdf', 'total_pages': 26, 'format': 'PDF 1.5', 'title': '标准名称', 'author': 'CNIS', 'subject': '', 'keywords': '', 'moddate': '2017-10-17T10:20:42+08:00', 'trapped': '', 'modDate': \"D:20171017102042+08'00'\", 'creationDate': \"D:20171017102042+08'00'\", 'page': 0}\n",
+      "元数据:{'producer': 'Microsoft® Word 2010', 'creator': 'Microsoft® Word 2010', 'creationdate': '2017-10-17T10:20:42+08:00', 'source': './国标儿心量表II.pdf', 'file_path': './国标儿心量表II.pdf', 'total_pages': 26, 'format': 'PDF 1.5', 'title': '标准名称', 'author': 'CNIS', 'subject': '', 'keywords': '', 'moddate': '2017-10-17T10:20:42+08:00', 'trapped': '', 'modDate': \"D:20171017102042+08'00'\", 'creationDate': \"D:20171017102042+08'00'\", 'page': 0}\n",
       "第一页内容预览:ICS 13.100 \n",
       "C 56 \n",
       "      \n",
@@ -41,7 +33,7 @@
    "source": [
     "# 导入文件\n",
     "from langchain_community.document_loaders import PyMuPDFLoader\n",
-    "pdf_loader = PyMuPDFLoader(\"./国标 儿心量表 II.pdf\")\n",
+    "pdf_loader = PyMuPDFLoader(\"./国标儿心量表II.pdf\")\n",
     "pdf_pages = pdf_loader.load()\n",
     "print(f\"文档类型:{type(pdf_pages)}\")\n",
     "print(f\"PDF 共:{len(pdf_pages)} 页\")\n",
@@ -53,7 +45,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 11,
    "id": "5b2fe97a",
    "metadata": {},
    "outputs": [
@@ -1457,7 +1449,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 12,
    "id": "63ddd9b4",
    "metadata": {},
    "outputs": [
@@ -3193,7 +3185,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 14,
    "id": "162f58bf",
    "metadata": {},
    "outputs": [],
@@ -3218,10 +3210,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 16,
    "id": "ec6607df",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\Lenovo\\AppData\\Local\\Temp\\ipykernel_3188\\2411040888.py:9: LangChainDeprecationWarning: Since Chroma 0.4.x the manual persistence method is no longer supported as docs are automatically persisted.\n",
+      "  db.persist() #向量保存到本地\n"
+     ]
+    }
+   ],
    "source": [
     "from langchain_community.vectorstores import Chroma\n",
     "\n",
@@ -3231,13 +3232,12 @@
     "    collection_metadata={\"hnsw:space\": \"cosine\"}, #余弦相似度\n",
     "    persist_directory=\"./Chroma_db\"\n",
     ")\n",
-    "db.persist() #向量保存到本地\n",
-    "\n"
+    "db.persist() #向量保存到本地"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 17,
    "id": "2de40144",
    "metadata": {},
    "outputs": [
@@ -3254,20 +3254,30 @@
       "发育商 develop\n",
       "来源:{}\n",
       "---- 结果:2----\n",
-      "内容:智龄 \n",
-      "心理年龄 \n",
-      "反映儿童智力水平高低的指标。 \n",
-      "注:在编制的量表中,按年龄分组编制测查项目,若被试者通过3岁的测查项目,就表示他使用该量表测查的智力年龄为3岁。 \n",
-      "2.3 \n",
-      "发育商 develop\n",
+      "内容:姓 名 \n",
+      "性 别 \n",
+      "民 族 \n",
+      "测验日期 \n",
+      "年 月 日 \n",
+      "出生日期 \n",
+      "年 月 日 \n",
+      "实足年龄 \n",
+      "项 目 \n",
+      "智 龄(月) \n",
+      "发育商(DQ) \n",
+      "大 运 动 \n",
+      "精细动作 \n",
+      "适应能力 \n",
+      "语 言 \n",
+      "社会行为 \n",
+      "全\n",
       "来源:{}\n",
       "---- 结果:3----\n",
-      "内容:智龄 \n",
-      "心理年龄 \n",
-      "反映儿童智力水平高低的指标。 \n",
-      "注:在编制的量表中,按年龄分组编制测查项目,若被试者通过3岁的测查项目,就表示他使用该量表测查的智力年龄为3岁。 \n",
-      "2.3 \n",
-      "发育商 develop\n",
+      "内容:4.4.3 计算发育商 \n",
+      "发育商计算方法见式(1)。 \n",
+      "5 发育商参考范围 \n",
+      "发育商参考范围:﹥130为优秀;110~129为良好;80~109为中等;70~79为临界偏低;﹤70为智力发育障碍。 \n",
+      "\n",
       "来源:{}\n"
      ]
     }
@@ -3286,7 +3296,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 19,
    "id": "e3bc3934",
    "metadata": {},
    "outputs": [
@@ -3294,7 +3304,11 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "=====RAG最终回答=====DQ即发育商(development quotient),是「用来衡量儿童心智发展水平的核心指标之一,是在大运动、精细动作、认知、情绪和社会性发展等方面对儿童发育情况进行衡量」的指标。其计算公式为:发育商=智龄÷实际年龄×100。\n"
+      "=====RAG最终回答=====发育商(development quotient,DQ)是「用来衡量儿童心智发展水平的核心指标之一,是在大运动、精细动作、认知、情绪和社会性发展等方面对儿童发育情况进行衡量」。\n",
+      "\n",
+      "其计算公式为:发育商=(智龄 / 实际年龄)×100。\n",
+      "\n",
+      "发育商参考范围:﹥130为优秀;110~129为良好;80~109为中等;70~79为临界偏低;﹤70为智力发育障碍。\n"
      ]
     }
    ],
@@ -3340,7 +3354,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "python_stydy (3.11.9)",
    "language": "python",
    "name": "python3"
   },

binární
02_project/国标儿心量表II.pdf