DjangoPeng · yajunjiao · Mar 28, 2024 · Mar 28, 2024 · Mar 28, 2024 · Mar 28, 2024
diff --git a/.gitignore b/.gitignore
@@ -169,4 +169,10 @@ openai_api/data/fine_food_reviews_with_embeddings_1k_2146.csv
 *.bin
 
 langchain/openai-translator/flagged/*
-langchain/openai-translator/flask_temps/*
+langchain/openai-translator/flask_temps/*
+openai-translator/ai_translator/.idea/ai_translator.iml
+openai-translator/ai_translator/.idea/inspectionProfiles/profiles_settings.xml
+openai-translator/ai_translator/.idea/inspectionProfiles/Project_Default.xml
+openai-translator/ai_translator/.idea/misc.xml
+openai-translator/ai_translator/.idea/modules.xml
+openai-translator/ai_translator/.idea/vcs.xml
diff --git a/langchain/jupyter/agents/openai_functionTest.ipynb b/langchain/jupyter/agents/openai_functionTest.ipynb
@@ -0,0 +1,313 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T12:01:26.511156800Z",
+     "start_time": "2024-03-29T12:01:20.975005400Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "from langchain.agents import tool\n",
+    "\n",
+    "@tool\n",
+    "def get_word_length(word: str) -> int:\n",
+    "    \"\"\"Returns the length of a word.\"\"\"\n",
+    "    return len(word)\n",
+    "\n",
+    "tools = [get_word_length]"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T12:02:39.804177100Z",
+     "start_time": "2024-03-29T12:02:38.049455200Z"
+    }
+   },
+   "id": "2d9fe2c1a3654657",
+   "execution_count": 2
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "from langchain.schema import SystemMessage\n",
+    "from langchain.agents import OpenAIFunctionsAgent\n",
+    "\n",
+    "system_message = SystemMessage(content=\"你是非常强大的AI助手，但在计算单词长度方面不擅长。\")\n",
+    "prompt = OpenAIFunctionsAgent.create_prompt(system_message=system_message)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T12:04:19.417806500Z",
+     "start_time": "2024-03-29T12:04:19.341513200Z"
+    }
+   },
+   "id": "54350a24c993624d",
+   "execution_count": 3
+  },
+  {
+   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "D:\\soft\\Python312\\Lib\\site-packages\\langchain_core\\_api\\deprecation.py:117: LangChainDeprecationWarning: The class `langchain.agents.openai_functions_agent.base.OpenAIFunctionsAgent` was deprecated in langchain 0.1.0 and will be removed in 0.2.0. Use create_openai_functions_agent instead.\n",
+      "  warn_deprecated(\n"
+     ]
+    }
+   ],
+   "source": [
+    "agent = OpenAIFunctionsAgent(llm=llm, tools=tools, prompt=prompt)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T12:04:53.611433300Z",
+     "start_time": "2024-03-29T12:04:52.422558700Z"
+    }
+   },
+   "id": "7e3e7c9a1e101a69",
+   "execution_count": 4
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "from langchain.agents import AgentExecutor\n",
+    "\n",
+    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T12:05:42.170247400Z",
+     "start_time": "2024-03-29T12:05:42.150934200Z"
+    }
+   },
+   "id": "17922ddf5f435a1d",
+   "execution_count": 5
+  },
+  {
+   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "D:\\soft\\Python312\\Lib\\site-packages\\langchain_core\\_api\\deprecation.py:117: LangChainDeprecationWarning: The function `run` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use invoke instead.\n",
+      "  warn_deprecated(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3m\n",
+      "Invoking: `get_word_length` with `{'word': 'educa'}`\n",
+      "\n",
+      "\n",
+      "\u001B[0m\u001B[36;1m\u001B[1;3m5\u001B[0m\u001B[32;1m\u001B[1;3m单词“educa”中有5个字母。\u001B[0m\n",
+      "\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "'单词“educa”中有5个字母。'"
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.run(\"单词“educa”中有多少个字母？\")"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T12:06:13.829616200Z",
+     "start_time": "2024-03-29T12:06:11.478938400Z"
+    }
+   },
+   "id": "bc07104a44ab6d5b",
+   "execution_count": 6
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import MessagesPlaceholder\n",
+    "\n",
+    "MEMORY_KEY = \"chat_history\"\n",
+    "prompt = OpenAIFunctionsAgent.create_prompt(\n",
+    "    system_message=system_message,\n",
+    "    extra_prompt_messages=[MessagesPlaceholder(variable_name=MEMORY_KEY)]\n",
+    ")"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T12:07:55.933638900Z",
+     "start_time": "2024-03-29T12:07:55.593759400Z"
+    }
+   },
+   "id": "ccb7cece70540a30",
+   "execution_count": 7
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "from langchain.memory import ConversationBufferMemory\n",
+    "\n",
+    "memory = ConversationBufferMemory(memory_key=MEMORY_KEY, return_messages=True)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T12:08:53.107717300Z",
+     "start_time": "2024-03-29T12:08:53.102043400Z"
+    }
+   },
+   "id": "addb142685d40adb",
+   "execution_count": 8
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "agent = OpenAIFunctionsAgent(llm=llm, tools=tools, prompt=prompt)\n",
+    "agent_executor = AgentExecutor(agent=agent, tools=tools, memory=memory, verbose=True)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T12:09:50.125508800Z",
+     "start_time": "2024-03-29T12:09:50.116425500Z"
+    }
+   },
+   "id": "dce86e5dc17f716f",
+   "execution_count": 9
+  },
+  {
+   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3m\n",
+      "Invoking: `get_word_length` with `{'word': 'educa'}`\n",
+      "\n",
+      "\n",
+      "\u001B[0m\u001B[36;1m\u001B[1;3m5\u001B[0m\u001B[32;1m\u001B[1;3m单词“educa”中有5个字母。\u001B[0m\n",
+      "\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "'单词“educa”中有5个字母。'"
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.run(\"单词“educa”中有多少个字母?\")"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T12:10:15.044103900Z",
+     "start_time": "2024-03-29T12:10:12.383340Z"
+    }
+   },
+   "id": "f4a142b8bb0cbc0d",
+   "execution_count": 10
+  },
+  {
+   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3m抱歉，我之前给出的答案有误。单词“educa”实际上不是一个真实的单词。请问您还有其他问题吗？\u001B[0m\n",
+      "\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "'抱歉，我之前给出的答案有误。单词“educa”实际上不是一个真实的单词。请问您还有其他问题吗？'"
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.run(\"那是一个真实的单词吗？\")"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T12:10:45.587808900Z",
+     "start_time": "2024-03-29T12:10:43.443403100Z"
+    }
+   },
+   "id": "6fe525108f45b5da",
+   "execution_count": 11
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/langchain/jupyter/agents/reactTest.ipynb b/langchain/jupyter/agents/reactTest.ipynb
@@ -0,0 +1,294 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T11:59:53.906392600Z",
+     "start_time": "2024-03-29T11:59:53.892848300Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "#os.environ[\"SERPAPI_API_KEY\"] = \"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'a02b49e6015aeb93ce4dbfd99b57418a5fcf37d62d65150fe58f05ea0a4dee17'"
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "os.environ[\"SERPAPI_API_KEY\"]"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T11:59:53.921749100Z",
+     "start_time": "2024-03-29T11:59:53.910572700Z"
+    }
+   },
+   "id": "c44e8fe66e3e5f06",
+   "execution_count": 2
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "from langchain_openai import OpenAI\n",
+    "\n",
+    "llm = OpenAI(temperature=0)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T11:46:52.577934400Z",
+     "start_time": "2024-03-29T11:46:46.942689500Z"
+    }
+   },
+   "id": "1e11ac9db94a3248",
+   "execution_count": 4
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "from langchain.agents import load_tools\n",
+    "from langchain.agents import initialize_agent\n",
+    "from langchain.agents import AgentType\n",
+    "\n",
+    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T11:48:45.628852700Z",
+     "start_time": "2024-03-29T11:48:45.603825200Z"
+    }
+   },
+   "id": "4453850349cd8662",
+   "execution_count": 7
+  },
+  {
+   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple\n",
+      "Collecting numexpr\n",
+      "  Downloading https://pypi.tuna.tsinghua.edu.cn/packages/d0/ff/87d5439fef391607dca416af15a07aebcceccf7e3816966507c11b58a2a3/numexpr-2.9.0-cp312-cp312-win_amd64.whl (96 kB)\n",
+      "     ---------------------------------------- 0.0/96.7 kB ? eta -:--:--\n",
+      "     -------------------------------------- - 92.2/96.7 kB 2.6 MB/s eta 0:00:01\n",
+      "     ---------------------------------------- 96.7/96.7 kB 1.9 MB/s eta 0:00:00\n",
+      "Requirement already satisfied: numpy>=1.13.3 in d:\\soft\\python312\\lib\\site-packages (from numexpr) (1.26.4)\n",
+      "Installing collected packages: numexpr\n",
+      "Successfully installed numexpr-2.9.0\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "pip install numexpr"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T11:48:39.002740800Z",
+     "start_time": "2024-03-29T11:48:33.036875100Z"
+    }
+   },
+   "id": "82e339dbb3363e2e",
+   "execution_count": 6
+  },
+  {
+   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "D:\\soft\\Python312\\Lib\\site-packages\\langchain_core\\_api\\deprecation.py:117: LangChainDeprecationWarning: The function `initialize_agent` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use Use new agent constructor methods like create_react_agent, create_json_agent, create_structured_chat_agent, etc. instead.\n",
+      "  warn_deprecated(\n"
+     ]
+    }
+   ],
+   "source": [
+    "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T11:49:42.587337300Z",
+     "start_time": "2024-03-29T11:49:42.544704200Z"
+    }
+   },
+   "id": "c7752fb2880e1f50",
+   "execution_count": 8
+  },
+  {
+   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "D:\\soft\\Python312\\Lib\\site-packages\\langchain_core\\_api\\deprecation.py:117: LangChainDeprecationWarning: The function `run` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use invoke instead.\n",
+      "  warn_deprecated(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3m I should use a search engine to find information about Leonardo DiCaprio's girlfriend and then use a calculator to calculate her age.\n",
+      "Action: Search\n",
+      "Action Input: \"Leonardo DiCaprio girlfriend\"\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3m[{'title': 'Is Leonardo DiCaprio Engaged to Vittoria Ceretti?', 'link': 'https://www.thecut.com/article/leonardo-dicaprio-vittoria-ceretti-engagement-ring.html', 'source': 'The Cut', 'date': '1 day ago', 'thumbnail': 'https://serpapi.com/searches/6606ab095f2203b7ae8d7f5b/images/7db95bf161919ea5f1437993aeba4501fe9fba0acebd51c0.jpeg'}, {'title': 'Leonardo DiCaprio, 49, gets cozy again with model Vittoria Ceretti, 25, and she even flashes a ring on THAT fi', 'link': 'https://www.dailymail.co.uk/tvshowbiz/article-13243303/Leonardo-DiCaprios-girlfriend-Vittoria-Ceretti-wearing-ring.html', 'source': 'Daily Mail', 'date': '2 days ago', 'thumbnail': 'https://serpapi.com/searches/6606ab095f2203b7ae8d7f5b/images/7db95bf161919ea5cc24078b67e8880b2a2065d86299c6fa.jpeg'}, {'title': 'Leonardo DiCaprio, 49, and Vittoria Ceretti, 25, spark engagement rumors as she flaunts new ring', 'link': 'https://pagesix.com/2024/03/27/entertainment/leonardo-dicaprio-vittoria-ceretti-spark-engagement-rumors/', 'source': 'Page Six', 'date': '1 day ago', 'thumbnail': 'https://serpapi.com/searches/6606ab095f2203b7ae8d7f5b/images/7db95bf161919ea541824bea9924d255b388ee4b94430297.jpeg'}, {'title': 'Leonardo DiCaprio sparks engagement rumors as girlfriend Vittoria Ceretti wears ring', 'link': 'https://www.marca.com/en/lifestyle/celebrities/2024/03/27/66047769ca47418c0e8b4586.html', 'source': 'Marca.com', 'date': '1 day ago', 'thumbnail': 'https://serpapi.com/searches/6606ab095f2203b7ae8d7f5b/images/7db95bf161919ea53904a654108da52820108789c1eba021.jpeg'}, {'title': 'Leonardo DiCaprio Sparks Engagement Rumors As Girlfriend Flaunts New NDA', 'link': 'https://www.theonion.com/leonardo-dicaprio-sparks-engagement-rumors-as-girlfrien-1851372103', 'source': 'The Onion', 'date': '17 hours ago', 'thumbnail': 'https://serpapi.com/searches/6606ab095f2203b7ae8d7f5b/images/7db95bf161919ea527cbadd3e3a65364753b1fe0e1644e19.jpeg'}]\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m Based on the search results, it seems like Leonardo DiCaprio's current girlfriend is model Vittoria Ceretti.\n",
+      "Action: Calculator\n",
+      "Action Input: 25^0.43\u001B[0m\n",
+      "Observation: \u001B[33;1m\u001B[1;3mAnswer: 3.991298452658078\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m This is the age of Vittoria Ceretti, Leonardo DiCaprio's girlfriend.\n",
+      "Final Answer: 3.991298452658078\u001B[0m\n",
+      "\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "'3.991298452658078'"
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.run(\"谁是莱昂纳多·迪卡普里奥的女朋友？她现在年龄的0.43次方是多少?\")"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T11:50:59.530688400Z",
+     "start_time": "2024-03-29T11:50:30.210495300Z"
+    }
+   },
+   "id": "52c7fd4ebdf9f425",
+   "execution_count": 9
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "bad1d32af38c87fc"
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "使用聊天模型(GPT-4)"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "e503b910460133d1"
+  },
+  {
+   "cell_type": "code",
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: The first part of the question is about Leonardo DiCaprio's girlfriend, which I can search for. The second part involves a mathematical calculation that I can perform using a calculator.\n",
+      "\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Search\",\n",
+      "  \"action_input\": \"Leonardo DiCaprio current girlfriend\"\n",
+      "}\n",
+      "```\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3mVittoria Ceretti\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m```\n",
+      "{\n",
+      "  \"action\": \"Calculator\",\n",
+      "  \"action_input\": \"0.43 ^ 2\"\n",
+      "}\n",
+      "```\u001B[0m\n",
+      "Observation: \u001B[33;1m\u001B[1;3mAnswer: 0.18489999999999998\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mFinal Answer: Vittoria Ceretti, 0.1849\u001B[0m\n",
+      "\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "'Vittoria Ceretti, 0.1849'"
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "chat_model = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
+    "agent = initialize_agent(tools, chat_model, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)\n",
+    "agent.run(\"谁是莱昂纳多·迪卡普里奥的女朋友？她现在年龄的0.43次方是多少?\")"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "ExecuteTime": {
+     "end_time": "2024-03-29T11:55:04.054776900Z",
+     "start_time": "2024-03-29T11:54:52.682394100Z"
+    }
+   },
+   "id": "f8e5f3fdde98c5e2",
+   "execution_count": 10
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/langchain/jupyter/agents/self_ask_with_searchTest.ipynb b/langchain/jupyter/agents/self_ask_with_searchTest.ipynb
diff --git a/langchain/jupyter/autogpt/China_Gold_Medal_Count_2023_Chengdu_Universiade.txt b/langchain/jupyter/autogpt/China_Gold_Medal_Count_2023_Chengdu_Universiade.txt
@@ -0,0 +1 @@
+China won 103 gold medals at the 2023 Chengdu Universiade.
diff --git a/langchain/jupyter/autogpt/China_gold_medals_2023_Chengdu_Universiade.txt b/langchain/jupyter/autogpt/China_gold_medals_2023_Chengdu_Universiade.txt
@@ -0,0 +1 @@
+China won 103 gold medals at the 2023 Chengdu Universiade.
diff --git a/langchain/jupyter/autogpt/autogptTest.ipynb b/langchain/jupyter/autogpt/autogptTest.ipynb
diff --git a/langchain/jupyter/chains/router_chainTest.ipynb b/langchain/jupyter/chains/router_chainTest.ipynb
diff --git a/langchain/jupyter/chains/sequential_chainTest.ipynb b/langchain/jupyter/chains/sequential_chainTest.ipynb
diff --git a/langchain/jupyter/chains/transform_chainTest.ipynb b/langchain/jupyter/chains/transform_chainTest.ipynb
diff --git a/langchain/jupyter/data_connection/document_loaderTest.ipynb b/langchain/jupyter/data_connection/document_loaderTest.ipynb
diff --git a/langchain/jupyter/data_connection/doucument_transformerTest.ipynb b/langchain/jupyter/data_connection/doucument_transformerTest.ipynb
diff --git a/langchain/jupyter/data_connection/text_embeddingTest.ipynb b/langchain/jupyter/data_connection/text_embeddingTest.ipynb
diff --git a/langchain/jupyter/data_connection/vector_storesTest.ipynb b/langchain/jupyter/data_connection/vector_storesTest.ipynb
diff --git a/langchain/jupyter/memory/memoryTest.ipynb b/langchain/jupyter/memory/memoryTest.ipynb
diff --git a/langchain/jupyter/model_io/modelTest.ipynb b/langchain/jupyter/model_io/modelTest.ipynb
diff --git a/langchain/jupyter/model_io/output_parserTest.ipynb b/langchain/jupyter/model_io/output_parserTest.ipynb
diff --git a/langchain/jupyter/model_io/promptTest.ipynb b/langchain/jupyter/model_io/promptTest.ipynb
diff --git a/langchain/openai-translator/ai_translator/config.yaml b/langchain/openai-translator/ai_translator/config.yaml
@@ -0,0 +1,5 @@
+model_name: "gpt-3.5-turbo"
+input_file: "../tests/test.pdf"
+output_file_format: "markdown"
+source_language: "English"
+target_language: "Chinese"
diff --git a/langchain/openai-translator/ai_translator/main.py b/langchain/openai-translator/ai_translator/main.py
@@ -17,4 +17,6 @@
 
     # 实例化 PDFTranslator 类，并调用 translate_pdf() 方法
     translator = PDFTranslator(config.model_name)
+    LOG.debug(config.input_file)
+    LOG.debug(config.output_file_format)
     translator.translate_pdf(config.input_file, config.output_file_format, pages=None)
diff --git a/langchain/openai-translator/tests/test_translated.md b/langchain/openai-translator/tests/test_translated.md
@@ -1,19 +1,20 @@
 测试数据
 这个数据集包含了由OpenAI的AI语言模型ChatGPT提供的两个测试样本。
-这些样本包括一个Markdown表格和一个英文文本段落，可以用来测试支持文本和表格格式的英译中翻译软件。
+这些样本包括一个Markdown表格和一个英文文本段落，可用于测试支持文本和表格格式的英文到中文翻译软件。
 文本测试
-快速的棕色狐狸跳过懒狗。这个句子包含了英语字母表中的每个字母至少一次。句子是经常用来测试字体、键盘和其他与文本相关的工具的。除了英语，其他许多语言也有句子。由于语言的独特特点，有些句子更难构造。
+快速的棕色狐狸跳过懒狗。这个句子包含了英语字母表中的每个字母至少一次。全字母句经常用于测试字体、键盘和其他文本相关工具。除了英语，许多其他语言也有全字母句。由于语言的独特特点，有些全字母句更难构造。
+表格测试
 
-| 水果 | 颜色 | 价格（美元） |
-| --- | --- | --- |
-| 苹果 | 红色 | 1.2 |
-| 香蕉 | 黄色 | 0.5 |
-| 橙子 | 橙色 | 0.8 |
-| 草莓 | 红色 | 2.5 |
-| 蓝莓 | 蓝色 | 3.0 |
-| 猕猴桃 | 绿色 | 1.0 |
-| 芒果 | 橙色 | 1.5 |
-| 葡萄 | 紫色 | 2.00 |
+| 水果，颜色，价格（美元） |
+| --- |
+| 苹果，红色，1.2 |
+| 香蕉，黄色，0.5 |
+| 橙子，橙色，0.8 |
+| 草莓，红色，2.5 |
+| 蓝莓，蓝色，3.0 |
+| 猕猴桃，绿色，1.0 |
+| 芒果，橙色，1.5 |
+| 葡萄，紫色，2.00 |
 
 ---
 
diff --git a/openai-translator/.idea/.gitignore b/openai-translator/.idea/.gitignore
diff --git a/openai-translator/.idea/inspectionProfiles/Project_Default.xml b/openai-translator/.idea/inspectionProfiles/Project_Default.xml
diff --git a/openai-translator/.idea/inspectionProfiles/profiles_settings.xml b/openai-translator/.idea/inspectionProfiles/profiles_settings.xml
diff --git a/openai-translator/.idea/misc.xml b/openai-translator/.idea/misc.xml
diff --git a/openai-translator/.idea/modules.xml b/openai-translator/.idea/modules.xml
diff --git a/openai-translator/.idea/openai-translator.iml b/openai-translator/.idea/openai-translator.iml
diff --git a/openai-translator/.idea/vcs.xml b/openai-translator/.idea/vcs.xml
diff --git a/openai-translator/ai_translator/.idea/.gitignore b/openai-translator/ai_translator/.idea/.gitignore
diff --git a/openai-translator/ai_translator/book/content.py b/openai-translator/ai_translator/book/content.py
@@ -26,7 +26,7 @@ def check_translation_type(self, translation):
             return True
         elif self.content_type == ContentType.TABLE and isinstance(translation, list):
             return True
-        elif self.content_type == ContentType.IMAGE and isinstance(translation, PILImage.Image):
+        elif self.content_type == ContentType.IMAGE and isinstance(translation, str):
             return True
         return False
 
@@ -47,13 +47,14 @@ def set_translation(self, translation, status):
                 raise ValueError(f"Invalid translation type. Expected str, but got {type(translation)}")
 
             LOG.debug(translation)
+            LOG.warning(type(translation))
             # Convert the string to a list of lists
             table_data = [row.strip().split() for row in translation.strip().split('\n')]
             LOG.debug(table_data)
             # Create a DataFrame from the table_data
-            translated_df = pd.DataFrame(table_data[1:], columns=table_data[0])
-            LOG.debug(translated_df)
-            self.translation = translated_df
+            #translated_df = pd.DataFrame(table_data[1:], columns=table_data[0])
+            #LOG.debug(translated_df)
+            self.translation = translation#translated_df
             self.status = status
         except Exception as e:
             LOG.error(f"An error occurred during table translation: {e}")

diff --git a/openai-translator/ai_translator/config.yaml b/openai-translator/ai_translator/config.yaml
@@ -0,0 +1,13 @@
+OpenAIModel:
+  model: "gpt-3.5-turbo"
+  api_key: "your_openai_api_key"
+
+GLMModel:
+  model_url: "gpt-3.5-turbo"
+  timeout: 300
+
+common:
+  book: "tests/test.pdf"
+  file_format: "markdown"
+  pre_name_write: "tests/img/"
+  pre_name_read: "img/"
diff --git a/openai-translator/ai_translator/flask_server.py b/openai-translator/ai_translator/flask_server.py
@@ -0,0 +1,115 @@
+import sys
+import os
+from argparse import Namespace
+
+from model import OpenAIModel
+
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+
+from flask import Flask, request, send_file, jsonify
+from utils import ArgumentParser, LOG, ConfigLoader
+from translator import PDFTranslator
+
+app = Flask(__name__)
+
+TEMP_FILE_DIR = "flask_temps/"
+
+@app.route('/translate', methods=['POST'])
+def translate():
+    try:
+        #input_file = request.files['input_file']
+        source_text = request.form.get['source_text', 'source_text']
+        source_language = request.form.get('source_language', 'English')
+        target_language = request.form.get('target_language', 'Chinese')
+
+        translation_text = Translator.translate_to_text(source_text=source_text, target_language=target_language)
+        response = {
+            'status': 'success',
+            'message': translation_text
+        }
+        return jsonify(response), 200
+
+    except Exception as e:
+        response = {
+            'status': 'error',
+            'message': str(e)
+        }
+        return jsonify(response), 400
+
+@app.route('/translation', methods=['POST'])
+def translation():
+    try:
+        input_file = request.files['input_file']
+        source_language = request.form.get('source_language', 'English')
+        target_language = request.form.get('target_language', 'Chinese')
+
+        LOG.debug(f"[input_file]\n{input_file}")
+        LOG.debug(f"[input_file.filename]\n{input_file.filename}")
+
+        if input_file and input_file.filename:
+            # # 创建临时文件
+            input_file_path = TEMP_FILE_DIR + input_file.filename
+            LOG.debug(f"[input_file_path]\n{input_file_path}")
+
+            input_file.save(input_file_path)
+
+            # 调用翻译函数
+            output_file_path = Translator.translate_pdf(
+                input_file=input_file_path,
+                source_language=source_language,
+                target_language=target_language)
+
+            # 移除临时文件
+            # os.remove(input_file_path)
+
+            # 构造完整的文件路径
+            output_file_path = os.getcwd() + "/" + output_file_path
+            LOG.debug(output_file_path)
+
+            # 返回翻译后的文件
+            return send_file(output_file_path, as_attachment=True)
+    except Exception as e:
+        response = {
+            'status': 'error',
+            'message': str(e)
+        }
+        return jsonify(response), 400
+
+
+
+def initialize_translator():
+    # 解析命令行
+    # argument_parser = ArgumentParser()
+    # args = argument_parser.parse_arguments()
+
+    args = Namespace(config='config.yaml', model_type='OpenAIModel', glm_model_url=None, timeout=None,
+                     openai_model='gpt-3.5-turbo', openai_api_key=None, book='tests/test.pdf', file_format='markdown',
+                     pre_name_write='tests/img/', pre_name_read='img/')
+
+    config_loader = ConfigLoader(args.config)
+
+    config = config_loader.load_config()
+
+    model_name = args.openai_model if args.openai_model else config['OpenAIModel']['model']
+    api_key = args.openai_api_key if args.openai_api_key else config['OpenAIModel']['api_key']
+    model = OpenAIModel(model=model_name, api_key=api_key)
+
+    pdf_file_path = args.book if args.book else config['common']['book']
+    global file_format
+    file_format = args.file_format if args.file_format else config['common']['file_format']
+
+    global pre_name_write
+    pre_name_write = args.pre_name_write if args.pre_name_write else config['common']['pre_name_write']
+    global pre_name_read
+    pre_name_read = args.pre_name_read if args.pre_name_read else config['common']['pre_name_read']
+
+    # 实例化 PDFTranslator 类，并调用 translate_pdf() 方法
+    global Translator
+    Translator = PDFTranslator(model)
+
+
+if __name__ == "__main__":
+    # 初始化 translator
+    initialize_translator()
+    # 启动 Flask Web Server
+    app.run(host="0.0.0.0", port=5000, debug=True)
diff --git a/openai-translator/ai_translator/gradio_server.py b/openai-translator/ai_translator/gradio_server.py
@@ -0,0 +1,70 @@
+import sys
+import os
+from argparse import Namespace
+
+import gradio as gr
+
+from model import OpenAIModel
+
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+
+from utils import ArgumentParser, LOG, ConfigLoader
+from translator import PDFTranslator
+
+def translation(input_file, source_language, target_language):
+    LOG.debug(f"[翻译任务]\n源文件:{input_file.name}\n源语言:{source_language}\n目标语言:{target_language}")
+
+    output_file_path = Translator.translate_pdf(input_file.name, pre_name_write, pre_name_read, file_format)
+
+    LOG.info(f"返回路径： {output_file_path}")
+    return output_file_path
+
+def launcher_gradio():
+    iface = gr.Interface(
+        fn=translation,
+        title="OpenAI-Translator v1.0(PDF电子书翻译工具)",
+        inputs=[
+            gr.File(label="上传PDF文件"),
+            gr.Textbox(label="源语言(默认：英文)", placeholder="English", value="English"),
+            gr.Textbox(label="目标语言(默认:中文)", placeholder="Chinese", value="Chinese")
+        ],
+        outputs=[
+            gr.File(label="下载翻译文件")
+        ]
+    )
+    iface.launch(share=True, server_name="0.0.0.0", server_port=10001)
+
+def initialize_translator():
+    #argument_parser = ArgumentParser()
+    #args = argument_parser.parse_arguments()
+
+    args = Namespace(config='config.yaml', model_type='OpenAIModel', glm_model_url=None, timeout=None,
+                     openai_model='gpt-3.5-turbo', openai_api_key=None, book='tests/test.pdf', file_format='markdown',
+                     pre_name_write='tests/img/', pre_name_read='img/')
+
+    config_loader = ConfigLoader(args.config)
+
+    config = config_loader.load_config()
+
+    model_name = args.openai_model if args.openai_model else config['OpenAIModel']['model']
+    api_key = args.openai_api_key if args.openai_api_key else config['OpenAIModel']['api_key']
+    model = OpenAIModel(model=model_name, api_key=api_key)
+
+    pdf_file_path = args.book if args.book else config['common']['book']
+    global file_format
+    file_format = args.file_format if args.file_format else config['common']['file_format']
+
+    global pre_name_write
+    pre_name_write = args.pre_name_write if args.pre_name_write else config['common']['pre_name_write']
+    global pre_name_read
+    pre_name_read = args.pre_name_read if args.pre_name_read else config['common']['pre_name_read']
+
+    # 实例化 PDFTranslator 类，并调用 translate_pdf() 方法
+    global Translator
+    Translator = PDFTranslator(model)
+   # translator.translate_pdf(pdf_file_path, pre_name_write, pre_name_read, file_format)
+
+
+if __name__ == "__main__":
+    initialize_translator()
+    launcher_gradio()
diff --git a/openai-translator/ai_translator/main.py b/openai-translator/ai_translator/main.py
@@ -1,5 +1,6 @@
 import sys
 import os
+from argparse import Namespace
 
 sys.path.append(os.path.dirname(os.path.abspath(__file__)))
 
@@ -8,8 +9,12 @@
 from translator import PDFTranslator
 
 if __name__ == "__main__":
-    argument_parser = ArgumentParser()
-    args = argument_parser.parse_arguments()
+    #argument_parser = ArgumentParser()
+    #args = argument_parser.parse_arguments()
+
+    args = Namespace(config='config.yaml', model_type='OpenAIModel', glm_model_url=None, timeout=None,
+              openai_model='gpt-3.5-turbo', openai_api_key=None, book='tests/test.pdf', file_format='markdown', pre_name_write='tests/img/', pre_name_read='img/')
+    print(f"args = {args}")
     config_loader = ConfigLoader(args.config)
 
     config = config_loader.load_config()
@@ -22,6 +27,9 @@
     pdf_file_path = args.book if args.book else config['common']['book']
     file_format = args.file_format if args.file_format else config['common']['file_format']
 
+    pre_name_write = args.pre_name_write if args.pre_name_write else config['common']['pre_name_write']
+    pre_name_read = args.pre_name_read if args.pre_name_read else config['common']['pre_name_read']
+
     # 实例化 PDFTranslator 类，并调用 translate_pdf() 方法
     translator = PDFTranslator(model)
-    translator.translate_pdf(pdf_file_path, file_format)
+    translator.translate_pdf(pdf_file_path, pre_name_write, pre_name_read, file_format)
diff --git a/openai-translator/ai_translator/model/model.py b/openai-translator/ai_translator/model/model.py
@@ -5,7 +5,7 @@ def make_text_prompt(self, text: str, target_language: str) -> str:
         return f"翻译为{target_language}：{text}"
 
     def make_table_prompt(self, table: str, target_language: str) -> str:
-        return f"翻译为{target_language}，保持间距（空格，分隔符），以表格形式返回：\n{table}"
+        return f"所有单词翻译为{target_language}，保持间距（空格，分隔符），以表格形式返回：\n{table}"
 
     def translate_prompt(self, content, target_language: str) -> str:
         if content.content_type == ContentType.TEXT:

diff --git a/openai-translator/ai_translator/tests/The_Old_Man_of_the_Sea.pdf b/openai-translator/ai_translator/tests/The_Old_Man_of_the_Sea.pdf
diff --git a/openai-translator/ai_translator/tests/img/pdf_img0.png b/openai-translator/ai_translator/tests/img/pdf_img0.png
diff --git a/openai-translator/ai_translator/tests/test.pdf b/openai-translator/ai_translator/tests/test.pdf
diff --git a/openai-translator/ai_translator/tests/test_translated.md b/openai-translator/ai_translator/tests/test_translated.md
@@ -0,0 +1,18 @@
+测试数据
+这个数据集包含了由OpenAI的AI语言模型ChatGPT提供的两个测试样本。
+这些样本包括一个markdown表格和一个英文文本段落，可以用来测试支持文本和表格格式的英译中翻译软件。
+文本测试
+快速的棕色狐狸跳过了懒惰的狗。这个全字母句包含了英语字母表中的每一个字母。全字母句经常用来测试字体、键盘和其他与文本有关的工具。除了英语，还有许多其他语言的全字母句。一些全字母句由于语言的独特特点更难构建。
+表格测试
+
+水果     颜色    价格(美元) 
+苹果     红色    1.20 
+香蕉     黄色    0.50 
+橙子     橙色    0.80 
+草莓     红色    2.50 
+蓝莓     蓝色    3.00 
+奇异果   绿色    1.00 
+芒果     橙色    1.50 
+葡萄     紫色    2.00
+
+![img/pdf_img0.png](img/pdf_img0.png)
diff --git a/openai-translator/ai_translator/translator/pdf_parser.py b/openai-translator/ai_translator/translator/pdf_parser.py
@@ -9,7 +9,7 @@ class PDFParser:
     def __init__(self):
         pass
 
-    def parse_pdf(self, pdf_file_path: str, pages: Optional[int] = None) -> Book:
+    def parse_pdf(self, pdf_file_path: str, pre_name_write: str, pages: Optional[int] = None) -> Book:
         book = Book(pdf_file_path)
 
         with pdfplumber.open(pdf_file_path) as pdf:
@@ -27,6 +27,10 @@ def parse_pdf(self, pdf_file_path: str, pages: Optional[int] = None) -> Book:
                 # Store the original text content
                 raw_text = pdf_page.extract_text()
                 tables = pdf_page.extract_tables()
+                imgs = pdf_page.images
+
+
+
 
                 # Remove each cell's content from the original text
                 for table_data in tables:
@@ -45,6 +49,16 @@ def parse_pdf(self, pdf_file_path: str, pages: Optional[int] = None) -> Book:
                     page.add_content(text_content)
                     LOG.debug(f"[raw_text]\n {cleaned_raw_text}")
 
+                if imgs:
+                    for img in imgs:
+                        bbox = (img["x0"], img["top"], img["x1"], img["bottom"])
+                        cropped_page = pdf_page.crop(bbox)
+                        im = cropped_page.to_image(antialias=True)
+                        imgName = "pdf_img0.png"
+                        im.save(f"{pre_name_write}pdf_img0.png")
+                        img_content = Content(content_type=ContentType.IMAGE, original=imgName, translation=imgName)
+                        page.add_content(img_content)
+                        LOG.debug(f"[image]\n{img_content.translation}")
 
 
                 # Handling tables
@@ -55,4 +69,5 @@ def parse_pdf(self, pdf_file_path: str, pages: Optional[int] = None) -> Book:
 
                 book.add_page(page)
 
+
         return book
diff --git a/openai-translator/ai_translator/translator/pdf_translator.py b/openai-translator/ai_translator/translator/pdf_translator.py
@@ -3,24 +3,40 @@
 from translator.pdf_parser import PDFParser
 from translator.writer import Writer
 from utils import LOG
+from book import ContentType
+
 
 class PDFTranslator:
     def __init__(self, model: Model):
         self.model = model
         self.pdf_parser = PDFParser()
         self.writer = Writer()
 
-    def translate_pdf(self, pdf_file_path: str, file_format: str = 'PDF', target_language: str = '中文', output_file_path: str = None, pages: Optional[int] = None):
-        self.book = self.pdf_parser.parse_pdf(pdf_file_path, pages)
+    def translate_pdf(self, pdf_file_path: str, pre_name_write: str, pre_name_read: str,file_format: str = 'PDF',target_language: str = '中文', output_file_path: str = None, pages: Optional[int] = None):
+        self.book = self.pdf_parser.parse_pdf(pdf_file_path, pre_name_write, pages)
 
+        LOG.debug(self.book.pages)
         for page_idx, page in enumerate(self.book.pages):
             for content_idx, content in enumerate(page.contents):
-                prompt = self.model.translate_prompt(content, target_language)
-                LOG.debug(prompt)
-                translation, status = self.model.make_request(prompt)
-                LOG.info(translation)
+                if content.content_type != ContentType.IMAGE:
+                    prompt = self.model.translate_prompt(content, target_language)
+                    LOG.debug(prompt)
+                    translation, status = self.model.make_request(prompt)
+                    LOG.info(translation)
+
+                    # Update the content in self.book.pages directly
+                    self.book.pages[page_idx].contents[content_idx].set_translation(translation, status)
+                elif content.content_type == ContentType.IMAGE:
+                    translation, status = content.translation, True
+                    self.book.pages[page_idx].contents[content_idx].set_translation(translation, status)
 
-                # Update the content in self.book.pages directly
-                self.book.pages[page_idx].contents[content_idx].set_translation(translation, status)
 
-        self.writer.save_translated_book(self.book, output_file_path, file_format)
+
+        output_file_path = self.writer.save_translated_book(self.book, pre_name_read, output_file_path, file_format)
+        return output_file_path
+
+    def translate_to_text(self, source_text: str, target_language: str) -> str:
+        prompt = self.model.translate_prompt(source_text, target_language)
+        LOG.debug(prompt)
+        translation, status = self.model.make_request(prompt)
+        return translation
diff --git a/openai-translator/ai_translator/translator/writer.py b/openai-translator/ai_translator/translator/writer.py
@@ -6,6 +6,7 @@
 from reportlab.platypus import (
     SimpleDocTemplate, Paragraph, Spacer, Table, TableStyle, PageBreak
 )
+import pandas as pd
 
 from book import Book, ContentType
 from utils import LOG
@@ -14,14 +15,16 @@ class Writer:
     def __init__(self):
         pass
 
-    def save_translated_book(self, book: Book, output_file_path: str = None, file_format: str = "PDF"):
+    def save_translated_book(self, book: Book, pre_name_read: str,output_file_path: str = None, file_format: str = "PDF"):
         if file_format.lower() == "pdf":
-            self._save_translated_book_pdf(book, output_file_path)
+            output_file_path = self._save_translated_book_pdf(book, output_file_path)
         elif file_format.lower() == "markdown":
-            self._save_translated_book_markdown(book, output_file_path)
+            output_file_path = self._save_translated_book_markdown(book, pre_name_read, output_file_path)
         else:
             raise ValueError(f"Unsupported file format: {file_format}")
 
+        return output_file_path
+
     def _save_translated_book_pdf(self, book: Book, output_file_path: str = None):
         if output_file_path is None:
             output_file_path = book.pdf_file_path.replace('.pdf', f'_translated.pdf')
@@ -76,7 +79,7 @@ def _save_translated_book_pdf(self, book: Book, output_file_path: str = None):
         doc.build(story)
         LOG.info(f"翻译完成: {output_file_path}")
 
-    def _save_translated_book_markdown(self, book: Book, output_file_path: str = None):
+    def _save_translated_book_markdown(self, book: Book, pre_name_read: str, output_file_path: str = None):
         if output_file_path is None:
             output_file_path = book.pdf_file_path.replace('.pdf', f'_translated.md')
 
@@ -95,14 +98,31 @@ def _save_translated_book_markdown(self, book: Book, output_file_path: str = Non
                         elif content.content_type == ContentType.TABLE:
                             # Add table to the Markdown file
                             table = content.translation
+                            #df = pd.DataFrame(table)
+                            #markdown_table = table.to_markdown()
+                            output_file.write(table + '\n\n')
+                            '''
+                            LOG.warning(table)
                             header = '| ' + ' | '.join(str(column) for column in table.columns) + ' |' + '\n'
                             separator = '| ' + ' | '.join(['---'] * len(table.columns)) + ' |' + '\n'
                             # body = '\n'.join(['| ' + ' | '.join(row) + ' |' for row in table.values.tolist()]) + '\n\n'
                             body = '\n'.join(['| ' + ' | '.join(str(cell) for cell in row) + ' |' for row in table.values.tolist()]) + '\n\n'
+                            LOG.warning(body)
                             output_file.write(header + separator + body)
+                            '''
+                        elif content.content_type == ContentType.IMAGE:
+                            LOG.debug( content.translation )
+                            image = pre_name_read + content.translation
+                            markdown_text = f"![{image}]({image})"
+                            LOG.debug(image)
+                            LOG.debug(markdown_text)
+                            output_file.write(markdown_text)
+
+
 
                 # Add a page break (horizontal rule) after each page except the last one
-                if page != book.pages[-1]:
-                    output_file.write('---\n\n')
+                #if page != book.pages[-1]:
+                #    output_file.write('---\n\n')
 
-        LOG.info(f"翻译完成: {output_file_path}")
+        LOG.info(f"翻译完成: {output_file_path}")
+        return output_file_path
diff --git a/openai-translator/requirements.txt b/openai-translator/requirements.txt
@@ -1,9 +1,15 @@
-openai==1.14.2
-pdfplumber
-simplejson
-requests
-PyYAML
-pillow
-reportlab
-pandas
-loguru
+openai==1.20.0
+langchain==0.1.13
+langchain-openai==0.1.1
+langchain-experimental==0.0.55
+chromadb==0.4.24
+faiss-cpu==1.8.0
+gradio==4.20.0
+unstructured==0.12.6
+google-search-results==2.4.2
+tiktoken==0.6.0
+matplotlib
+plotly
+numpy
+scikit-learn
+pandas
diff --git a/requeirmentsT b/requeirmentsT
@@ -0,0 +1,15 @@
+openai==1.14.2
+langchain==0.1.13
+langchain-openai==0.1.1
+langchain-experimental==0.0.55
+chromadb==0.4.24
+faiss-cpu==1.8.0
+gradio==4.20.0
+unstructured==0.12.6
+google-search-results==2.4.2
+tiktoken==0.6.0
+matplotlib
+plotly
+numpy
+scikit-learn
+pandas
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		China won 103 gold medals at the 2023 Chengdu Universiade.