[{"data":1,"prerenderedAt":803},["ShallowReactive",2],{"navigation":3,"\u002Fllm\u002Flangchain2":144,"\u002Fllm\u002Flangchain2-surround":798},[4,36,53,86,131],{"title":5,"path":6,"stem":7,"children":8,"icon":35},"Golang","\u002Fgolang","1.golang\u002F1.index",[9,11,15,19,23,27,31],{"title":10,"path":6,"stem":7},"golang-各种golang学习以及使用过程中记录",{"title":12,"path":13,"stem":14},"gopls-官方gopls内置mcp server的基本使用","\u002Fgolang\u002Fgopls_mcp_usages","1.golang\u002F2.gopls_mcp_usages",{"title":16,"path":17,"stem":18},"实践-(一)创建简单的http服务器","\u002Fgolang\u002Fgo_http_simple_server","1.golang\u002F3.go_http_simple_server",{"title":20,"path":21,"stem":22},"wails入门系列(一)环境安装与demo","\u002Fgolang\u002Fwails_start","1.golang\u002F4.wails_start",{"title":24,"path":25,"stem":26},"wails入门系列(二)无边框应用的菜单栏以及窗口拖拽","\u002Fgolang\u002Fwails_frameless","1.golang\u002F5.wails_frameless",{"title":28,"path":29,"stem":30},"go\u002Fredis-redis中大数字自动转换成指数形式的处理","\u002Fgolang\u002Fredis_big_num","1.golang\u002F6.redis_big_num",{"title":32,"path":33,"stem":34},"go\u002F方法记录-局部坐标与世界坐标间的相互转换(位置\u002F方向)","\u002Fgolang\u002Fworld_local_transform","1.golang\u002F7.world_local_transform",false,{"title":37,"icon":35,"path":38,"stem":39,"children":40,"page":35},"瞎折腾","\u002Ftinkering","2.tinkering",[41,45,49],{"title":42,"path":43,"stem":44},"mi50显卡ubuntu运行大模型开坑(一)显卡准备以及驱动安装","\u002Ftinkering\u002Fmi50_gpu_llm_1","2.tinkering\u002F1.mi50_gpu_llm_1",{"title":46,"path":47,"stem":48},"mi50显卡ubuntu运行大模型开坑(二)使用llama.cpp部署Qwen3系列","\u002Ftinkering\u002Fmi50_gpu_llm_2","2.tinkering\u002F2.mi50_gpu_llm_2",{"title":50,"path":51,"stem":52},"mi50显卡ubuntu运行大模型开坑(三)安装风扇并且控制转速","\u002Ftinkering\u002Fmi50_gpu_llm_3","2.tinkering\u002F3.mi50_gpu_llm_3",{"title":54,"icon":35,"path":55,"stem":56,"children":57,"page":35},"LLM","\u002Fllm","3.llm",[58,62,66,70,74,78,82],{"title":59,"path":60,"stem":61},"langchain入门-安装以及初次使用(deepseek api版本)","\u002Fllm\u002Flangchain1","3.llm\u002F01.langchain1",{"title":63,"path":64,"stem":65},"langchain入门-使用langchain调用本地部署的大模型(以llama.cpp以及ollama为例)","\u002Fllm\u002Flangchain2","3.llm\u002F02.langchain2",{"title":67,"path":68,"stem":69},"langchain入门-使用langchain编写一个简单的聊天机器人(DeepSeek API&命令行版本)","\u002Fllm\u002Flangchain3","3.llm\u002F03.langchain3",{"title":71,"path":72,"stem":73},"langchain入门-使用langchain构建一个拥有RAG能力的代码问答应用(DeepSeek API&本地bge-m3&命令行版本)","\u002Fllm\u002Flangchain4","3.llm\u002F04.langchain4",{"title":75,"path":76,"stem":77},"golang\u002Feino eino框架的基础使用 Message以及ChatModel入门","\u002Fllm\u002Feino1","3.llm\u002F05.eino1",{"title":79,"path":80,"stem":81},"golang\u002Feino eino框架的基础使用 在ChatModel中使用工具","\u002Fllm\u002Feino2","3.llm\u002F06.eino2",{"title":83,"path":84,"stem":85},"llm\u002Fagent agent-zero初步搭建与使用","\u002Fllm\u002Fagent_zero_start","3.llm\u002F07.agent_zero_start",{"title":87,"icon":35,"path":88,"stem":89,"children":90,"page":35},"Verilog","\u002Fverilog","4.verilog",[91,95,99,103,107,111,115,119,123,127],{"title":92,"path":93,"stem":94},"31条指令单周期cpu设计(Verilog)-(一)相关软件","\u002Fverilog\u002Fmips1","4.verilog\u002F01.mips1",{"title":96,"path":97,"stem":98},"31条指令单周期cpu设计(Verilog)-(二)总体设计","\u002Fverilog\u002Fmips2","4.verilog\u002F02.mips2",{"title":100,"path":101,"stem":102},"31条指令单周期cpu设计(Verilog)-(三)指令分析","\u002Fverilog\u002Fmips3","4.verilog\u002F03.mips3",{"title":104,"path":105,"stem":106},"31条指令单周期cpu设计(Verilog)-(四)数据输入输出关系表","\u002Fverilog\u002Fmips4","4.verilog\u002F04.mips4",{"title":108,"path":109,"stem":110},"31条指令单周期cpu设计(Verilog)-(五)整体数据通路图设计","\u002Fverilog\u002Fmips5","4.verilog\u002F05.mips5",{"title":112,"path":113,"stem":114},"31条指令单周期cpu设计(Verilog)-(六)指令操作时间表设计","\u002Fverilog\u002Fmips6","4.verilog\u002F06.mips6",{"title":116,"path":117,"stem":118},"31条指令单周期cpu设计(Verilog)-(七)整体代码结构","\u002Fverilog\u002Fmips7","4.verilog\u002F07.mips7",{"title":120,"path":121,"stem":122},"31条指令单周期cpu设计(Verilog)-(八)上代码→指令译码以及控制器","\u002Fverilog\u002Fmips8","4.verilog\u002F08.mips8",{"title":124,"path":125,"stem":126},"31条指令单周期cpu设计(Verilog)-(九)上代码→基础模块实现","\u002Fverilog\u002Fmips9","4.verilog\u002F09.mips9",{"title":128,"path":129,"stem":130},"31条指令单周期cpu设计(Verilog)-(十)上代码→顶层模块设计&总结","\u002Fverilog\u002Fmips10","4.verilog\u002F10.mips10",{"title":132,"icon":35,"path":133,"stem":134,"children":135,"page":35},"Rust","\u002Frust","5.rust",[136,140],{"title":137,"path":138,"stem":139},"egui(一)从编译运行template开始","\u002Frust\u002Fegui1","5.rust\u002F01.egui1",{"title":141,"path":142,"stem":143},"egui(二)看看template的main函数：日志输出以及eframe run_native","\u002Frust\u002Fegui2","5.rust\u002F02.egui2",{"id":145,"title":63,"body":146,"description":790,"extension":791,"links":792,"meta":793,"navigation":287,"path":64,"seo":794,"stem":65,"__hash__":797},"docs\u002F3.llm\u002F02.langchain2.md",{"type":147,"value":148,"toc":779},"minimark",[149,153,178,182,186,315,318,471,475,478,621,624,775],[150,151,152],"h2",{"id":152},"说在前面",[154,155,156],"blockquote",{},[157,158,159,163,166,169,172,175],"ul",{},[160,161,162],"li",{},"操作系统：windows",[160,164,165],{},"python版本：3.9",[160,167,168],{},"langchain版本：0.3.20",[160,170,171],{},"pycharm版本：2023.1.2 (Community Edition)",[160,173,174],{},"ollama版本：0.5.4",[160,176,177],{},"llama.cpp版本：b4870",[150,179,181],{"id":180},"ollamaqwen25-coder7b","ollama(qwen2.5-coder:7b)",[183,184,185],"h3",{"id":185},"部署模型",[157,187,188,211,218,245],{},[160,189,190,194,195,202,203],{},[191,192,193],"code",{},"ollama","部署大模型比较简单，到",[196,197,201],"a",{"href":198,"rel":199},"https:\u002F\u002Follama.com\u002F",[200],"nofollow","官网","下载安装包后安装",[204,205],"img",{"alt":206,"src":207,"className":208},"ollama安装",".\u002Fllm\u002F4.webp",[209,210],"block","mx-auto",[160,212,213,214],{},"根据自己电脑的条件选择合适的模型，比如\n",[204,215],{"alt":216,"src":217},"choose_model",".\u002Fllm\u002F5.webp",[160,219,220,221],{},"然后打开命令行，执行",[222,223,228],"pre",{"className":224,"code":225,"language":226,"meta":227,"style":227},"language-shell shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","ollama run qwen2.5-coder\n","shell","",[191,229,230],{"__ignoreMap":227},[231,232,235,238,242],"span",{"class":233,"line":234},"line",1,[231,236,193],{"class":237},"sBMFI",[231,239,241],{"class":240},"sfazB"," run",[231,243,244],{"class":240}," qwen2.5-coder\n",[160,246,247,248],{},"然后就可以直接在命令行对话了",[222,249,251],{"className":224,"code":250,"language":226,"meta":227,"style":227},"$ ollama run qwen2.5-coder:latest\n>>> 你好\n你好！有什么我可以帮忙的吗？\n\n>>> Send a message (\u002F? for help)\n",[191,252,253,266,276,282,289],{"__ignoreMap":227},[231,254,255,258,261,263],{"class":233,"line":234},[231,256,257],{"class":237},"$",[231,259,260],{"class":240}," ollama",[231,262,241],{"class":240},[231,264,265],{"class":240}," qwen2.5-coder:latest\n",[231,267,269,273],{"class":233,"line":268},2,[231,270,272],{"class":271},"sTEyZ",">>> ",[231,274,275],{"class":237},"你好\n",[231,277,279],{"class":233,"line":278},3,[231,280,281],{"class":237},"你好！有什么我可以帮忙的吗？\n",[231,283,285],{"class":233,"line":284},4,[231,286,288],{"emptyLinePlaceholder":287},true,"\n",[231,290,292,294,297,300,303,306,309,312],{"class":233,"line":291},5,[231,293,272],{"class":271},[231,295,296],{"class":237},"Send",[231,298,299],{"class":240}," a",[231,301,302],{"class":240}," message",[231,304,305],{"class":271}," (\u002F? ",[231,307,308],{"class":240},"for",[231,310,311],{"class":240}," help",[231,313,314],{"class":271},")\n",[183,316,317],{"id":317},"使用langchain",[157,319,320,339],{},[160,321,322,323],{},"langchain提供了直接调用ollama api的package，安装后直接使用即可\n",[222,324,326],{"className":224,"code":325,"language":226,"meta":227,"style":227},"pip install langchain-ollama\n",[191,327,328],{"__ignoreMap":227},[231,329,330,333,336],{"class":233,"line":234},[231,331,332],{"class":237},"pip",[231,334,335],{"class":240}," install",[231,337,338],{"class":240}," langchain-ollama\n",[160,340,341,342,415,416],{},"代码环节\n",[222,343,345],{"className":224,"code":344,"language":226,"meta":227,"style":227},"from langchain_ollama import OllamaLLM\n\nollm = OllamaLLM(model=\"qwen2.5-coder:latest\")\nprint(ollm.invoke(\"你好\"))\n",[191,346,347,361,365,396],{"__ignoreMap":227},[231,348,349,352,355,358],{"class":233,"line":234},[231,350,351],{"class":237},"from",[231,353,354],{"class":240}," langchain_ollama",[231,356,357],{"class":240}," import",[231,359,360],{"class":240}," OllamaLLM\n",[231,362,363],{"class":233,"line":268},[231,364,288],{"emptyLinePlaceholder":287},[231,366,367,370,373,376,380,383,386,389,392,394],{"class":233,"line":278},[231,368,369],{"class":237},"ollm",[231,371,372],{"class":240}," =",[231,374,375],{"class":240}," OllamaLLM",[231,377,379],{"class":378},"sMK4o","(",[231,381,382],{"class":271},"model",[231,384,385],{"class":378},"=",[231,387,388],{"class":378},"\"",[231,390,391],{"class":240},"qwen2.5-coder:latest",[231,393,388],{"class":378},[231,395,314],{"class":378},[231,397,398,402,404,407,409,412],{"class":233,"line":284},[231,399,401],{"class":400},"s2Zo4","print",[231,403,379],{"class":271},[231,405,406],{"class":240},"ollm.invoke",[231,408,379],{"class":271},[231,410,411],{"class":237},"\"你好\"",[231,413,414],{"class":271},"))\n","\n运行\n",[222,417,419],{"className":224,"code":418,"language":226,"meta":227,"style":227},"(venv) PS D:\\Code\\langchain> python .\\main.py\n你好！有什么我可以帮忙的吗？\n",[191,420,421,467],{"__ignoreMap":227},[231,422,423,425,428,431,434,437,440,443,446,449,452,455,458,461,464],{"class":233,"line":234},[231,424,379],{"class":378},[231,426,427],{"class":237},"venv",[231,429,430],{"class":378},")",[231,432,433],{"class":237}," PS",[231,435,436],{"class":240}," D:",[231,438,439],{"class":271},"\\C",[231,441,442],{"class":240},"ode",[231,444,445],{"class":271},"\\l",[231,447,448],{"class":240},"angchai",[231,450,451],{"class":271},"n",[231,453,454],{"class":378},">",[231,456,457],{"class":240}," python",[231,459,460],{"class":240}," .",[231,462,463],{"class":271},"\\m",[231,465,466],{"class":240},"ain.py\n",[231,468,469],{"class":233,"line":268},[231,470,281],{"class":237},[150,472,474],{"id":473},"llamacppdeepseek-r115b","llama.cpp(deepseek-r1:1.5b)",[183,476,477],{"id":477},"模型部署",[157,479,480,483,496,521,528,584],{},[160,481,482],{},"算力不足，搞个1.5b测试吧",[160,484,485,486,491,492],{},"llama.cpp部署也挺简单的，到",[196,487,490],{"href":488,"rel":489},"https:\u002F\u002Fgithub.com\u002Fggml-org\u002Fllama.cpp\u002Freleases",[200],"github","选择合适的版本\n",[204,493],{"alt":494,"src":495},"在这里插入图片描述",".\u002Fllm\u002F6.webp",[160,497,498,499,502,503,506,507,510,511,514,515],{},"x64-windows-nvdia gpu\n下载",[191,500,501],{},"cudart-llama-bin-win-cuxx.x-x64.zip","以及",[191,504,505],{},"llama-b4870-bin-win-cuda-cuxx.x-x64.zip","，其中",[191,508,509],{},"cudart","是cuda相关的依赖，解压后将里面的文件放到",[191,512,513],{},"llama...zip","解压后的同级目录即可\n例如\n",[204,516],{"alt":206,"src":517,"className":518},".\u002Fllm\u002F7.webp",[519,520,209,210],"w-50","h-auto",[160,522,523,524,527],{},"mac-m4\n下载",[191,525,526],{},"llama-b4870-bin-macos-arm64.zip","解压即可",[160,529,530,531],{},"使用llama-client即可在命令行下进行交互，例如\n",[222,532,534],{"className":224,"code":533,"language":226,"meta":227,"style":227},".\u002Fllama-cli -m DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf\n> 你好\n\u003Cthink>\n\n\u003C\u002Fthink>\n你好！很高兴见到你，有什么我可以帮忙的吗？无论是聊天、解答问题还是提供建议，我都在这里为你服务。😊\n",[191,535,536,547,554,565,569,578],{"__ignoreMap":227},[231,537,538,541,544],{"class":233,"line":234},[231,539,540],{"class":237},".\u002Fllama-cli",[231,542,543],{"class":240}," -m",[231,545,546],{"class":240}," DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf\n",[231,548,549,551],{"class":233,"line":268},[231,550,454],{"class":378},[231,552,553],{"class":271}," 你好\n",[231,555,556,559,562],{"class":233,"line":278},[231,557,558],{"class":378},"\u003C",[231,560,561],{"class":271},"think",[231,563,564],{"class":378},">\n",[231,566,567],{"class":233,"line":284},[231,568,288],{"emptyLinePlaceholder":287},[231,570,571,573,576],{"class":233,"line":291},[231,572,558],{"class":378},[231,574,575],{"class":271},"\u002Fthink",[231,577,564],{"class":378},[231,579,581],{"class":233,"line":580},6,[231,582,583],{"class":237},"你好！很高兴见到你，有什么我可以帮忙的吗？无论是聊天、解答问题还是提供建议，我都在这里为你服务。😊\n",[160,585,586,587],{},"如果需要让langchain能够使用，需要部署服务，即使用llama-server\n",[222,588,590],{"className":224,"code":589,"language":226,"meta":227,"style":227},".\u002Fllama-sever -m DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf --port 50052 --host 0.0.0.0 -c 2048\n",[191,591,592],{"__ignoreMap":227},[231,593,594,597,599,602,605,609,612,615,618],{"class":233,"line":234},[231,595,596],{"class":237},".\u002Fllama-sever",[231,598,543],{"class":240},[231,600,601],{"class":240}," DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf",[231,603,604],{"class":240}," --port",[231,606,608],{"class":607},"sbssI"," 50052",[231,610,611],{"class":240}," --host",[231,613,614],{"class":607}," 0.0.0.0",[231,616,617],{"class":240}," -c",[231,619,620],{"class":607}," 2048\n",[183,622,317],{"id":623},"使用langchain-1",[157,625,626,654],{},[160,627,628,631,632,635,636,639,640],{},[191,629,630],{},"llama.cpp","部署的服务使用的API格式是与",[191,633,634],{},"openai","兼容的，所以在",[191,637,638],{},"langchain","中，我们可以使用openai对应的package\n",[222,641,643],{"className":224,"code":642,"language":226,"meta":227,"style":227},"pip install langchain-openai\n",[191,644,645],{"__ignoreMap":227},[231,646,647,649,651],{"class":233,"line":234},[231,648,332],{"class":237},[231,650,335],{"class":240},[231,652,653],{"class":240}," langchain-openai\n",[160,655,341,656,415,710],{},[222,657,661],{"className":658,"code":659,"language":660,"meta":227,"style":227},"language-python shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","from langchain_openai import ChatOpenAI\n\nllm = ChatOpenAI(max_tokens=None,\n                 timeout=None,\n                 openai_api_base=\"http:\u002F\u002F127.0.0.1:50052\",\n                 openai_api_key=\"none\")\n# openai_api_base 就是llama-server 部署时监听的地址\n# openai_api_key 必须要填 随便填就行 不能为 \"\"\nprint(llm.invoke(\"你好\").content)\n","python",[191,662,663,668,672,677,682,687,692,698,704],{"__ignoreMap":227},[231,664,665],{"class":233,"line":234},[231,666,667],{},"from langchain_openai import ChatOpenAI\n",[231,669,670],{"class":233,"line":268},[231,671,288],{"emptyLinePlaceholder":287},[231,673,674],{"class":233,"line":278},[231,675,676],{},"llm = ChatOpenAI(max_tokens=None,\n",[231,678,679],{"class":233,"line":284},[231,680,681],{},"                 timeout=None,\n",[231,683,684],{"class":233,"line":291},[231,685,686],{},"                 openai_api_base=\"http:\u002F\u002F127.0.0.1:50052\",\n",[231,688,689],{"class":233,"line":580},[231,690,691],{},"                 openai_api_key=\"none\")\n",[231,693,695],{"class":233,"line":694},7,[231,696,697],{},"# openai_api_base 就是llama-server 部署时监听的地址\n",[231,699,701],{"class":233,"line":700},8,[231,702,703],{},"# openai_api_key 必须要填 随便填就行 不能为 \"\"\n",[231,705,707],{"class":233,"line":706},9,[231,708,709],{},"print(llm.invoke(\"你好\").content)\n",[222,711,713],{"className":224,"code":712,"language":226,"meta":227,"style":227},"(venv) PS D:\\Code\\langchain> python .\\main.py\n\u003Cthink>\n\n\u003C\u002Fthink>\n\n你好！很高兴见到你，有什么我可以帮忙的吗？无论是聊天、解答问题还是提供建议，我都在这里为你服务。😊\n",[191,714,715,747,755,759,767,771],{"__ignoreMap":227},[231,716,717,719,721,723,725,727,729,731,733,735,737,739,741,743,745],{"class":233,"line":234},[231,718,379],{"class":378},[231,720,427],{"class":237},[231,722,430],{"class":378},[231,724,433],{"class":237},[231,726,436],{"class":240},[231,728,439],{"class":271},[231,730,442],{"class":240},[231,732,445],{"class":271},[231,734,448],{"class":240},[231,736,451],{"class":271},[231,738,454],{"class":378},[231,740,457],{"class":240},[231,742,460],{"class":240},[231,744,463],{"class":271},[231,746,466],{"class":240},[231,748,749,751,753],{"class":233,"line":268},[231,750,558],{"class":378},[231,752,561],{"class":271},[231,754,564],{"class":378},[231,756,757],{"class":233,"line":278},[231,758,288],{"emptyLinePlaceholder":287},[231,760,761,763,765],{"class":233,"line":284},[231,762,558],{"class":378},[231,764,575],{"class":271},[231,766,564],{"class":378},[231,768,769],{"class":233,"line":291},[231,770,288],{"emptyLinePlaceholder":287},[231,772,773],{"class":233,"line":580},[231,774,583],{"class":237},[776,777,778],"style",{},"html pre.shiki code .sBMFI, html code.shiki .sBMFI{--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B}html pre.shiki code .sfazB, html code.shiki .sfazB{--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D}html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html pre.shiki code .sTEyZ, html code.shiki .sTEyZ{--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8}html pre.shiki code .sMK4o, html code.shiki .sMK4o{--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF}html pre.shiki code .s2Zo4, html code.shiki .s2Zo4{--shiki-light:#6182B8;--shiki-default:#82AAFF;--shiki-dark:#82AAFF}html pre.shiki code .sbssI, html code.shiki .sbssI{--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C}",{"title":227,"searchDepth":234,"depth":268,"links":780},[781,782,786],{"id":152,"depth":268,"text":152},{"id":180,"depth":268,"text":181,"children":783},[784,785],{"id":185,"depth":278,"text":185},{"id":317,"depth":278,"text":317},{"id":473,"depth":268,"text":474,"children":787},[788,789],{"id":477,"depth":278,"text":477},{"id":623,"depth":278,"text":317},"详细介绍如何使用 Langchain 调用本地部署的大模型，包括 llama.cpp 和 Ollama 的配置方法、API 调用示例，以及常见问题解决方案。","md",null,{},{"title":795,"description":796},"【llm\u002Flangchain】langchain入门-使用langchain调用本地部署的大模型(以llama.cpp以及ollama为例)","详细介绍如何使用 Langchain 调用本地部署的大模型，包含 llama.cpp 和 Ollama 的安装配置、API 调用方法、以及本地大模型部署的完整流程，适合 Langchain 本地化部署学习。","Ub1uN3wJUHLjJRMFg8jBBgjO6IWUopRndlJAIRBlmCM",[799,801],{"title":59,"path":60,"stem":61,"description":800,"children":-1},"Langchain 入门教程，包含 Python 环境配置、DeepSeek API 集成、以及首次使用示例，适合初学者快速上手。",{"title":67,"path":68,"stem":69,"description":802,"children":-1},"使用 Langchain 构建命令行聊天机器人，介绍消息历史管理、LangGraph 持久化层（MemorySaver）、StateGraph 状态管理以及历史对话裁剪（trim_messages）优化方法。",1776616490416]