LangChain is a framework to build with LLMs by chaining interoperable components. LangGraph is the framework for building controllable agentic workflows.<\/p>\n
pip install langchain\npip install -qU langchain-openai<\/code><\/pre>\nexample 1<\/h3>\n<\/li>\n<\/ul>\n#!\/usr\/bin\/env python3\nfrom typing import List\nfrom langchain_openai import ChatOpenAI\nfrom langchain_core.output_parsers import StrOutputParser\nfrom langchain_core.prompts import ChatPromptTemplate\n\nimport os\nfrom dotenv import load_dotenv\nload_dotenv()\n\n#os.environ["LANGCHAIN_TRACING_V2"] = "true"\nos.environ["OPENAI_API_KEY"] = os.getenv("LLM_API_KEY")\nos.environ["USER_AGENT"] = "waltertest"\n#os.environ["LANGCHAIN_API_KEY"] = getpass.getpass()\n#os.environ["OPENAI_API_KEY"] = getpass.getpass()\n\nmodel = ChatOpenAI(\n model='deepseek-chat',\n openai_api_key=os.getenv("LLM_API_KEY"),\n openai_api_base=os.getenv("LLM_BASE_URL"),\n max_tokens=4096\n)\n\nsystem_template = "Translate the following into {language}:"\nprompt_template = ChatPromptTemplate.from_messages(\n [("system", system_template), ("user", "{text}")]\n)\n\nparser = StrOutputParser()\n\n#result = model.invoke(messages)\n#parser.invoke(result)\n#result = prompt_template.invoke({"language": "Chinese", "text": "hi"})\n\nchain = prompt_template | model | parser\n\nresult = chain.invoke({"language": "chinese", "text": "As you sow, so shall you reap"})\nprint(result)<\/code><\/pre>\n\u8f93\u51fa: \u79cd\u74dc\u5f97\u74dc\uff0c\u79cd\u8c46\u5f97\u8c46<\/p>\n
example 2<\/h3>\n#!\/usr\/bin\/env python\nfrom fastapi import FastAPI\nfrom langchain_core.prompts import ChatPromptTemplate\nfrom langchain_core.output_parsers import StrOutputParser\nfrom langchain_openai import ChatOpenAI\nfrom langserve import add_routes\n\nimport os, sys\nfrom loguru import logger\nfrom dotenv import load_dotenv\n\nload_dotenv()\n\n# 1. Create prompt template\nsystem_template = "Translate the following into {language}:"\nprompt_template = ChatPromptTemplate.from_messages([\n ('system', system_template),\n ('user', '{text}')\n])\n\n# 2. Create model\nmodel = ChatOpenAI(\n model='deepseek-chat',\n openai_api_key=os.getenv("LLM_API_KEY"),\n openai_api_base=os.getenv("LLM_BASE_URL"),\n max_tokens=4096\n)\n\n# 3. Create parser\nparser = StrOutputParser()\n\n# 4. Create chain\nchain = prompt_template | model | parser\n\n# 4. App definition\napp = FastAPI(\n title="LangChain Server",\n version="1.0",\n description="A simple API server using LangChain's Runnable interfaces",\n)\n\n# 5. Adding chain route\nadd_routes(\n app,\n chain,\n path="\/chain",\n)\n\nif __name__ == "__main__":\n import uvicorn\n\n uvicorn.run(app, host="localhost", port=8000)<\/code><\/pre>\n\n- Call the above API<\/li>\n<\/ul>\n
#!\/usr\/bin\/env python\nfrom langserve import RemoteRunnable\n\nremote_chain = RemoteRunnable("http:\/\/localhost:8000\/chain\/")\nresult = remote_chain.invoke({"language": "chinese", "text": "As you sow, so shall you reap"})\nprint(result)<\/code><\/pre>\n\u6253\u5370: \u79cd\u74dc\u5f97\u74dc\uff0c\u79cd\u8c46\u5f97\u8c46<\/p>\n
Reference<\/h2>\n\n- https:\/\/python.langchain.com\/v0.2\/docs\/tutorials\/llm_chain\/<\/a><\/li>\n
- https:\/\/python.langchain.com\/docs\/concepts\/<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"
Overview LangChain is a framework to build with LLMs by chaining interoperable components. LangGraph is the framework for building controllable agentic workflows. build an application install library pip install langchain pip install -qU langchain-openai example 1 #!\/usr\/bin\/env python3 from typing import List from langchain_openai import ChatOpenAI from langchain_core.output_parsers import StrOutputParser from langchain_core.prompts import ChatPromptTemplate import […] →Read more<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5],"tags":[],"class_list":["post-1384","post","type-post","status-publish","format-standard","hentry","category-5"],"_links":{"self":[{"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1384"}],"collection":[{"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1384"}],"version-history":[{"count":10,"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1384\/revisions"}],"predecessor-version":[{"id":1394,"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1384\/revisions\/1394"}],"wp:attachment":[{"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1384"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1384"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.fanyamin.com\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1384"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}