ã¯ããã« ããã«ã¡ã¯ïŒæšå¹Ž9æããInsight Edgeã®éçºããŒã ã«åç»ããåºæŸã§ããInsight Edgeã§ã¯çæAIæ¡ä»¶ãæ
åœããŠããŸãã åç»ããŠãããŸã éããªãã§ãããæè¡éžå®ã顧客ãšã®èª¿æŽãå«ãå€ãã®æ¥åãè£éãæã£ãŠèªç±ã«ã§ãããšãããè¯ããšæããŠããŸãããŸããInsight Edgeã§ã¯æ¥åæéã®10%ãå匷äŒãªã©ã®èªå·±åçºã«å
ãŠãããšã奚å±ãããŠããŸãããã®æåã®ãããã§ãLangChainã®å匷äŒãéå¶ãããTech Blogã«èšäºãå¯çš¿ããããšããããããªäºã«ææŠã§ããŠãšãŠãè¯ãç°å¢ã ãªãšæããŠããŸãã ããŠãæè¿ç§ãæ
åœããæ¡ä»¶ã§ã çæAIã«å®æ§çãªåæã ãã§ãªãå®éçãªåæããããã ãšããèŠæããããŸãããããã§ä»åã¯ãçæAIã«ããŒã¿åæããããææ³ãæ€èšŒããŠã¿ãŸãããå
·äœçã«ã¯ãçæAIã®Agentã«Kaggleã®ãã¥ãŒããªã¢ã«ãšããŠæåãªã¿ã€ã¿ããã¯å·ã®ä¹å®¢ã®ããŒã¿ã»ãããåæãããåæçµæãè©äŸ¡ããã®ã§ç޹ä»ããããšæããŸãã ç®æ¬¡ ã¯ããã« ç®æ¬¡ æŠèŠ â»è£è¶³ æ¡ä»¶ã§æ§ç¯ããã·ã¹ãã ã®æŠèŠ äºåç¥è èªåŸãšãŒãžã§ã³ããšã¯ ReAct(Reasoning and Acting)ãšã¯ LangChainãšã¯ â»è£è¶³ Code Interpreterã§ã¯ãªãAgentã§å®è£
ããçç± æè¡éžå® LangChainã®Agenté¢é£ã®ã³ã³ããŒãã³ãã«ã€ã㊠éžå®çç± äºåæºå å®è£
å
容 å®è¡çµæ èå¯ åæçµæ åæéçš Agentã«ããèªåŸçãªãšã©ãŒè§£æ±º ãŸãšã æ€èšŒçµæ Code Interpreterãšã®æ¯èŒ ä»åŸã«åããŠ ææ³ æŠèŠ ç§ãæ
åœããŠããæ¡ä»¶ã§ãçæAIã«å®éçãªåæããããããšããèŠæããããŸãããããããçæAI㯠確ççã«ããŒã¿ãçæãããããæ°åŠã®ãããªè«ççæèãæ°å€èšç®ãèŠæ ã§ãã ããã§ã©ã®ããã«çæAIã«ããŒã¿åæããããã®ãæè¡èª¿æ»ãããŸãããçæAIã«èšç®ãããŒã¿åæããããå Žåã Agent ã䜿ã£ãŠPythonã®ã³ãŒããçæã»å®è¡ãããææ³ ãäžè¬çã§ãã ä»åã¯ãçæAIã®Agentã«Kaggleã®ãã¥ãŒããªã¢ã«ãšããŠæåãªã¿ã€ã¿ããã¯å·ã®ä¹å®¢ã®ããŒã¿ã»ãããåæãããåæçµæãè©äŸ¡ããŸããã â»è£è¶³ æ¡ä»¶ã§æ§ç¯ããã·ã¹ãã ã®æŠèŠ ä»åã®æ€èšŒãšã¯ããŸãé¢ä¿ããªãã®ã§ãèå³ãç¡ãæ¹ã¯èªã¿é£ã°ããŠãã ããã åæããŒãã®å
¥å : ãŠãŒã¶ãåæãããããŒããå
¥å 宿§çãªåæã®å®æœ : çæAIãå
¥åãããããŒãã«é¢é£ããæ
å ±ãElastic Searchã®ãã€ããªããæ€çŽ¢æ©èœãçšããRAGã§åéãããã®æ
å ±ã«åºã¥ããŠå®æ§çãªåæã宿œ å®éçãªåæã®å®æœ : çæAIã®Agentã宿§çãªåæçµæãå
ã«ç€Ÿå
ããŒã¿ã®åæãããããšã§å®éçãªåæã宿œïŒâ»ãããä»åã®æè¡æ€èšŒã«é¢é£ããéšåã§ããïŒ æçµçãªã¬ããŒãã®çæ : ã·ã¹ãã ã 宿§çãšå®éçãªèŠç¹ãèåããã æçµçãªåæã¬ããŒããçæ äºåç¥è èªåŸãšãŒãžã§ã³ããReActãLangChainã«ã€ããŠã®ç°¡åãªèª¬æã§ãããåç¥ã®æ¹ã¯ æè¡éžå® ãŸã§èªã¿é£ã°ããŠãã ããã èªåŸãšãŒãžã§ã³ããšã¯ AgentãšããåèªãåºãŠããŸããããããŸã銎æã¿ã®ãªãæ¹ããããšæãã®ã§ç°¡åã«èª¬æããŸããçæAIãLLMã®æèã§åºãŠããAgent=èªåŸãšãŒãžã§ã³ããšæã£ãŠããã ããŠæ§ããŸããã èªåŸãšãŒãžã§ã³ãã¯ãäžããããæçµç®çã«å¯ŸããŠãèªãæèããŠèšç»ãããå®éã«è¡åãããŠæçµç®çãéæããããšããã·ã¹ãã ã§ãã ãã®è¡åã®éã«ã èªåŸãšãŒãžã§ã³ãã¯ããŒã«ã䜿ã£ãŠçŸå®äžçã®ã·ã¹ãã ã«å¹²æž ã§ããŸãã ãã®èª¬æã ãšæœè±¡åºŠãé«ããããåãããªããšæãã®ã§ä»åã®æ€èšŒãäŸã«èª¬æããŸãã èªåŸãšãŒãžã§ã³ãã«ã¯ããã¿ã€ã¿ããã¯å·ã®ä¹å®¢ã®ããŒã¿ã»ãããåæããããšããæçµç®çã ããäžããŸãã ãããšèªåŸãšãŒãžã§ã³ãã¯ãæåã«æèããŠã©ã®ããã«åæãããèšç»ãç«ãŠãŸããæ¬¡ã«ãèšç»ã«åŸãã€ã³ã¿ãŒãããæ€çŽ¢ãããããŒã«ãPythonã³ãŒãçæã»å®è¡ããŒã«ã䜿ã£ãŠããŒã¿åæã宿œããŠæçµç®çãéæããããšããŸãã çæAIãå
éšã§èããŠããã ãã§ãªããã€ã³ã¿ãŒãããæ€çŽ¢ããŒã«ãPythonã³ãŒãçæã»å®è¡ããŒã«ã䜿ã£ãŠãçŸå®äžçã®ã·ã¹ãã ãšãããšããããŠãããšããããéåžžã®çæAIã®å©çšãšå€§ããç°ãªããŸã ã ä»åã¯ReActãšããææ³ã§AgentãåäœãããŠããã®ã§ã詳现ãªä»çµã¿ã¯æ¬¡ã® ReAct(Reasoning and Acting)ãšã¯ ã§èª¬æããŸãã èªåŸãšãŒãžã§ã³ãã«ã€ããŠè©³çްã確èªãããæ¹ã¯ã Autonomous Agents & Agent Simulations ãåç
§ããŠãã ããã ReAct(Reasoning and Acting)ãšã¯ ReAct(Reasoning and Acting)ã¯çæAIã«è«ççãªæèããããPrompt Engineeringã®ææ³ã®1ã€ã§ããçæAIã«æšè«ãšè¡åãç¹°ãè¿ãããããšã§è«ççæèãä¿ããã®ã§ã次ã®äžæ®µéã®ããã»ã¹ãç¹°ãè¿ããŸãã æè(Thought) : ç®çãçè§£ããè¡åèšç»ã»ã¿ã¹ã¯ã®è©³çްåãè¡ããå
·äœçãªè§£æ±ºçãèæ¡ããã芳å¯(Observation)ãããã£ãŒãããã¯ãåãåããé©å®è¡åèšç»ãä¿®æ£ããã è¡å(Action) : æè(Thought)段éã§èæ¡ããã解決çãå®è¡ããã 芳å¯(Observation) : è¡å(Action)ã®çµæã芳å¯ããæ¬¡ã®æè(Thought)ãžãã£ãŒãããã¯ããã LangChainã®Agentã¯ããã® è¡å(Action)ã®éšåã«ããŒã«ãäœ¿çš ã§ããŸããSerpApiçã®æ€çŽ¢ããŒã«ãPythonREPLçã®Pythonã³ãŒãçæã»å®è¡ããŒã«ã䜿çšããŸããå©çšå¯èœãªããŒã«ã®èª¬æãçè§£ããç®çéæã«å¿
èŠãªãã®ãAgentèªãéžæããŸãã ã€ãŸãã äžããããæçµç®çã«å¯ŸããŠèªãæèããŠèšç»ãç«ãŠãé©åãªããŒã«ãéžæããŠè¡åããçµæã®èгå¯ãšãã£ãŒãããã¯ã®ã«ãŒããç®çéæãŸã§ç¹°ãè¿ãèªåŸãšãŒãžã§ã³ã ãäœæãããŸãã ReActã«ã€ããŠè©³çްã確èªãããæ¹ã¯ãReActãæå±ãããè«æ ReAct: Synergizing Reasoning and Acting in Language Models ãåç
§ããŠãã ããã LangChainãšã¯ LangChainãšã¯å€§èŠæš¡èšèªã¢ãã«(LLM)ãçšããã¢ããªã±ãŒã·ã§ã³ãéçºããããã®ãã¬ãŒã ã¯ãŒã¯ã§ãã æ§ã
ãªãšã³ã·ã¹ãã ãšé£æºãããããªã£ãŠããŸãã LangChainã«ã¯ã¢ãžã¥ãŒã«ã6ã€ããã®ã§ç°¡åã«ç޹ä»ããŸããä»åã¯äž»ã«Agentsã®ã¢ãžã¥ãŒã«ã«é¢ä¿ããããŸãã ã¢ãžã¥ãŒã« æŠèŠ Model I/O LLMã«å¯Ÿããããã³ããå
¥åãåŒã³åºããçµæã®åãåãã®å®è£
ãç°¡åã«ããã Retrieval LLMã«æªç¥ã®æ
å ±ã«ã¢ã¯ã»ã¹ããæ©èœãæäŸãããRetrieval-Augmented Generation(RAG)ãæ±ãã¢ãžã¥ãŒã«ãå€éšã®æ€çŽ¢ãšã³ãžã³ãããŒã¿ããŒã¹ãšé£æºããŠãLLMã«äºååŠç¿ããŠããªãæ
å ±ã«å¯Ÿå¿ãããæ©èœãç°¡åã«å®è£
ã§ããããã«ããã Memory éå»ã®äŒè©±å±¥æŽãããŒã¿ããŒã¹ã«ä¿åããããåŒã³åºãæ©èœãç°¡åã«å®è£
ã§ããããã«ããã Chains è€æ°ã®ã¢ãžã¥ãŒã«ã®çµã¿åãããç°¡åã«å®è£
ã§ããããã«ããã Agents èªåŸçã«æèããå€éšã«å¹²æžããèªåŸãšãŒãžã§ã³ãã®æ§ç¯ãç°¡åã«ããã Callbacks æ§ã
ãªã€ãã³ãçºçæã®åŠçã®å®è£
ãç°¡åã«ããããã°ã®å®è£
ãªã©ã«çšããã LangChainã«ã€ããŠè©³çްã確èªãããæ¹ã¯ã LangChainå
¬åŒããã¥ã¡ã³ã ãåç
§ããŠãã ããã â»è£è¶³ Code Interpreterã§ã¯ãªãAgentã§å®è£
ããçç± ãã¡ããä»åã®æ€èšŒãšã¯çŽæ¥é¢ä¿ããªãã®ã§ãèå³ãç¡ãæ¹ã¯èªã¿é£ã°ããŠãã ããã æè¡æ€èšŒããã®ã¯çæAIã®Agentã«ããŒã¿åæããããéšåã§ããOpenAIã®Code InterpreterãšäŒŒãæ©èœã§ãããCode Interpreterã¯å€éšç°å¢ïŒã€ã³ã¿ãŒãããçïŒã«ã¢ã¯ã»ã¹ã§ããªãçã®å¶çŽããããŸãã äžæ¹ãAgentã§ããã°äžæç¹ã解決ã§ããªããšã©ãŒãçºçããéã«ãæ€çŽ¢ããŒã«ã䜿ã£ãŠæ€çŽ¢ããçãä»ã®ããŒã«ã䜿ã£ãè¡åãåãããšãã§ããŸãããã®ããAgentã§å®è£
ããæ¹ã顧客ã®èŠæã«æè»ã«å¯Ÿå¿ã§ããŸãã ãŸãæ
åœããæ¡ä»¶ã¯ã æ¡ä»¶ã§æ§ç¯ããã·ã¹ãã ã®æŠèŠ ã®ããã«è€éã§ä»åŸãæ¡åŒµãããããªèŠä»¶ã§ãã Agentã§ããã°è¡åãããŒã«ã«ã€ããŠèªç±ã«ã«ã¹ã¿ãã€ãºãã§ãã ããAgentã§å®è£
ããŸããã æè¡éžå® çæAIã«ããŒã¿åæããããéšåãæ€èšŒããŸãã æ€èšŒã¯LangChainã§å®è£
ããŸããã LangChainã®Agenté¢é£ã®ã³ã³ããŒãã³ãã«ã€ã㊠éžå®çç±ã話ãåã«ãLangChainã®Agenté¢é£ã®ã³ã³ããŒãã³ãã®èª¬æãããŠãããŸãããåç¥ã®æ¹ã¯èªã¿é£ã°ããŠãã ããã ã³ã³ããŒãã³ã 説æ AgentExecutor AgentExecutorã¯ãAgentã®å®è¡ã管çããã³ã³ããŒãã³ãã§ãAgentãå®è¡ããã¿ã¹ã¯ãå¶åŸ¡ããçµæãåŠçããã Agent Agentã¯ãç¹å®ã®ã¿ã¹ã¯ãããã»ã¹ãèªååããããã®ãšã³ãã£ãã£ã§ãäžé£ã®Toolsã䜿çšãããããŒã«ã®Descriptionãèªãã§é©åãªããŒã«ãéžæããã Tools Toolsã¯ãAgentãã¿ã¹ã¯ãå®è¡ããéã«äœ¿çšããå
·äœçãªæ©èœããµãŒãã¹ã®éåãToolsã«ã¯å€éšã®APIåŒã³åºããå¯èœã«ããããŒã«ãGoogleæ€çŽ¢ãªã©ãå¯èœã«ããæ€çŽ¢ããŒã«ãPythonã®ã³ãŒãçæã»å®è¡ãå¯èœã«ããããŒã«ãªã©ãããã â»LangChainã§å©çšå¯èœãªToolsäžèŠ§ã¯ ãã¡ã ã ãŸããç¬èªã®Toolsã®äœæãç°¡åã«ã§ãããç¬èªã®Retrieverãå®çŸ©ããŠããã°ç¬èªå®è£
ããRAGãçµã¿èŸŒãã Agentãäœãããšãã§ããã Toolkit Toolkitã¯ãè€æ°ã®Toolsãçµã¿åãããŠæ§æãããã»ããã§ãç¹å®ã®ã¿ã¹ã¯ãå¹ççã«å®è¡ããããã«æé©åãããŠããã Pythonã®ã³ãŒãçæã»å®è¡ã«ç¹åããToolkitãªã©ãããã â»LangChainã§å©çšå¯èœãªToolkitäžèŠ§ã¯ ãã¡ã ã éžå®çç± æè¡èŠçŽ éžå®çç± LLM: GPT-4 Turbo 粟床ãšã³ã¹ããéèŠããããã ãã¬ãŒã ã¯ãŒã¯: LangChain çæAIã®Agentã容æã«å®è£
ã»ç®¡çã§ãããã¬ãŒã ã¯ãŒã¯ã§ãããããã¡ã¯ãã¹ã¿ã³ããŒãã«ãªãã€ã€ããããã Tools: PythonREPL Pythonã®ã³ãŒãçæã»å®è¡ãå¯èœã«ããããŒã«ãããŒã¿åæã¿ã¹ã¯ã«ãããŠãPythonã䜿çšããŠåæããããã Tools: DuckDuckGoSearch ã€ã³ã¿ãŒãããæ€çŽ¢ãå¯èœã«ããããŒã«ãäžæç¹ã解決ã§ããªããšã©ãŒãçºçããå Žåã«æ€çŽ¢ããŠå¯ŸåŠããããã ä»åã¯ããŒã«ãšããŠç¬èªå®çŸ©ããã Agent: ReAct Agentã®æ±çšæ§ãšè«ççãªæèèœåãè©äŸ¡ãããã ReAct ãæ¡çšãæ¡ä»¶ã§æ§ç¯ããã·ã¹ãã ããã£ãã圢åŒã®ãããLangChainã®AgentTypeã¯CHAT_ZERO_SHOT_REACT_DESCRIPTION ãæ¡çšã äºåæºå äºåã«ã¿ã€ã¿ããã¯å·ã®ä¹å®¢ã®ããŒã¿ã»ãããããŠã³ããŒãããS3ãªã©ã®ããŠã³ããŒãå¯èœãªå Žæã«é
眮ããŠãã ãããã¿ã€ã¿ããã¯å·ã®ä¹å®¢ã®ããŒã¿ã»ããã¯KaggleããããŠã³ããŒãã§ããŸãã ããŒã¿ã»ããã¯Kaggleã«ãŠãŒã¶ç»é²ããã Kaggleã®ã¿ã€ã¿ããã¯ããŒã¿ã»ããã®ããŒãž ããããŠã³ããŒãã§ããŸãã ãŸããOpenAIã®APIããŒã¯ç°å¢å€æ°ã«äºåã«ç»é²ããŠãããŠãã ããã OPEN_API_KEY="ãèªèº«ã®ä¿æããŠããAPIããŒãèšèŒããŠãã ãã" å®è£
å
容 äžèšã®ã³ãŒãã§ãã¿ã€ã¿ããã¯å·ã®ä¹å®¢ããŒã¿ã»ãããããŠã³ããŒãããã¿ã€ã¿ããã¯å·ã§çåã«å¯äžããä¹å®¢ã®å±æ§ãåæãããŸãã ã³ãŒãã®å
容㯠éžå®çç± ã«èšèŒããéããªã®ã§è©³çްãªèª¬æã¯å²æããŸãã æ¡ä»¶ã§ã¯åçŸæ§ã®é«ãåæãæ±ããããŠãããããLLMã®temperatureã0ã«èšå®ããŸããã Agentã«äžããæç€ºã¯ä»¥äžã«ããŠããŸãã ã¿ã€ã¿ããã¯å·ã®ä¹å®¢ã®ããŒã¿ã»ãããåæããŠãã ãããçåã«å¯äžãã屿§ãã©ã³ãã³ã°ã§è¡šç€ºãã圱é¿åºŠãæ°å€ã§è¡šç€ºããŠãã ãããããŒã¿ã»ããã¯ãhttps://xxxxxxxxxxxx/train.csv ã䜿çšããŠãã ããã ããŒã¿ã»ãããã€ã³ã¿ãŒãããããããŠã³ããŒãããããæç€ºããã®ã¯ãOpenAIã®Code Interpreterãã§ããªãå€éšç°å¢ãžã®ã¢ã¯ã»ã¹ãå¯èœãæ€èšŒããããã§ããã³ãŒããå®è¡ããå Žåã¯ã äºåæºå ã«ããããã«ããŠã³ããŒãå¯èœãªURLã«æžãæããŠãã ããã from langchain.agents import AgentType, initialize_agent, load_tools, Tool from langchain.chat_models import ChatOpenAI from langchain.tools import DuckDuckGoSearchRun chat = ChatOpenAI( temperature= 0 , # åçŸæ§ãéèŠãããããtemperatureã0ã«èšå® model= "gpt-4-turbo-preview" ) tools = load_tools( # Agentã䜿çšå¯èœãªããŒã«ã®é
åãèªã¿èŸŒãïŒè€æ°æå®å¯èœãAgentãããŒã«ã®descriptionãèªã¿é©åãªããŒã«ãéžæããïŒ [ "python_repl" #ãPythonã®ã³ãŒããå®è¡ããããã®Tool ] ) search = DuckDuckGoSearchRun() # äžæç¹ããšã©ãŒã®è§£æ±ºçãæ€çŽ¢ããããDuckDuckGoSearchã远å tools.append( # 远å ããDuckDuckGoSearchãtoolsã«è¿œå Tool( # ããŒã«ãšããŠæ€çŽ¢ããŒã«ãç¬èªå®çŸ© name= "duckduckgo-search" , func=search.run, description= "This tool is used for conducting internet searches to address uncertainties or unresolved errors that arise during tasks or development processes." # Agentãéžæã§ããããã«ããŒã«ã®èª¬æãèšèŒ ) ) agent = initialize_agent( tools=tools, # Agentã䜿çšããããšãã§ããããŒã«ã®é
åãæå® llm=chat, # Agentã䜿çšããèšèªã¢ãã«ãæå® agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, #ReActãå®è¡ããAgentãæå® verbose= True # å®è¡äžã®è©³çްãªãã°ã衚瀺ãã ) result = agent.run( "ã¿ã€ã¿ããã¯å·ã®ä¹å®¢ã®ããŒã¿ã»ãããåæããŠãã ãããçåã«å¯äžãã屿§ãã©ã³ãã³ã°ã§è¡šç€ºãã圱é¿åºŠãæ°å€ã§è¡šç€ºããŠãã ãããããŒã¿ã»ããã¯ãhttps://xxxxxxxxxxxx/train.csv ã䜿çšããŠãã ããã" ) print (f "å®è¡çµæ: {result}" ) å®è¡çµæ å®è¡ãããšãè«ççã«æšè«ãšè¡åãç¹°ãè¿ããæçµçã«ã©ã³ãã³ã°ãåºåã§ããŸããã åºåçµæ parch : 0.6250 sex : 0.5365 sibsp : 0.5110 pclass : 0.3639 fare_quantile : 0.3567 age_group : 0.1178 ãã®åæçµæã§ã¯ãparchïŒåä¹ããŠããå®¶æïŒèŠªåïŒã®äººæ°ïŒãsexïŒæ§å¥ïŒãsibspïŒåä¹ããŠããå
åŒå§åйãé
å¶è
ã®æ°ïŒãpclassïŒå®¢å®€ççŽïŒãfare_groupïŒéè³ïŒãage_groupïŒå¹Žéœ¢ïŒã®é ã«çåãžã®åœ±é¿ã匷ã屿§ã ã£ãããã§ããã å®è¡çµæãèŠãŠã¿ãŸããããïŒâ»å®è¡çµæäžã®ããŒã¿ã»ããã®ããŠã³ããŒãURLã¯æžãæããŠããŸãã) å®è¡çµæå
šæïŒéåžžã«é·ãã®ã§è©³çްã確èªãããæ¹ã®ã¿ããã®æç« ãã¯ãªãã¯ããŠå±éããŠãã ãããïŒ > Entering new AgentExecutor chain... Question: Analyze the Titanic passengers dataset to determine which attributes had an impact on survival. Provide the analysis results in a ranking with numerical values indicating the degree of impact on survival. Download the dataset using Python from the provided URL ( https://xxxxxxxxx/train.csv ) . Thought: To analyze the Titanic dataset, I will first need to download the data using Python. After downloading, I will load the data into a pandas DataFrame and perform exploratory data analysis ( EDA ) to determine which attributes had the most significant impact on survival. Action: { " action " : " Python_REPL " , " action_input " : " import pandas as pd \n df = pd.read_csv('https://xxxxxxxxx/train.csv') \n print(df.head()) " } Python REPL can execute arbitrary code. Use with caution. Observation: pclass survived name sex age sibsp parch ticket fare cabin embarked boat body home.dest 0 1 1 Allen, Miss. Elisabeth Walton female 29 . 0000 0 0 24160 211 . 3375 B5 S 2 NaN St Louis, MO 1 1 1 Allison, Master. Hudson Trevor male 0 . 9167 1 2 113781 151 . 5500 C22 C26 S 11 NaN Montreal, PQ / Chesterville, ON 2 1 0 Allison, Miss. Helen Loraine female 2 . 0000 1 2 113781 151 . 5500 C22 C26 S NaN NaN Montreal, PQ / Chesterville, ON 3 1 0 Allison, Mr. Hudson Joshua Creighton male 30 . 0000 1 2 113781 151 . 5500 C22 C26 S NaN 135 . 0 Montreal, PQ / Chesterville, ON 4 1 0 Allison, Mrs. Hudson J C ( Bessie Waldo Daniels ) female 25 . 0000 1 2 113781 151 . 5500 C22 C26 S NaN NaN Montreal, PQ / Chesterville, ON Thought:The dataset has been successfully loaded into a pandas DataFrame. The next step is to perform exploratory data analysis ( EDA ) to determine which attributes had the most significant impact on survival. I will start by checking for missing values in the dataset, as this can affect the analysis. Then, I will proceed to calculate the survival rates based on different attributes such as ' pclass ' , ' sex ' , ' age ' , ' sibsp ' , ' parch ' , ' fare ' , and ' embarked ' . Action: { " action " : " Python_REPL " , " action_input " : " print(df.isnull().sum()) " } Observation: pclass 0 survived 0 name 0 sex 0 age 263 sibsp 0 parch 0 ticket 0 fare 1 cabin 1014 embarked 2 boat 823 body 1188 home.dest 564 dtype: int64 Thought:The dataset contains a significant number of missing values in the ' age ' , ' cabin ' , ' boat ' , ' body ' , and ' home.dest ' columns. The ' boat ' and ' body ' columns are not typically used for survival analysis, as they relate to post-accident events ( lifeboats and body recovery ) . The ' cabin ' data is also largely missing, which may limit its usefulness in the analysis. However, ' age ' and ' embarked ' are important factors that are often considered in survival analysis. The missing value in ' fare ' is negligible as it is only one entry. The next step is to analyze the impact of various attributes on survival. I will calculate survival rates based on ' pclass ' , ' sex ' , ' age ' , ' sibsp ' , ' parch ' , and ' fare ' . Since ' age ' has missing values, I will need to decide how to handle them, either by imputing a value or by excluding those rows from certain parts of the analysis. For the initial analysis, I will focus on the attributes with complete data. I will start by calculating the survival rates for ' pclass ' and ' sex ' , as these are commonly known to have had a significant impact on survival. Then I will proceed with ' sibsp ' , ' parch ' , and ' fare ' . For ' age ' , I will consider how to handle the missing values before proceeding. Action: { " action " : " Python_REPL " , " action_input " : " survival_rates = {} \n for column in ['pclass', 'sex', 'sibsp', 'parch']: \n survival_rates[column] = df.groupby(column)['survived'].mean() \n print(survival_rates) " } Observation: { ' pclass ' : pclass 1 0 . 619195 2 0 . 429603 3 0 . 255289 Name: survived, dtype: float64, ' sex ' : sex female 0 . 727468 male 0 . 190985 Name: survived, dtype: float64, ' sibsp ' : sibsp 0 0 . 346801 1 0 . 510972 2 0 . 452381 3 0 . 300000 4 0 . 136364 5 0 . 000000 8 0 . 000000 Name: survived, dtype: float64, ' parch ' : parch 0 0 . 335329 1 0 . 588235 2 0 . 504425 3 0 . 625000 4 0 . 166667 5 0 . 166667 6 0 . 000000 9 0 . 000000 Name: survived, dtype: float64 } Thought:The survival rates based on ' pclass ' , ' sex ' , ' sibsp ' , and ' parch ' show clear trends. Higher class passengers ( pclass 1 ) had a higher survival rate than those in lower classes. Females had a much higher survival rate than males. The number of siblings/spouses ( sibsp ) and parents/children ( parch ) aboard also had varying impacts on survival rates, with some numbers showing higher survival rates than others. To provide a more comprehensive analysis, I will now calculate the survival rate for ' fare ' by categorizing it into quantiles, which will help to understand if higher fares ( which could correlate with higher socio-economic status or cabin location ) had an impact on survival. I will also handle the missing ' age ' data by filling in the missing values with the median age, and then categorizing age into groups to see if there is a trend in survival rates across different age groups. First, I will handle the ' fare ' attribute by categorizing it into quantiles. Action: { " action " : " Python_REPL " , " action_input " : " df['fare_quantile'] = pd.qcut(df['fare'], 4, labels=False) \n survival_rates['fare_quantile'] = df.groupby('fare_quantile')['survived'].mean() \n print(survival_rates['fare_quantile']) " } Observation: fare_quantile 0 . 0 0 . 228487 1 . 0 0 . 284375 2 . 0 0 . 435976 3 . 0 0 . 585139 Name: survived, dtype: float64 Thought:The survival rates for the ' fare_quantile ' show a positive correlation between fare price and survival, with passengers who paid higher fares having a higher survival rate. This suggests that socio-economic status , which could be inferred from the fare paid, had an impact on survival. Next, I will address the missing ' age ' data. Since age is an important factor and cannot be ignored, I will impute the missing values with the median age. After imputing the missing values, I will categorize the ' age ' into groups and calculate the survival rates for each group to see if there is a trend in survival rates across different age groups. Action: { " action " : " Python_REPL " , " action_input " : " median_age = df['age'].median() \n df['age'].fillna(median_age, inplace=True) \n df['age_group'] = pd.qcut(df['age'], 4, labels=False) \n survival_rates['age_group'] = df.groupby('age_group')['survived'].mean() \n print(survival_rates['age_group']) " } Observation: age_group 0 0 . 435435 1 0 . 317597 2 0 . 425532 3 0 . 394410 Name: survived, dtype: float64 Thought:The survival rates for the ' age_group ' show that the youngest and older age groups had slightly higher survival rates than the middle age groups, although the differences are not as pronounced as with other attributes like ' sex ' and ' pclass ' . Now that I have calculated the survival rates for ' pclass ' , ' sex ' , ' sibsp ' , ' parch ' , ' fare_quantile ' , and ' age_group ' , I can rank these attributes by their impact on survival. To do this, I will calculate the difference in survival rates between the highest and lowest groups within each attribute to determine the range of impact. Then I will rank the attributes based on these ranges. Action: { " action " : " Python_REPL " , " action_input " : " impact_ranges = {} \n for attribute, rates in survival_rates.items(): \n impact_ranges[attribute] = rates.max() - rates.min() \n impact_ranking = sorted(impact_ranges.items(), key=lambda x: x[1], reverse=True) \n for rank in impact_ranking: \n print(f'{rank[0]}: {rank[1]:.4f}') " } Observation: parch: 0 . 6250 sex: 0 . 5365 sibsp: 0 . 5110 pclass: 0 . 3639 fare_quantile: 0 . 3567 age_group: 0 . 1178 Thought:The ranking of attributes based on their impact on survival, with the numerical values indicating the degree of impact, is as follows: 1 . `parch` ( number of parents/children aboard ) : 0 . 6250 2 . `sex` : 0 . 5365 3 . `sibsp` ( number of siblings/spouses aboard ) : 0 . 5110 4 . `pclass` ( passenger class ) : 0 . 3639 5 . `fare_quantile` ( fare price category ) : 0 . 3567 6 . `age_group` : 0 . 1178 It is important to note that the `parch` attribute shows the largest range of impact, which might be surprising as it is not typically considered the most significant factor. However, this could be due to the way the survival rates are calculated across different numbers of parents/children aboard, which might not be linear and could be influenced by small sample sizes for certain values. The `sex` attribute has the second-highest impact, which aligns with historical accounts that women were given priority during the lifeboat boarding process. The `sibsp` attribute is third, suggesting that having siblings or a spouse aboard had a significant impact on survival, potentially due to the support system or prioritization of families during evacuation. The `pclass` attribute is fourth, indicating that passenger class was a significant factor, with first-class passengers having a higher survival rate. The `fare_quantile` is fifth, which is related to socio-economic status and potentially cabin location, with higher fares correlating with higher survival rates. Lastly, the `age_group` has the smallest range of impact, suggesting that age was a less significant factor compared to the others, although there was still some variation in survival rates across age groups. Final Answer: The ranking of attributes by impact on survival, from highest to lowest, is as follows: 1 . `parch` : 0 . 6250 2 . `sex` : 0 . 5365 3 . `sibsp` : 0 . 5110 4 . `pclass` : 0 . 3639 5 . `fare_quantile` : 0 . 3567 6 . `age_group` : 0 . 1178 > Finished chain. å®è¡çµæ: The ranking of attributes by impact on survival, from highest to lowest, is as follows: 1 . `parch` : 0 . 6250 2 . `sex` : 0 . 5365 3 . `sibsp` : 0 . 5110 4 . `pclass` : 0 . 3639 5 . `fare_quantile` : 0 . 3567 6 . `age_group` : 0 . 1178 äžèº«ãèŠãŠã¿ãŸããããã¯ããã«Questionã§æçµç®çãå®çŸ©ããŠããŸãã Question: Analyze the Titanic passengers dataset to determine which attributes had an impact on survival. Provide the analysis results in a ranking with numerical values indicating the degree of impact on survival. Download the dataset using Python from the provided URL ( https://xxxxxxxxx/train.csv ) . ãã¡ããšæç€ºéãã«ãçåã«å¯äžãã屿§ãã©ã³ãã³ã°åœ¢åŒã§è¡šç€ºããã¿ã¹ã¯ãçè§£ããŠããŸããã ãã®åŸã¯ã以äž6ã¹ãããã«åããŠå®è¡ããŠããããã§ãã ããŒã¿ã»ããã®ããŠã³ããŒããšèªã¿èŸŒã¿ : æå®ãããURLããã¿ã€ã¿ããã¯ã®ããŒã¿ã»ãããããŠã³ããŒãããPandasã®DataFrameã«èªã¿èŸŒã¿ãŸããèªã¿èŸŒãã ããŒã¿ã®å
é éšåã衚瀺ããŠãããŒã¿ãæ£ããèªã¿èŸŒãŸããããšã確èªããŸãã æ¬ æå€ã®ç¢ºèª : ããŒã¿ã»ããã«å«ãŸããæ¬ æå€ã®æ°ã確èªããŸããç¹ã«ã幎霢(age)ããããã£ãã³(cabin)ãããä¹è¹ããæž¯(embarked)ããªã©ã®ã«ã©ã ã§æ¬ æå€ãå€ãããšãåãããŸãããããã®æ¬ æå€ã¯åæã«åœ±é¿ãäžãããããé©åã«åŠçããå¿
èŠããããŸãã çåçã®èšç® : çåã«åœ±é¿ãäžããå¯èœæ§ã®ãã屿§ïŒã客宀ççŽ(pclass)ãããæ§å¥(sex)ãããå
åŒå§åйãé
å¶è
ã®æ°(sibsp)ããã芪ãåã©ãã®æ°(parch)ãïŒã«ã€ããŠãã°ã«ãŒãããšã«çåçãèšç®ããŸãã æé(fare)ã«åºã¥ãçåçã®èšç® : ä¹è¹æéãååäœæ°ã§åå²ããæéã®ã«ããŽãªãŒããšã«çåçãèšç®ããŸããæéãçåçã«ã©ã®ããã«åœ±é¿ããããåæããŸãã 幎霢(age)ã«åºã¥ãçåçã®èšç® : 幎霢ããŒã¿ã®æ¬ æå€ãäžå€®å€ã§è£å®ãã幎霢ãã°ã«ãŒãã«åããŠçåçãèšç®ããŸãã幎霢ãçåçã«ã©ã®ããã«åœ±é¿ããããåæããŸãã 屿§ã®åœ±é¿åºŠã®ã©ã³ãã³ã°ã®è¡šç€º : æåŸã«ãå屿§ã«åºã¥ããŠèšç®ãããçåçã®å·®ãçšããŠãçåã«æã圱é¿ãäžãã屿§ãã©ã³ãã³ã°åœ¢åŒã§è¡šç€ºããŸããã©ã³ãã³ã°ã¯ãå屿§ãçåã«äžãã圱é¿ã®åºŠåããæ°å€ã§ç€ºããŠããŸãã èå¯ åæçµæ Agentã«ããåæãšäººã«ããåæãæ¯èŒããŠåŠ¥åœæ§ã確èªããŸãã Kaggleã§ä»åã®ããŒã¿ã»ããã®åæããããŠãããã¡ãã®æçš¿ ãèŠãŠããçåã«åœ±é¿ãäžããŠãã屿§ãåãã§ããã人ãè¡ã£ãåæãšæ¯èŒããŠããä»åã®Agentã®è¡ã£ãåæã¯åŠ¥åœãšèšããŸããã¿ã€ã¿ããã¯å·ã®å²å®ãšç
§ããåãããŠã客宀ççŽãæ§å¥ãåäŸãé£ããå®¶æãªã©ã®å±æ§ãçåã«åœ±é¿ãããšããåæã¯åŠ¥åœãšèšããŸãã åæéçš ä»åã®æ€èšŒã§ã¯åæçµæãããåæéçšèªäœã®èå¯ãéèŠã§ãã çåã«å¯äžãã屿§ãã©ã³ãã³ã°è¡šç€ºãããšããå€§ç®æšã®ã¿ãäžããŠããŸãããã Agentã¯ç®çéæã®ããã«èªåŸçã«æèãèªã詳现ãªã¿ã¹ã¯ãäœãåºããŠå®è¡ ããŠããŸãããç¹ã«ããŒã¿ã確èªããŠèªãã®å€æã§æ¬ æå€ã確èªããŠè£å®ããããçåçãèšç®ããåŸãé¢é£ã®ãããããªå±æ§ã詳现ã«åæããã¿ã¹ã¯ãèªãäœãåºããŠå®è¡ããŠããç¹ã¯éåžžã«è峿·±ãã§ãã ä»åã®ããŒã¿ã»ãããåæããŠããèšäºãããã€ãæèŠããŸãããã æ¬ æå€ãåããçã®æç€ºãããŠããªãã¿ã¹ã¯ã人ãšåæ§ã®æé ã§å®è¡ã§ããŠããŸããã ãã®ãããªè«ççãªæèãã§ããçç±ã¯ ReAct ã®æšè«ãã¬ãŒã ã¯ãŒã¯ã䜿çšããããã ãšèããããŸãã 該åœç®ææç² Thought:The dataset has been successfully loaded into a pandas DataFrame. The next step is to perform exploratory data analysis ( EDA ) to determine which attributes had the most significant impact on survival. I will start by checking for missing values in the dataset, as this can affect the analysis. Then, I will proceed to calculate the survival rates based on different attributes such as ' pclass ' , ' sex ' , ' age ' , ' sibsp ' , ' parch ' , ' fare ' , and ' embarked ' . Action: { " action " : " Python_REPL " , " action_input " : " print(df.isnull().sum()) " } Observation: pclass 0 survived 0 name 0 sex 0 age 263 sibsp 0 parch 0 ticket 0 fare 1 cabin 1014 embarked 2 boat 823 body 1188 home.dest 564 dtype: int64 Thought:The dataset contains a significant number of missing values in the ' age ' , ' cabin ' , ' boat ' , ' body ' , and ' home.dest ' columns. The ' boat ' and ' body ' columns are not typically used for survival analysis, as they relate to post-accident events ( lifeboats and body recovery ) . The ' cabin ' data is also largely missing, which may limit its usefulness in the analysis. However, ' age ' and ' embarked ' are important factors that are often considered in survival analysis. The missing value in ' fare ' is negligible as it is only one entry. The next step is to analyze the impact of various attributes on survival. I will calculate survival rates based on ' pclass ' , ' sex ' , ' age ' , ' sibsp ' , ' parch ' , and ' fare ' . Since ' age ' has missing values, I will need to decide how to handle them, either by imputing a value or by excluding those rows from certain parts of the analysis. For the initial analysis, I will focus on the attributes with complete data. Agentã«ããèªåŸçãªãšã©ãŒè§£æ±º äœåºŠãæ€èšŒãããŠãããšãAgentãçæããPythonã®ã³ãŒããå®è¡æã«ãšã©ãŒãåãããšããããŸããããšã©ãŒãçºçããéã«Agentã¯ã ReAct ã®æšè«ãã¬ãŒã ã¯ãŒã¯ã«æ²¿ã£ãŠããšã©ãŒãèªåŸçã«è§£æ±ºããŠããŸãããå
·äœçã«ã¯çºçãããšã©ãŒã®è§£æ±ºçãæ€çŽ¢ããŒã«ã§æ€çŽ¢ããŠè§£æ±ºããŠããŸããã èªåŸçãªãšã©ãŒè§£æ±ºã®ããã»ã¹ 芳å¯(Observation) : ååã®è¡å(Action)ã®çµæããšã©ãŒã®çºçã確èªããã æè(Thought) : 解決çãæ¢ãããã«ãé©åãªããŒã«ã®äœ¿çšããããäžæç¹ããšã©ãŒã®è§£æ±ºçãæ€çŽ¢ããããã®ããŒã«ããšãã説æã®æ€çŽ¢ããŒã«ãèŠã€ãã解決çãã€ã³ã¿ãŒãããæ€çŽ¢ããããšãèšç»ããã è¡å(Action) : æ€çŽ¢ããŒã«ãçšããŠè§£æ±ºçãæ€çŽ¢ããã 芳å¯(Observation) : æ€çŽ¢çµæããæçãªæ
å ±ãæœåºããã æè(Thought) : æœåºãããæ
å ±ããå
·äœçãªã¢ã¯ã·ã§ã³ãèæ¡ããã è¡å(Action) : Pythonã³ãŒãçæã»å®è¡ããŒã«ã§è§£æ±ºçãå®è¡ããã ãã®ããã« äºæãã¬äºæ
ã«ééããŠããæšè«ãšè¡åãç¹°ãè¿ãReActã®Agentã¯æè»ã«å¯Ÿå¿ ã§ããŸããç¶æ³ã«åãããŠèšæ©å¿å€ã«èšç»ã倿ŽããããŒã«ã䜿ãåããç®çéæã«åããŠã¿ã¹ã¯ãç¶ç¶ã§ããç¹ãReActã§åäœããAgentã®åŒ·ã¿ã§ãã äžèšã®äºäŸã¯ãseabornãšããã¢ãžã¥ãŒã«ãã€ã³ã¹ããŒã«ã§ããªããšã©ãŒãçºçãã解決çãæ€çŽ¢ããŒã«ã§æ€çŽ¢ããŠããŸããçµå±ã€ã³ã¹ããŒã«ã§ããªããšããåé¡ã¯è§£æ±ºã§ããŸããã§ããããä»ã®ã¢ãžã¥ãŒã«ã䜿ãããšã§ãšã©ãŒãåé¿ããŠåæãé²ããŠããŸããã Agentãçºçãããšã©ãŒã®è§£æ±ºçãæ€çŽ¢ããããåé¿çãæ¢ããŠåæãç¶ããŠããäºäŸ Action: { " action " : " Python_REPL " , " action_input " : " !pip install seaborn " } Observation: SyntaxError ( ' invalid syntax ' , ( ' <string> ' , 1 , 1 , ' !pip install seaborn\n ' , 1 , 2 )) Thought:It seems that I made the same mistake again. I need to use the duckduckgo-search tool to search for the correct way to install the seaborn module. Action: { " action " : " duckduckgo-search " , " action_input " : " install seaborn module in Python using pip " } Observation: Latest version Jan 25 , 2024 Project description seaborn: statistical data visualization Seaborn is a Python visualization library based on matplotlib. It provides a high-level interface for drawing attractive statistical graphics. Documentation Online documentation is available at seaborn.pydata.org. We can install the seaborn package by running the below command . pip install seaborn Kindly ensure that you have pip installed on your device before running this command . For Python 3 , we can use the pip3 command instead of pip. We can also specify the required version of the module we wish to install, as shown below. pip3 install seaborn = = 0 . 9 . 0 The pip show seaborn command will either state that the package is not installed or show a bunch of information about the package, including the location where the package is installed. # Make sure your IDE is using the correct Python version If the package is not installed, make sure your IDE is using the correct version of Python. How can I Install a Python module within code? Ask Question Asked 11 years, 5 months ago Modified 8 months ago Viewed 552k times 503 I need to install a package from PyPI straight within my script. Getting Started First of all, let us install Seaborn. Seaborn can be installed using the pip. Type the below command in the terminal. pip install seaborn In the terminal, it will look like this - After the installation is completed you will get a successfully installed message at the end of the terminal as shown below. Thought:Based on the search results, the correct way to install the seaborn module is by using the pip command . I will now install seaborn using the pip command . Action: { " action " : " Python_REPL " , " action_input " : " !pip install seaborn " } Observation: SyntaxError ( ' invalid syntax ' , ( ' <string> ' , 1 , 1 , ' !pip install seaborn\n ' , 1 , 2 )) Thought:I apologize for the repeated mistake. It seems that I am unable to install the seaborn module using the pip command in this environment. However, I can still analyze the dataset using other available tools and libraries. I will proceed with analyzing the dataset without using seaborn. ãŸãšã æ€èšŒçµæ çæAIã¯äžè¬ã«ç¢ºççã«ããŒã¿ãçæãããããè«ççãªæèãããŒã¿åæã®ãããªæ°å€èšç®ã¯èŠæã§ãã ããããä»åæ€èšŒããããã«çæAIã®Agentã« ReAct ã®ãããªæšè«ãã¬ãŒã ã¯ãŒã¯ãšPythonã³ãŒãçæã»å®è¡ãããããŒã«ãçµã¿åãããããšã§ãè«ççæèãæ°å€èšç®ãå¿
èŠãªããŒã¿åæçã®ã¿ã¹ã¯ãå®è¡ã§ãã ããã«ãªããŸããAgentã«ããåæã人ã«ããåæãšæ¯èŒããŠãåŠ¥åœæ§ã®é«ããã®ã§ããã ãŸããçæããPythonã®ã³ãŒãã§ãšã©ãŒãçºçããéã«æ€çŽ¢ã®ããŒã«ã䜿ã£ãŠããšã©ãŒã®è§£æ±ºçãæ€çŽ¢ãã«è¡ããªã©èšæ©å¿å€ãªå¯Ÿå¿ãããŠããŸããã æ³å®å€ã®äºæ
ãèµ·ããŠããèšç»ã倿ŽãããŒã«ã䜿ãåããŠå¯Ÿå¿ã§ããç¹ããæšè«ãšè¡åãç¹°ãè¿ãReActã®Agentã®åŒ·ã¿ ãšèšããŸãã Code Interpreterãšã®æ¯èŒ OpenAIã®Code Interpreterã§ã¯ããã»ã©æšè«ãšè¡åãç¹°ãè¿ããŠã¿ã¹ã¯ãå®è¡ããããšã¯ãããŸããããšã©ãŒè§£æ±ºã®ããã«ã€ã³ã¿ãŒãããã§æ€çŽ¢ãããªã©ã®èšæ©å¿å€ãªå¯Ÿå¿ãã§ããŸãããããããã€ã³ã¿ãŒãããçã®å€éšç°å¢ã«ã¢ã¯ã»ã¹ãã§ããŸãããäžèšã®ç¹ãããä»åã®ãããªAgentã®å®è£
ã«åªäœæ§ããããŸãã éã«ãããšAgentã¯è¡åãäºæž¬ãã¥ãããè¡ååæ°ãå¢ããŠè¿çãŸã§æéãããã£ãããGPT-4 Turboã®åŒã³åºãåæ°ãå¢å ããŠé«ã³ã¹ãã«ãªãå¯èœæ§ããããŸããèŠä»¶ã«å¿ããŠæå€§è¡ååæ°ãèšå®ããçã®å¯Ÿçããããšè¯ããšæããŸãã ä»åŸã«åã㊠æ¡ä»¶ã§ã¯ãçæAIã§RAGãçšããŠãã©ã€ããŒãããŒã¿ã®å®æ§çãªåæãããåŸããã宿§çãªåæãå
ã«å®éçãªåæãããŸããä»åã®æ€èšŒãããè€éã§é«ãç²ŸåºŠãæ±ããããã®ã§ä»åŸãæ¹è¯ãå¿
èŠã§ããä»åã¯åäžã®Agentã§å®è£
ããŸããããä»åŸã¯è€æ°ã®Agentã䜿ã£ãæ§æã詊ããããšæããŸãããã«ããšãŒãžã§ã³ããšåŒã°ãããè€æ°ã®ç°ãªã圹å²ãæã£ããšãŒãžã§ã³ããååããã·ã¹ãã ãã BabyAGI ãªã©ã®é«åºŠãªèªåŸãšãŒãžã§ã³ããæ€èšŒããé«ç²ŸåºŠã§ããè€éãªã¿ã¹ã¯ãžå¯èœãªã·ã¹ãã ãå®è£
ããããšæããŸãã ææ³ çæAIã®Agentã䜿ã£ãããŒã¿åæãããŠã¿ãŸãããã ReAct ã®è«ççæèã«ã¯é©ããããŸãããç¹ã«ãAgentãçæããPythonã®ã³ãŒãã§ãšã©ãŒãçºçããéã«æ€çŽ¢ãå§ããæã«ã¯ããããªããšãã§ããã®ããšéåžžã«é©ããŸããã æè¿ã§ã¯ãè€æ°ã®ç°ãªã圹å²ãæã£ããšãŒãžã§ã³ããååãããã«ããšãŒãžã§ã³ãçãè€éãªã¿ã¹ã¯ã«å¯Ÿå¿ã§ããã¢ãŒããã¯ãã£ãæµè¡ã£ãŠããŸãããŸããæè¿ã®LLMã¯ãã«ãã¢ãŒãã«ïŒããã¹ãã ãã§ãªããç»åãé³å£°ãåç»ãªã©æ§ã
ãªããŒã¿åœ¢åŒã«å¯Ÿå¿ããã¢ãã«ïŒã«ããªã£ãŠããŠããŸãã ãã«ãã¢ãŒãã«ãšãã«ããšãŒãžã§ã³ããçµã¿åããããšããªãå¹
åºãã¿ã¹ã¯ãã§ããããã«ãªã ã®ã§ã¯ãªãããšæããŸãã éçãè¶ããŠé²åãç¶ããçæAIã¯ãéåžžã«é¢çœãã®ã§ä»åŸãç©æ¥µçã«é¢ãã£ãŠããããšæããŸãïŒ æ¬èšäºãã©ãªããã®åœ¹ã«ç«ãŠã°å¹žãã§ãïŒ