久久精品国产精品青草图片,亚洲精品国产福利在线观看,久久亚洲国产欧洲精品一

? ? ? ?當解決具體問題時，這些模塊與LLM進行多輪對話。這是基于LLM的自治代理的典型情況，其中動態創建鏈并按順序執行，同時多次輪詢LLM。

? ? ? ?下圖是LangSmith[1]的界面，從圖中可以看到使用的tokens總數以及兩個延遲類別。

? ? ? ?此圖顯示了Trace部分，其中包含為該代理創建的完整鏈，以及輸入和輸出。LangSmith在鏈的每一步都給出了詳細的分解，包括成本（tokens）和延遲。

會話和狀態歷史記錄（上下文）存儲在內存模塊中，這使代理可以參考思維過程的先前部分，并可能從歷史記憶采取不同的路線。

為了驗證ToT技術的有效性，本文實現了一個基于ToT的代理來解決數獨難題。

? ? ? ?論文指出的一個漏洞是LLM是基于前面的序列生成內容，而忽略了向后編輯。然而，當我們人類解決一個問題時，如果派生的步驟不正確，我們很可能會回溯到以前的迭代。這種回溯方法否定了LLM達到不確定或無答案場景的危險。

? ? ? ?其次，為了建立確保正確性，我們人類的一種做法是在解決問題的每一步都進行測試，這確保了最終解決方案的可信度。本文統計了自回歸語言模型在基于以前的token生成新token時，不會顯式執行邏輯正確性檢查，這限制了LLM糾正自身錯誤的能力。隨著模型生成更多的tokens，一個小錯誤可能會被放大，這通常被稱為級聯。因此這會導致生成質量下降，并使其難以從錯誤中恢復。級聯很早就被認為是手動創建提示鏈的一種危險。然而，考慮到自主代理在運行中創建了一系列提示，它仍然容易受到級聯的影響。

上圖顯示了四種方法的成功率：zero-shot（zs）、one-shot（os）、few-shot（fs）和Tree-of-Thought（tot）。

? ? ? ?以下是ToT代理的完整代碼，您可以將其復制并粘貼到筆記本中。您需要更新的只是OpenAI API密鑰和LangSmith API密鑰。

pip install langchainpip install langchain_experimentalpip install -U langsmithpip install openai ####### import osfrom uuid import uuid4 unique_id = uuid4().hex[0:8]os.environ["LANGCHAIN_TRACING_V2"] = "true"os.environ["LANGCHAIN_PROJECT"] = f"Agent Tot"os.environ["LANGCHAIN_ENDPOINT"] = "https://api.smith.langchain.com"os.environ["LANGCHAIN_API_KEY"] = "xxxxxxxxxxxxxxxxxxxxxxxx"os.environ['OPENAI_API_KEY'] = str("xxxxxxxxxxxxxxxxxxxxxxxx") ####### from langchain.llms import OpenAIllm = OpenAI(temperature=1, max_tokens=512, model="text-davinci-003") ####### sudoku_puzzle = "3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1"sudoku_solution = "3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1"problem_description = f"""{sudoku_puzzle} - This is a 4x4 Sudoku puzzle.- The * represents a cell to be filled.- The | character separates rows.- At each step, replace one or more * with digits 1-4.- There must be no duplicate digits in any row, column or 2x2 subgrid.- Keep the known digits from previous valid thoughts in place.- Each thought can be a partial or the final solution.""".strip()print(problem_description) ######## The following code implement a simple rule based checker for # a specific 4x4 sudoku puzzle.####### from typing import Tuplefrom langchain_experimental.tot.checker import ToTCheckerfrom langchain_experimental.tot.thought import ThoughtValidityimport re class MyChecker(ToTChecker): def evaluate(self, problem_description: str, thoughts: Tuple[str, ...] = ()) -> ThoughtValidity: last_thought = thoughts[-1] clean_solution = last_thought.replace(" ", "").replace('"', "") regex_solution = clean_solution.replace("*", ".").replace("|", "\\|") if sudoku_solution in clean_solution: return ThoughtValidity.VALID_FINAL elif re.search(regex_solution, sudoku_solution): return ThoughtValidity.VALID_INTERMEDIATE else: return ThoughtValidity.INVALID ######## Testing the MyChecker class above:####### checker = MyChecker()assert checker.evaluate("", ("3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1",)) == ThoughtValidity.VALID_INTERMEDIATEassert checker.evaluate("", ("3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1",)) == ThoughtValidity.VALID_FINALassert checker.evaluate("", ("3,4,1,2|1,2,3,4|2,1,4,3|4,3,*,1",)) == ThoughtValidity.VALID_INTERMEDIATEassert checker.evaluate("", ("3,4,1,2|1,2,3,4|2,1,4,3|4,*,3,1",)) == ThoughtValidity.INVALID ######## Initialize and run the ToT chain, # with maximum number of interactions k set to 30 and # the maximum number child thoughts c set to 8.####### from langchain_experimental.tot.base import ToTChain tot_chain = ToTChain(llm=llm, checker=MyChecker(), k=30, c=5, verbose=True, verbose_llm=False)tot_chain.run(problem_description=problem_description) #######

> Entering new ToTChain chain...Starting the ToT solve procedure./usr/local/lib/python3.10/dist-packages/langchain/chains/llm.py:278: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain. warnings.warn(Thought: 3,4,*,2|1,*,3,*|*,1,*,3|4,*,*,1 Thought: 3,4,1,2|1,*,3,*|*,1,*,3|4,*,*,1 Thought: 3,4,1,2|1,2,3,*|*,1,*,3|4,*,*,1 Thought: 3,4,1,2|1,2,3,4|*,1,*,3|4,*,*,1 Thought: 3,4,1,2|1,2,3,*|1,1,*,3|4,*,*,1 Thought: 3,4,1,2|1,2,3,*|*,2,*,3|4,*,*,1 Thought: 3,4,1,2|1,2,3,*|*,1,1,3|4,*,*,1 Thought: 3,4,1,2|1,2,3,*|*,1,*,4|4,*,*,1 Thought: 3,4,1,2|1,2,3,*|*,1,*,1|4,4,*,1 Thought: 3,4,1,2|1,2,3,*|1,1,*,3|4,*,*,1 Thought: 3,4,1,2|1,2,3,*|*,1,2,3|4,*,*,1 Thought: 3,4,1,2|1,2,3,*|*,1,*,3|4,1,*,1 Thought: 3,4,1,2|1,2,3,*|*,1,*,3|4,*,1,1 Thought: 3,4,1,2|1,*,3,4|*,1,*,3|4,*,*,1 Thought: 3,4,1,2|1,2,3,4|*,1,*,3|4,*,*,1 Thought: 3,4,1,2|1,2,3,4|2,1,*,3|4,*,*,1 Thought: 3,4,1,2|1,2,3,4|2,1,4,3|4,*,*,1 Thought: 3,4,1,2|1,2,3,4|2,1,4,3|4,1,*,* Thought: 3,4,1,2|1,2,3,4|2,1,4,3|4,2,*,* Thought: 3,4,1,2|1,2,3,4|2,1,4,3|4,3,*,* Thought: 3,4,1,2|1,2,3,4|2,1,4,3|4,3,1,* Thought: 3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,* Thought: 3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1 > Finished chain.3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1

[3]?https://cobusgreyling.medium.com/langchain-langsmith-llm-guided-tree-of-thought-47a2cd5bcfca