单页网站 开元,wordpress博客小工具标签,酒类网站建,怎样设计网站版面本教程将介绍如何使用LangChain库和chatglm API来解决一个4x4的数独问题。我们将通过以下步骤实现这一目标#xff1a;
初始化chatglm 的聊天模型。定义数独问题和解决方案。创建一个自定义的检查器来验证每一步的思考。使用ToTChain来运行整个思考过程。
1. 初始化chatglm4…本教程将介绍如何使用LangChain库和chatglm API来解决一个4x4的数独问题。我们将通过以下步骤实现这一目标
初始化chatglm 的聊天模型。定义数独问题和解决方案。创建一个自定义的检查器来验证每一步的思考。使用ToTChain来运行整个思考过程。
1. 初始化chatglm4 的聊天模型
首先我们需要导入langchain_openai库中的ChatOpenAI类并初始化一个聊天模型实例。
from langchain_openai import ChatOpenAIllm ChatOpenAI(temperature1,modelGLM-4-Plus,openai_api_keyyour api key,openai_api_basehttps://open.bigmodel.cn/api/paas/v4/,max_tokens512,
)2. 定义数独问题和解决方案
接下来我们定义一个4x4的数独问题和其解决方案并生成问题描述。
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)输出结果如下
3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1- 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.3. 创建自定义检查器
我们需要创建一个自定义的检查器MyChecker用于验证每一步的思考是否有效。
import re
from typing import Tuplefrom langchain_experimental.tot.checker import ToTChecker
from langchain_experimental.tot.thought import ThoughtValidityclass 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_FINALelif re.search(regex_solution, sudoku_solution):return ThoughtValidity.VALID_INTERMEDIATEelse:return ThoughtValidity.INVALID4. 测试检查器
我们可以通过一些断言来测试检查器的功能。
checker MyChecker()
assert (checker.evaluate(, (3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1,)) ThoughtValidity.VALID_INTERMEDIATE
)
assert (checker.evaluate(, (3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1,)) ThoughtValidity.VALID_FINAL
)
assert (checker.evaluate(, (3,4,1,2|1,2,3,4|2,1,4,3|4,3,*,1,)) ThoughtValidity.VALID_INTERMEDIATE
)
assert (checker.evaluate(, (3,4,1,2|1,2,3,4|2,1,4,3|4,*,3,1,)) ThoughtValidity.INVALID
)5. 运行ToTChain
最后我们使用ToTChain来运行整个思考过程并尝试解决数独问题。
from langchain_experimental.tot.base import ToTChaintot_chain ToTChain(llmllm, checkerMyChecker(), k30, c5, verboseTrue, verbose_llmFalse
)
tot_chain.run(problem_descriptionproblem_description)输出结果如下
C:\Users\32564\AppData\Local\Temp\ipykernel_5080\1223294212.py:6: LangChainDeprecationWarning: The method Chain.run was deprecated in langchain 0.1.0 and will be removed in 1.0. Use :meth:~invoke instead.tot_chain.run(problem_descriptionproblem_description)
d:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([1m Entering new ToTChain chain...[0m
Starting the ToT solve procedure.
[33;1m[1;3mThought: 3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([31;1m[1;3m Thought: 3,1,*,2|1,*,3,*|*,1,*,3|4,*,*,1
[0m[31;1m[1;3m Thought: 3,*,4,2|1,*,3,*|*,1,*,3|4,*,*,1
[0m[33;1m[1;3m Thought: 3,*,*,2|1,2,3,*|*,1,*,3|4,*,*,1
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([33;1m[1;3m Thought: 3,*,*,2|1,2,3,4|*,1,*,3|4,*,*,1
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([33;1m[1;3m Thought: 3,*,*,2|1,2,3,4|2,1,*,3|4,*,*,1
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([33;1m[1;3m Thought: 3,*,*,2|1,2,3,4|2,1,4,3|4,*,*,1
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([33;1m[1;3m Thought: 3,*,*,2|1,2,3,4|2,1,4,3|4,3,*,1
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([33;1m[1;3m Thought:
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([33;1m[1;3m Thought:
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([33;1m[1;3m Thought: 3,*,*,2|1,2,3,4|2,1,4,3|4,3,2,1
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([33;1m[1;3m Thought: 3,*,*,2|1,2,3,4|2,1,4,3|4,3,2,1
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([31;1m[1;3m Thought: 3,1,*,2|1,2,3,4|2,1,4,3|4,3,2,1
[0m[33;1m[1;3m Thought: 3,4,*,2|1,2,3,4|2,1,4,3|4,3,2,1
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([33;1m[1;3m Thought:
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([33;1m[1;3m Thought:
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([33;1m[1;3m Thought:
[0md:\soft\anaconda\envs\langchain\Lib\site-packages\langchain\chains\llm.py:341: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.warnings.warn([32;1m[1;3m Thought: 3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1
[0m
[1m Finished chain.[0m3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1通过以上步骤我们成功地使用LangChain解决了一个4x4的数独问题。希望这个教程对你有所帮助如果有任何问题欢迎随时提问。
