langchain/docs/extras/use_cases/graph/tot.ipynb
2023-07-30 21:08:11 -07:00

240 lines
7.8 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Tree of Thought (ToT) example\n",
"\n",
"The Tree of Thought (ToT) is a chain that allows you to query a Large Language Model (LLM) using the Tree of Thought technique. This is based on the paper [\"Large Language Model Guided Tree-of-Thought\"](https://arxiv.org/pdf/2305.08291.pdf)"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/harrisonchase/.pyenv/versions/3.9.1/envs/langchain/lib/python3.9/site-packages/deeplake/util/check_latest_version.py:32: UserWarning: A newer version of deeplake (3.6.13) is available. It's recommended that you update to the latest version using `pip install -U deeplake`.\n",
" warnings.warn(\n"
]
}
],
"source": [
"from langchain.llms import OpenAI\n",
"\n",
"llm = OpenAI(temperature=1, max_tokens=512, model=\"text-davinci-003\")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\n",
"\n",
"- This is a 4x4 Sudoku puzzle.\n",
"- The * represents a cell to be filled.\n",
"- The | character separates rows.\n",
"- At each step, replace one or more * with digits 1-4.\n",
"- There must be no duplicate digits in any row, column or 2x2 subgrid.\n",
"- Keep the known digits from previous valid thoughts in place.\n",
"- Each thought can be a partial or the final solution.\n"
]
}
],
"source": [
"sudoku_puzzle = \"3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\"\n",
"sudoku_solution = \"3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1\"\n",
"problem_description = f\"\"\"\n",
"{sudoku_puzzle}\n",
"\n",
"- This is a 4x4 Sudoku puzzle.\n",
"- The * represents a cell to be filled.\n",
"- The | character separates rows.\n",
"- At each step, replace one or more * with digits 1-4.\n",
"- There must be no duplicate digits in any row, column or 2x2 subgrid.\n",
"- Keep the known digits from previous valid thoughts in place.\n",
"- Each thought can be a partial or the final solution.\n",
"\"\"\".strip()\n",
"print(problem_description)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Rules Based Checker\n",
"\n",
"Each thought is evaluated by the thought checker and is given a validity type: valid, invalid or partial. A simple checker can be rule based. For example, in the case of a sudoku puzzle, the checker can check if the puzzle is valid, invalid or partial.\n",
"\n",
"In the following code we implement a simple rule based checker for a specific 4x4 sudoku puzzle.\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"from typing import Tuple\n",
"from langchain_experimental.tot.checker import ToTChecker\n",
"from langchain_experimental.tot.thought import ThoughtValidity\n",
"import re\n",
"\n",
"class MyChecker(ToTChecker):\n",
" def evaluate(self, problem_description: str, thoughts: Tuple[str, ...] = ()) -> ThoughtValidity:\n",
" last_thought = thoughts[-1]\n",
" clean_solution = last_thought.replace(\" \", \"\").replace('\"', \"\")\n",
" regex_solution = clean_solution.replace(\"*\", \".\").replace(\"|\", \"\\\\|\")\n",
" if sudoku_solution in clean_solution:\n",
" return ThoughtValidity.VALID_FINAL\n",
" elif re.search(regex_solution, sudoku_solution):\n",
" return ThoughtValidity.VALID_INTERMEDIATE\n",
" else:\n",
" return ThoughtValidity.INVALID"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Just testing the MyChecker class above:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"checker = MyChecker()\n",
"assert checker.evaluate(\"\", (\"3,*,*,2|1,*,3,*|*,1,*,3|4,*,*,1\",)) == ThoughtValidity.VALID_INTERMEDIATE\n",
"assert checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1\",)) == ThoughtValidity.VALID_FINAL\n",
"assert checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,3,*,1\",)) == ThoughtValidity.VALID_INTERMEDIATE\n",
"assert checker.evaluate(\"\", (\"3,4,1,2|1,2,3,4|2,1,4,3|4,*,3,1\",)) == ThoughtValidity.INVALID"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Tree of Thought Chain\n",
"\n",
"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`."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ToTChain chain...\u001b[0m\n",
"Starting the ToT solve procedure.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/harrisonchase/workplace/langchain/libs/langchain/langchain/chains/llm.py:275: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[31;1m\u001b[1;3mThought: 3*,*,2|1*,3,*|*,1,*,3|4,*,*,1\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3*,1,2|1*,3,*|*,1,*,3|4,*,*,1\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3*,1,2|1*,3,4|*,1,*,3|4,*,*,1\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3*,1,2|1*,3,4|*,1,2,3|4,*,*,1\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3*,1,2|1*,3,4|2,1,*,3|4,*,*,1\n",
"\u001b[0m"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Type <enum 'ThoughtValidity'> not serializable\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[31;1m\u001b[1;3mThought: 3,*,*,2|1,*,3,*|*,1,*,3|4,1,*,*\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3,*,*,2|*,3,2,*|*,1,*,3|4,1,*,*\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3,2,*,2|1,*,3,*|*,1,*,3|4,1,*,*\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3,2,*,2|1,*,3,*|1,1,*,3|4,1,*,*\n",
"\u001b[0m\u001b[31;1m\u001b[1;3mThought: 3,2,*,2|1,1,3,*|1,1,*,3|4,1,*,*\n",
"\u001b[0m\u001b[33;1m\u001b[1;3mThought: 3,*,*,2|1,2,3,*|*,1,*,3|4,*,*,1\n",
"\u001b[0m\u001b[31;1m\u001b[1;3m Thought: 3,1,4,2|1,2,3,4|2,1,4,3|4,3,2,1\n",
"\u001b[0m\u001b[32;1m\u001b[1;3m Thought: 3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1\n",
"\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'3,4,1,2|1,2,3,4|2,1,4,3|4,3,2,1'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain_experimental.tot.base import ToTChain\n",
"\n",
"tot_chain = ToTChain(llm=llm, checker=MyChecker(), k=30, c=5, verbose=True, verbose_llm=False)\n",
"tot_chain.run(problem_description=problem_description)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}