"'Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable and easier to accomplish. This process can be done using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in thinking step by step or exploring multiple reasoning possibilities at each step. Task decomposition can be facilitated by providing simple prompts to a language model, task-specific instructions, or human inputs.'"
"'Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable and easier to accomplish. This process can be done using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in breaking down tasks effectively. Task decomposition can be facilitated by providing simple prompts to a language model, task-specific instructions, or human inputs.'"
]
},
"execution_count": 7,
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
@ -369,17 +371,17 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 11,
"id": "0e89c75f-7ad7-4331-a2fe-57579eb8f840",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Task decomposition can be achieved through various methods, including using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in breaking down complex tasks into smaller steps. Common ways of task decomposition include providing simple prompts to a language model, task-specific instructions tailored to the specific task at hand, or incorporating human inputs to guide the decomposition process effectively.'"
"'Task decomposition can be achieved through various methods, including using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in breaking down tasks effectively. Common ways of task decomposition include providing simple prompts to a language model, task-specific instructions, or human inputs to break down complex tasks into smaller and more manageable steps. Additionally, task decomposition can involve utilizing resources like internet access for information gathering, long-term memory management, and GPT-3.5 powered agents for delegation of simple tasks.'"
]
},
"execution_count": 8,
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
@ -401,7 +403,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 12,
"id": "7686b874-3a85-499f-82b5-28a85c4c768c",
"metadata": {},
"outputs": [
@ -411,11 +413,11 @@
"text": [
"User: What is Task Decomposition?\n",
"\n",
"AI: Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable and easier to accomplish. This process can be done using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in thinking step by step or exploring multiple reasoning possibilities at each step. Task decomposition can be facilitated by providing simple prompts to a language model, task-specific instructions, or human inputs.\n",
"AI: Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable and easier to accomplish. This process can be done using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in breaking down tasks effectively. Task decomposition can be facilitated by providing simple prompts to a language model, task-specific instructions, or human inputs.\n",
"\n",
"User: What are common ways of doing it?\n",
"\n",
"AI: Task decomposition can be achieved through various methods, including using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in breaking down complex tasks into smaller steps. Common ways of task decomposition include providing simple prompts to a language model, task-specific instructions tailored to the specific task at hand, or incorporating human inputs to guide the decomposition process effectively.\n",
"AI: Task decomposition can be achieved through various methods, including using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide the model in breaking down tasks effectively. Common ways of task decomposition include providing simple prompts to a language model, task-specific instructions, or human inputs to break down complex tasks into smaller and more manageable steps. Additionally, task decomposition can involve utilizing resources like internet access for information gathering, long-term memory management, and GPT-3.5 powered agents for delegation of simple tasks.\n",
"\n"
]
}
@ -452,7 +454,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 13,
"id": "71c32048-1a41-465f-a9e2-c4affc332fd9",
"metadata": {},
"outputs": [],
@ -552,17 +554,17 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 14,
"id": "6d0a7a73-d151-47d9-9e99-b4f3291c0322",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable. This process helps agents or models tackle difficult tasks by dividing them into more easily achievable subgoals. Task decomposition can be done through techniques like Chain of Thought or Tree of Thoughts, which guide the model in thinking step by step or exploring multiple reasoning possibilities at each step.'"
"'Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable. Techniques like Chain of Thought (CoT) and Tree of Thoughts help in decomposing hard tasks into multiple manageable tasks by instructing models to think step by step and explore multiple reasoning possibilities at each step. Task decomposition can be achieved through various methods such as using prompting techniques, task-specific instructions, or human inputs.'"
]
},
"execution_count": 2,
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
@ -578,17 +580,17 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 15,
"id": "17021822-896a-4513-a17d-1d20b1c5381c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"Common ways of task decomposition include using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide models in breaking down complex tasks into smaller steps. This can be achieved through simple prompting with LLMs, task-specific instructions, or human inputs to help the model understand and navigate the task effectively. Task decomposition aims to enhance model performance on complex tasks by utilizing more test-time computation and shedding light on the model's thinking process.\""
"'Task decomposition can be done in common ways such as using prompting techniques like Chain of Thought (CoT) or Tree of Thoughts, which instruct models to think step by step and explore multiple reasoning possibilities at each step. Another way is to provide task-specific instructions, such as asking to \"Write a story outline\" for writing a novel, to guide the decomposition process. Additionally, task decomposition can also involve human inputs to break down complex tasks into smaller and simpler steps.'"
"Error in LangChainTracer.on_tool_end callback: TracerException(\"Found chain run at ID 5cd28d13-88dd-4eac-a465-3770ac27eff6, but expected {'tool'} run.\")\n"
"{'action': {'messages': [ToolMessage(content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\n(3) Task execution: Expert models execute on the specific tasks and log results.\\nInstruction:\\n\\nWith the input and the inference results, the AI assistant needs to describe the process and results. The previous stages can be formed as - User Input: {{ User Input }}, Task Planning: {{ Tasks }}, Model Selection: {{ Model Assignment }}, Task Execution: {{ Predictions }}. You must first answer the user\\'s request in a straightforward manner. Then describe the task process and show your analysis and model inference results to the user in the first person. If inference results contain a file path, must tell the user the complete file path.\\n\\nFig. 11. Illustration of how HuggingGPT works. (Image source: Shen et al. 2023)\\nThe system comprises of 4 stages:\\n(1) Task planning: LLM works as the brain and parses the user requests into multiple tasks. There are four attributes associated with each task: task type, ID, dependencies, and arguments. They use few-shot examples to guide LLM to do task parsing and planning.\\nInstruction:', name='blog_post_retriever', id='9c3a17f7-653c-47fa-b4e4-fa3d8d24c85d', tool_call_id='call_wxRrUmNbaNny8wh9JIb5uCRB')]}}\n",
"{'tools': {'messages': [ToolMessage(content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nFig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.', name='blog_post_retriever', tool_call_id='call_TbhPPPN05GKi36HLeaN4QM90')]}}\n",
"----\n",
"{'agent': {'messages': [AIMessage(content='Task decomposition is a technique used to break down complex tasks into smaller and simpler steps. This approach helps agents in planning and executing tasks more effectively. One common method for task decomposition is the Chain of Thought (CoT) technique, where models are instructed to think step by step to decompose hard tasks into manageable steps. Another extension of CoT is the Tree of Thoughts, which explores multiple reasoning possibilities at each step by creating a tree structure of thought steps.\\n\\nTask decomposition can be achieved through various methods, such as using language models with simple prompting, task-specific instructions, or human inputs. By breaking down tasks into smaller components, agents can better plan and execute tasks efficiently.\\n\\nIf you would like more detailed information or examples on task decomposition, feel free to ask!', response_metadata={'token_usage': {'completion_tokens': 154, 'prompt_tokens': 588, 'total_tokens': 742}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'stop', 'logprobs': None}, id='run-8991fa20-c527-4f9e-a058-fc6264fe6259-0')]}}\n",
"{'agent': {'messages': [AIMessage(content='Task decomposition is a technique used to break down complex tasks into smaller and simpler steps. This approach helps in transforming big tasks into multiple manageable tasks, making it easier for autonomous agents to handle and interpret the thinking process. One common method for task decomposition is the Chain of Thought (CoT) technique, where models are instructed to \"think step by step\" to decompose hard tasks. Another extension of CoT is the Tree of Thoughts, which explores multiple reasoning possibilities at each step by creating a tree structure of multiple thoughts per step. Task decomposition can be facilitated through various methods such as using simple prompts, task-specific instructions, or human inputs.', response_metadata={'token_usage': {'completion_tokens': 130, 'prompt_tokens': 636, 'total_tokens': 766}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-3ef17638-65df-4030-a7fe-795e6da91c69-0')]}}\n",
"{'agent': {'messages': [AIMessage(content='Hello Bob! How can I assist you today?', response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 67, 'total_tokens': 78}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'stop', 'logprobs': None}, id='run-1451e59b-b135-4776-985d-4759338ffee5-0')]}}\n",
"{'agent': {'messages': [AIMessage(content='Hello Bob! How can I assist you today?', response_metadata={'token_usage': {'completion_tokens': 11, 'prompt_tokens': 67, 'total_tokens': 78}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-1cd17562-18aa-4839-b41b-403b17a0fc20-0')]}}\n",
"----\n"
]
}
@ -766,19 +773,26 @@
},
{
"cell_type": "code",
"execution_count": 23,
"execution_count": 21,
"id": "e2c570ae-dd91-402c-8693-ae746de63b16",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Error in LangChainTracer.on_tool_end callback: TracerException(\"Found chain run at ID c54381c0-c5d9-495a-91a0-aca4ae755663, but expected {'tool'} run.\")\n"
"{'action': {'messages': [ToolMessage(content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\n(3) Task execution: Expert models execute on the specific tasks and log results.\\nInstruction:\\n\\nWith the input and the inference results, the AI assistant needs to describe the process and results. The previous stages can be formed as - User Input: {{ User Input }}, Task Planning: {{ Tasks }}, Model Selection: {{ Model Assignment }}, Task Execution: {{ Predictions }}. You must first answer the user\\'s request in a straightforward manner. Then describe the task process and show your analysis and model inference results to the user in the first person. If inference results contain a file path, must tell the user the complete file path.\\n\\nFig. 11. Illustration of how HuggingGPT works. (Image source: Shen et al. 2023)\\nThe system comprises of 4 stages:\\n(1) Task planning: LLM works as the brain and parses the user requests into multiple tasks. There are four attributes associated with each task: task type, ID, dependencies, and arguments. They use few-shot examples to guide LLM to do task parsing and planning.\\nInstruction:', name='blog_post_retriever', id='e0895fa5-5d41-4be0-98db-10a83d42fc2f', tool_call_id='call_ab2x4iUPSWDAHS5txL7PspSK')]}}\n",
"{'tools': {'messages': [ToolMessage(content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nFig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.', name='blog_post_retriever', tool_call_id='call_rg7zKTE5e0ICxVSslJ1u9LMg')]}}\n",
"----\n",
"{'agent': {'messages': [AIMessage(content='Task decomposition is a technique used in complex tasks where the task is broken down into smaller and simpler steps. This approach helps in managing and solving difficult tasks by dividing them into more manageable components. One common method for task decomposition is the Chain of Thought (CoT) technique, which prompts the model to think step by step and decompose hard tasks into smaller steps. Another extension of CoT is the Tree of Thoughts, which explores multiple reasoning possibilities at each step by creating a tree structure of thought steps.\\n\\nTask decomposition can be achieved through various methods, such as using language models with simple prompting, task-specific instructions, or human inputs. By breaking down tasks into smaller components, agents can better plan and execute complex tasks effectively.\\n\\nIf you would like more detailed information or examples related to task decomposition, feel free to ask!', response_metadata={'token_usage': {'completion_tokens': 165, 'prompt_tokens': 611, 'total_tokens': 776}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'stop', 'logprobs': None}, id='run-13296566-8577-4d65-982b-a39718988ca3-0')]}}\n",
"{'agent': {'messages': [AIMessage(content='Task decomposition is a technique used to break down complex tasks into smaller and simpler steps. This approach helps in managing and solving intricate problems by dividing them into more manageable components. By decomposing tasks, agents or models can better understand the steps involved and plan their actions accordingly. Techniques like Chain of Thought (CoT) and Tree of Thoughts are examples of methods that enhance model performance on complex tasks by breaking them down into smaller steps.', response_metadata={'token_usage': {'completion_tokens': 87, 'prompt_tokens': 659, 'total_tokens': 746}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-b9166386-83e5-4b82-9a4b-590e5fa76671-0')]}}\n",
"{'action': {'messages': [ToolMessage(content='Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\nFig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nResources:\\n1. Internet access for searches and information gathering.\\n2. Long Term memory management.\\n3. GPT-3.5 powered Agents for delegation of simple tasks.\\n4. File output.\\n\\nPerformance Evaluation:\\n1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.\\n2. Constructively self-criticize your big-picture behavior constantly.\\n3. Reflect on past decisions and strategies to refine your approach.\\n4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.\\n\\n(3) Task execution: Expert models execute on the specific tasks and log results.\\nInstruction:\\n\\nWith the input and the inference results, the AI assistant needs to describe the process and results. The previous stages can be formed as - User Input: {{ User Input }}, Task Planning: {{ Tasks }}, Model Selection: {{ Model Assignment }}, Task Execution: {{ Predictions }}. You must first answer the user\\'s request in a straightforward manner. Then describe the task process and show your analysis and model inference results to the user in the first person. If inference results contain a file path, must tell the user the complete file path.', name='blog_post_retriever', id='c749bb8e-c8e0-4fa3-bc11-3e2e0651880b', tool_call_id='call_KvoiamnLfGEzMeEMlV3u0TJ7')]}}\n",
"Error in LangChainTracer.on_tool_end callback: TracerException(\"Found chain run at ID 29553415-e0f4-41a9-8921-ba489e377f68, but expected {'tool'} run.\")\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'tools': {'messages': [ToolMessage(content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nFig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.', name='blog_post_retriever', tool_call_id='call_6kbxTU5CDWLmF9mrvR7bWSkI')]}}\n",
"----\n",
"{'agent': {'messages': [AIMessage(content='According to the blog post, common ways of task decomposition include:\\n\\n1. Using language models with simple prompting like \"Steps for XYZ\" or \"What are the subgoals for achieving XYZ?\"\\n2. Utilizing task-specific instructions, for example, using \"Write a story outline\" for writing a novel.\\n3. Involving human inputs in the task decomposition process.\\n\\nThese methods help in breaking down complex tasks into smaller and more manageable steps, facilitating better planning and execution of the overall task.', response_metadata={'token_usage': {'completion_tokens': 100, 'prompt_tokens': 1475, 'total_tokens': 1575}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'stop', 'logprobs': None}, id='run-98b765b3-f1a6-4c9a-ad0f-2db7950b900f-0')]}}\n",
"{'agent': {'messages': [AIMessage(content='Common ways of task decomposition include:\\n1. Using LLM with simple prompting like \"Steps for XYZ\" or \"What are the subgoals for achieving XYZ?\"\\n2. Using task-specific instructions, for example, \"Write a story outline\" for writing a novel.\\n3. Involving human inputs in the task decomposition process.', response_metadata={'token_usage': {'completion_tokens': 67, 'prompt_tokens': 1339, 'total_tokens': 1406}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-9ad14cde-ca75-4238-a868-f865e0fc50dd-0')]}}\n",
"{'agent': {'messages': [AIMessage(content=\"Hello Bob! Since you didn't ask a specific question, I don't need to use any tools to respond. It's nice to meet you. San Francisco is a wonderful city with lots to see and do. I hope you're enjoying living there. Please let me know if you have any other questions!\", response_metadata={'id': 'msg_01Mmfzfs9m4XMgVzsCZYMWqH', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 271, 'output_tokens': 65}}, id='run-44c57f9c-a637-4888-b7d9-6d985031ae48-0', usage_metadata={'input_tokens': 271, 'output_tokens': 65, 'total_tokens': 336})]}}\n",
"----\n",
"{'agent': {'messages': [AIMessage(content=[{'text': 'To get current weather information for your location in San Francisco, let me invoke the search tool:', 'type': 'text'}, {'id': 'toolu_01BGEyQaSz3pTq8RwUUHSRoo', 'input': {'query': 'san francisco weather'}, 'name': 'tavily_search_results_json', 'type': 'tool_use'}], response_metadata={'id': 'msg_013AVSVsRLKYZjduLpJBY4us', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 347, 'output_tokens': 80}}, id='run-de7923b6-5ee2-4ebe-bd95-5aed4933d0e3-0', tool_calls=[{'name': 'tavily_search_results_json', 'args': {'query': 'san francisco weather'}, 'id': 'toolu_01BGEyQaSz3pTq8RwUUHSRoo'}], usage_metadata={'input_tokens': 347, 'output_tokens': 80, 'total_tokens': 427})]}}\n",
"{'agent': {'messages': [AIMessage(content='Based on the search results, the current weather in San Francisco is:\\n\\nTemperature: 53.6°F (12°C)\\nConditions: Misty\\nWind: 5.6 mph (9 kph) from the Northwest\\nHumidity: 88%\\nCloud Cover: 100% \\n\\nThe results provide detailed information like wind chill, heat index, visibility and more. It looks like a typical cool, foggy morning in San Francisco. Let me know if you need any other details about the weather where you live!', response_metadata={'id': 'msg_019WGLbaojuNdbCnqac7zaGW', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 1035, 'output_tokens': 120}}, id='run-1bb68bf3-b212-4ef4-8a31-10c830421c78-0', usage_metadata={'input_tokens': 1035, 'output_tokens': 120, 'total_tokens': 1155})]}}\n",
"We first need to create the tools we want to use. Our main tool of choice will be [Tavily](/docs/integrations/tools/tavily_search) - a search engine. We have a built-in tool in LangChain to easily use Tavily search engine as tool.\n"
" 'content': 'San Francisco Temperature History May 2024. The daily range of reported temperatures (gray bars) and 24-hour highs (red ticks) and lows (blue ticks), placed over the daily average high (faint red line) and low (faint blue line) temperature, with 25th to 75th and 10th to 90th percentile bands.'}]"
" 'content': 'Current Weather for Popular Cities . San Francisco, CA 58 ° F Partly Cloudy; Manhattan, NY warning 51 ° F Cloudy; Schiller Park, IL (60176) warning 51 ° F Fair; Boston, MA warning 41 ° F ...'}]"
]
},
"execution_count": 3,
@ -207,24 +200,13 @@
}
],
"source": [
"search.invoke(\"what is the weather in SF\")"
]
},
{
"cell_type": "markdown",
"id": "c3b47c1d",
"metadata": {},
"source": [
"If we want, we can create other tools. Once we have all the tools we want, we can put them in a list that we will reference later."
" AIMessage(content='The current weather in San Francisco, California is partly cloudy with a temperature of 16.7°C (62.1°F). The wind is coming from the west at a speed of 20.2 kph (12.5 mph). The humidity is at 62%. [Source](https://www.weatherapi.com/)', response_metadata={'token_usage': {'completion_tokens': 67, 'prompt_tokens': 691, 'total_tokens': 758}, 'model_name': 'gpt-4', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-953864dd-9af6-48aa-bc61-8b63388fca03-0', usage_metadata={'input_tokens': 691, 'output_tokens': 67, 'total_tokens': 758})]"
"[HumanMessage(content='whats the weather in sf?', id='1d6c96bb-4ddb-415c-a579-a07d5264de0d'),\n",
" AIMessage(content='Based on the search results, here is a summary of the current weather in San Francisco:\\n\\nThe weather in San Francisco is currently misty with a temperature of around 53°F (12°C). There is complete cloud cover and moderate winds from the northwest around 5-9 mph (9-14 km/h). Humidity is high at 88%. Visibility is around 3 miles (6.4 km). \\n\\nThe results provide an hourly forecast as well as current conditions from a couple different weather sources. Let me know if you need any additional details about the San Francisco weather!', response_metadata={'id': 'msg_01BRX9mrT19nBDdHYtR7wJ92', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 920, 'output_tokens': 132}}, id='run-d0325583-3ddc-4432-b2b2-d023eb97660f-0', usage_metadata={'input_tokens': 920, 'output_tokens': 132, 'total_tokens': 1052})]"
"{'agent': {'messages': [AIMessage(content='Your name is Bob. How can I assist you further?', response_metadata={'token_usage': {'completion_tokens': 13, 'prompt_tokens': 154, 'total_tokens': 167}, 'model_name': 'gpt-4', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-e1181ba6-732d-4564-b479-9f1ab6bf01f6-0')]}}\n",
"{'agent': {'messages': [AIMessage(content='You mentioned your name is Bob when you introduced yourself earlier. So your name is Bob.', response_metadata={'id': 'msg_01WNwnRNGwGDRw6vRdivt6i1', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 1184, 'output_tokens': 21}}, id='run-f5c0b957-8878-405a-9d4b-a7cd38efe81f-0', usage_metadata={'input_tokens': 1184, 'output_tokens': 21, 'total_tokens': 1205})]}}\n",
"----\n"
]
}
@ -703,7 +683,7 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 15,
"id": "24460239",
"metadata": {},
"outputs": [
@ -711,7 +691,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"{'agent': {'messages': [AIMessage(content=\"As an AI, I don't have access to personal data about individuals unless it has been shared with me in the course of our conversation. I am designed to respect user privacy and confidentiality. So, I don't know your name.\", response_metadata={'token_usage': {'completion_tokens': 48, 'prompt_tokens': 86, 'total_tokens': 134}, 'model_name': 'gpt-4', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-b3c8d577-fdbf-4f0f-8fd8-ecb3a5ac8920-0', usage_metadata={'input_tokens': 86, 'output_tokens': 48, 'total_tokens': 134})]}}\n",
"{'agent': {'messages': [AIMessage(content=\"I'm afraid I don't actually know your name. As an AI assistant without personal information about you, I don't have a specific name associated with our conversation.\", response_metadata={'id': 'msg_01NoaXNNYZKSoBncPcLkdcbo', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 267, 'output_tokens': 36}}, id='run-c9f7df3d-525a-4d8f-bbcf-a5b4a5d2e4b0-0', usage_metadata={'input_tokens': 267, 'output_tokens': 36, 'total_tokens': 303})]}}\n",
"'Task decomposition involves breaking down complex tasks into smaller and simpler steps to make them more manageable. This process can be achieved through techniques like Chain of Thought (CoT) or Tree of Thoughts, which help agents plan and execute tasks effectively by dividing them into sequential subgoals. Task decomposition can be facilitated by using prompting techniques, task-specific instructions, or human inputs to guide the agent through the steps required to accomplish a task.'"
"\"Task decomposition involves breaking down complex tasks into smaller and simpler steps to make them more manageable for an agent or model. This process helps in guiding the agent through the various subgoals required to achieve the overall task efficiently. Different techniques like Chain of Thought and Tree of Thoughts can be used to decompose tasks into step-by-step processes, enhancing performance and understanding of the model's thinking process.\""
]
},
"execution_count": 4,
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
@ -278,7 +271,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 8,
"id": "2b685428-8b82-4af1-be4f-7232c5d55b73",
"metadata": {},
"outputs": [],
@ -322,7 +315,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 9,
"id": "66f275f3-ddef-4678-b90d-ee64576878f9",
"metadata": {},
"outputs": [],
@ -354,7 +347,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 10,
"id": "0005810b-1b95-4666-a795-08d80e478b83",
"metadata": {},
"outputs": [
@ -362,7 +355,7 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Task decomposition can be done in several common ways, such as using Language Model (LLM) with simple prompting like \"Steps for XYZ\" or asking for subgoals to achieve a specific task. Task-specific instructions can also be provided, like requesting a story outline for writing a novel. Additionally, human inputs can be utilized to decompose tasks into smaller components effectively.\n"
"Task decomposition can be achieved through various methods such as using techniques like Chain of Thought (CoT) or Tree of Thoughts to break down complex tasks into smaller steps. Common ways include prompting the model with simple instructions like \"Steps for XYZ\" or task-specific instructions like \"Write a story outline.\" Human inputs can also be used to guide the task decomposition process effectively.\n"
]
}
],
@ -421,7 +414,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 11,
"id": "9c3fb176-8d6a-4dc7-8408-6a22c5f7cc72",
"metadata": {},
"outputs": [],
@ -450,17 +443,17 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 12,
"id": "1046c92f-21b3-4214-907d-92878d8cba23",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Task decomposition involves breaking down complex tasks into smaller and simpler steps to make them more manageable for an agent or model. This process helps in guiding the agent through the various subgoals required to achieve the overall task efficiently. Different techniques like Chain of Thought and Tree of Thoughts can be used to decompose tasks into manageable components.'"
"'Task decomposition involves breaking down complex tasks into smaller and simpler steps to make them more manageable. Techniques like Chain of Thought (CoT) and Tree of Thoughts help models decompose hard tasks into multiple manageable subtasks. This process allows agents to plan ahead and tackle intricate tasks effectively.'"
]
},
"execution_count": 9,
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
@ -476,17 +469,17 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 13,
"id": "0e89c75f-7ad7-4331-a2fe-57579eb8f840",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Task decomposition can be achieved through various methods such as using prompting techniques like \"Steps for XYZ\" to guide the model through subgoals, providing task-specific instructions like \"Write a story outline\" for specific tasks, or incorporating human inputs to break down complex tasks. These approaches help in dividing a large task into smaller, more manageable components for better understanding and execution.'"
"'Task decomposition can be achieved through various methods such as using Language Model (LLM) with simple prompting, task-specific instructions tailored to the specific task at hand, or incorporating human inputs to break down the task into smaller components. These approaches help in guiding agents to think step by step and decompose complex tasks into more manageable subgoals.'"
]
},
"execution_count": 10,
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
@ -508,7 +501,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 14,
"id": "7686b874-3a85-499f-82b5-28a85c4c768c",
"metadata": {},
"outputs": [
@ -518,11 +511,11 @@
"text": [
"User: What is Task Decomposition?\n",
"\n",
"AI: Task decomposition involves breaking down complex tasks into smaller and simpler steps to make them more manageable for an agent or model. This process helps in guiding the agent through the various subgoals required to achieve the overall task efficiently. Different techniques like Chain of Thought and Tree of Thoughts can be used to decompose tasks into manageable components.\n",
"AI: Task decomposition involves breaking down complex tasks into smaller and simpler steps to make them more manageable. Techniques like Chain of Thought (CoT) and Tree of Thoughts help models decompose hard tasks into multiple manageable subtasks. This process allows agents to plan ahead and tackle intricate tasks effectively.\n",
"\n",
"User: What are common ways of doing it?\n",
"\n",
"AI: Task decomposition can be achieved through various methods such as using prompting techniques like \"Steps for XYZ\" to guide the model through subgoals, providing task-specific instructions like \"Write a story outline\" for specific tasks, or incorporating human inputs to break down complex tasks. These approaches help in dividing a large task into smaller, more manageable components for better understanding and execution.\n",
"AI: Task decomposition can be achieved through various methods such as using Language Model (LLM) with simple prompting, task-specific instructions tailored to the specific task at hand, or incorporating human inputs to break down the task into smaller components. These approaches help in guiding agents to think step by step and decompose complex tasks into more manageable subgoals.\n",
"\n"
]
}
@ -557,7 +550,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 15,
"id": "71c32048-1a41-465f-a9e2-c4affc332fd9",
"metadata": {},
"outputs": [],
@ -657,17 +650,17 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 16,
"id": "6d0a7a73-d151-47d9-9e99-b4f3291c0322",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Task decomposition involves breaking down a complex task into smaller and simpler steps to make it more manageable. This process helps agents or models tackle difficult tasks by dividing them into more easily achievable subgoals. Task decomposition can be done through techniques like Chain of Thought or Tree of Thoughts, which guide the model in thinking step by step or exploring multiple reasoning possibilities at each step.'"
"'Task decomposition is a technique used to break down complex tasks into smaller and simpler steps. It involves transforming big tasks into multiple manageable tasks to facilitate problem-solving. Different methods like Chain of Thought and Tree of Thoughts can be employed to decompose tasks effectively.'"
]
},
"execution_count": 2,
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
@ -683,17 +676,17 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 17,
"id": "17021822-896a-4513-a17d-1d20b1c5381c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"Common ways of task decomposition include using techniques like Chain of Thought (CoT) or Tree of Thoughts to guide models in breaking down complex tasks into smaller steps. This can be achieved through simple prompting with LLMs, task-specific instructions, or human inputs to help the model understand and navigate the task effectively. Task decomposition aims to enhance model performance on complex tasks by utilizing more test-time computation and shedding light on the model's thinking process.\""
"'Task decomposition can be achieved through various methods such as using prompting techniques like \"Steps for XYZ\" or \"What are the subgoals for achieving XYZ?\", providing task-specific instructions like \"Write a story outline,\" or incorporating human inputs to break down complex tasks into smaller components. These approaches help in organizing thoughts and planning ahead for successful task completion.'"
]
},
"execution_count": 3,
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
@ -724,7 +717,7 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 18,
"id": "809cc747-2135-40a2-8e73-e4556343ee64",
"metadata": {},
"outputs": [],
@ -749,17 +742,24 @@
},
{
"cell_type": "code",
"execution_count": 13,
"execution_count": 19,
"id": "931c4fe3-c603-4efb-9b37-5f7cbbb1cbbd",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Error in LangChainTracer.on_tool_end callback: TracerException(\"Found chain run at ID 0ec120e2-b1fc-4593-9fee-2dd4f4cae256, but expected {'tool'} run.\")\n"
]
},
{
"data": {
"text/plain": [
"'Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\nFig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\n(3) Task execution: Expert models execute on the specific tasks and log results.\\nInstruction:\\n\\nWith the input and the inference results, the AI assistant needs to describe the process and results. The previous stages can be formed as - User Input: {{ User Input }}, Task Planning: {{ Tasks }}, Model Selection: {{ Model Assignment }}, Task Execution: {{ Predictions }}. You must first answer the user\\'s request in a straightforward manner. Then describe the task process and show your analysis and model inference results to the user in the first person. If inference results contain a file path, must tell the user the complete file path.\\n\\nFig. 11. Illustration of how HuggingGPT works. (Image source: Shen et al. 2023)\\nThe system comprises of 4 stages:\\n(1) Task planning: LLM works as the brain and parses the user requests into multiple tasks. There are four attributes associated with each task: task type, ID, dependencies, and arguments. They use few-shot examples to guide LLM to do task parsing and planning.\\nInstruction:'"
"'Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\nFig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nFig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.'"
"Error in LangChainTracer.on_tool_end callback: TracerException(\"Found chain run at ID 1a50f4da-34a7-44af-8cbb-c67c90c9619e, but expected {'tool'} run.\")\n"
"{'action': {'messages': [ToolMessage(content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\n(3) Task execution: Expert models execute on the specific tasks and log results.\\nInstruction:\\n\\nWith the input and the inference results, the AI assistant needs to describe the process and results. The previous stages can be formed as - User Input: {{ User Input }}, Task Planning: {{ Tasks }}, Model Selection: {{ Model Assignment }}, Task Execution: {{ Predictions }}. You must first answer the user\\'s request in a straightforward manner. Then describe the task process and show your analysis and model inference results to the user in the first person. If inference results contain a file path, must tell the user the complete file path.\\n\\nFig. 11. Illustration of how HuggingGPT works. (Image source: Shen et al. 2023)\\nThe system comprises of 4 stages:\\n(1) Task planning: LLM works as the brain and parses the user requests into multiple tasks. There are four attributes associated with each task: task type, ID, dependencies, and arguments. They use few-shot examples to guide LLM to do task parsing and planning.\\nInstruction:', name='blog_post_retriever', id='e83e4002-33d2-46ff-82f4-fddb3035fb6a', tool_call_id='call_demTlnha4vYA1IH6CByYupBQ')]}}\n",
"{'tools': {'messages': [ToolMessage(content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nFig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.', name='blog_post_retriever', tool_call_id='call_1ZkTWsLYIlKZ1uMyIQGUuyJx')]}}\n",
"----\n",
"{'agent': {'messages': [AIMessage(content='Task decomposition is a technique used in autonomous agent systems to break down complex tasks into smaller and simpler steps. This approach helps agents better understand and plan for the various steps involved in completing a task. One common method for task decomposition is the Chain of Thought (CoT) technique, where models are prompted to \"think step by step\" to decompose hard tasks into manageable steps. Another approach, known as Tree of Thoughts, extends CoT by exploring multiple reasoning possibilities at each step and creating a tree structure of tasks.\\n\\nTask decomposition can be achieved through various methods, such as using simple prompts for language models, task-specific instructions, or human inputs. By breaking down tasks into smaller components, agents can effectively plan and execute tasks with greater efficiency.\\n\\nIn summary, task decomposition is a valuable strategy for autonomous agents to tackle complex tasks by breaking them down into smaller, more manageable steps.', response_metadata={'token_usage': {'completion_tokens': 177, 'prompt_tokens': 588, 'total_tokens': 765}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'stop', 'logprobs': None}, id='run-808f32b9-ae61-4f31-a55a-f30643594282-0')]}}\n",
"{'agent': {'messages': [AIMessage(content='Task decomposition is a technique used to break down complex tasks into smaller and simpler steps. This approach helps in managing and solving difficult tasks by dividing them into more manageable components. One common method of task decomposition is the Chain of Thought (CoT) technique, where models are instructed to think step by step to decompose hard tasks into smaller steps. Another extension of CoT is the Tree of Thoughts, which explores multiple reasoning possibilities at each step and generates multiple thoughts per step, creating a tree structure. Task decomposition can be facilitated by using simple prompts, task-specific instructions, or human inputs.', response_metadata={'token_usage': {'completion_tokens': 119, 'prompt_tokens': 636, 'total_tokens': 755}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-4a701854-97f2-4ec2-b6e1-73410911fa72-0')]}}\n",
"{'action': {'messages': [ToolMessage(content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\n(3) Task execution: Expert models execute on the specific tasks and log results.\\nInstruction:\\n\\nWith the input and the inference results, the AI assistant needs to describe the process and results. The previous stages can be formed as - User Input: {{ User Input }}, Task Planning: {{ Tasks }}, Model Selection: {{ Model Assignment }}, Task Execution: {{ Predictions }}. You must first answer the user\\'s request in a straightforward manner. Then describe the task process and show your analysis and model inference results to the user in the first person. If inference results contain a file path, must tell the user the complete file path.\\n\\nFig. 11. Illustration of how HuggingGPT works. (Image source: Shen et al. 2023)\\nThe system comprises of 4 stages:\\n(1) Task planning: LLM works as the brain and parses the user requests into multiple tasks. There are four attributes associated with each task: task type, ID, dependencies, and arguments. They use few-shot examples to guide LLM to do task parsing and planning.\\nInstruction:', name='blog_post_retriever', id='e0895fa5-5d41-4be0-98db-10a83d42fc2f', tool_call_id='call_ab2x4iUPSWDAHS5txL7PspSK')]}}\n",
"----\n",
"{'agent': {'messages': [AIMessage(content='Task decomposition is a technique used in complex tasks where the task is broken down into smaller and simpler steps. This approach helps in managing and solving difficult tasks by dividing them into more manageable components. One common method for task decomposition is the Chain of Thought (CoT) technique, which prompts the model to think step by step and decompose hard tasks into smaller steps. Another extension of CoT is the Tree of Thoughts, which explores multiple reasoning possibilities at each step by creating a tree structure of thought steps.\\n\\nTask decomposition can be achieved through various methods, such as using language models with simple prompting, task-specific instructions, or human inputs. By breaking down tasks into smaller components, agents can better plan and execute complex tasks effectively.\\n\\nIf you would like more detailed information or examples related to task decomposition, feel free to ask!', response_metadata={'token_usage': {'completion_tokens': 165, 'prompt_tokens': 611, 'total_tokens': 776}, 'model_name': 'gpt-3.5-turbo', 'system_fingerprint': 'fp_3b956da36b', 'finish_reason': 'stop', 'logprobs': None}, id='run-13296566-8577-4d65-982b-a39718988ca3-0')]}}\n",
"Error in LangChainTracer.on_tool_end callback: TracerException(\"Found chain run at ID 9a7ba580-ec91-412d-9649-1b5cbf5ae7bc, but expected {'tool'} run.\")\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'tools': {'messages': [ToolMessage(content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nFig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.\\n\\nTree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.', name='blog_post_retriever', tool_call_id='call_DdAAJJgGIQOZQgKVE4duDyML')]}}\n",
Harrison Chase
3 months ago
committed by
GitHub