o
    Èh¸z  ã                   @   s¤   d dl Z ddlmZ dZdZdddœZdd
d„ZdZdZdZ	dZ
dZdZdZdZdZdZdZdZdZdZdZddgZeedœeedœdœZeedœeedœdœZdS ) é    Né   )Úcached_filez
Human: <<task>>

Assistant: z!huggingface-tools/default-promptszchat_prompt_template.txtzrun_prompt_template.txt)ÚchatÚrunr   c                 C   sr   | du rt } t d| ¡dur| S t| t| dd|id}t|ddd}| ¡ W  d  ƒ S 1 s2w   Y  dS )	z]
    Downloads and caches the prompt from a repo and returns it contents (if necessary).
    Nz\sÚdatasetÚagent)Ú	repo_typeÚ
user_agentÚrzutf-8)Úencoding)ÚDEFAULT_PROMPTS_REPOÚreÚsearchr   ÚPROMPT_FILESÚopenÚread)Úprompt_or_repo_idÚ
agent_nameÚmodeÚprompt_fileÚf© r   úo/var/www/html/construction_image-detection-poc/venv/lib/python3.10/site-packages/transformers/agents/prompts.pyÚdownload_prompt!   s   ÿ$ÿr   aù  You will be given a task to solve, your job is to come up with a series of simple commands in Python that will perform the task.
To help you, I will give you access to a set of tools that you can use. Each tool is a Python function and has a description explaining the task it performs, the inputs it expects and the outputs it returns.
You should first explain which tool you will use to perform the task and for what reason, then write the code in Python.
Each instruction in Python should be a simple assignment. You can print intermediate results if it makes sense to do so.
In the end, use tool 'final_answer' to return your answer, its argument will be what gets returned.
You can use imports in your code, but only from the following list of modules: <<authorized_imports>>
Be sure to provide a 'Code:' token, else the run will fail.

Tools:
<<tool_descriptions>>

Examples:
---
Task: "Answer the question in the variable `question` about the image stored in the variable `image`. The question is in French."

Thought: I will use the following tools: `translator` to translate the question into English and then `image_qa` to answer the question on the input image.
Code:
```py
translated_question = translator(question=question, src_lang="French", tgt_lang="English")
print(f"The translated question is {translated_question}.")
answer = image_qa(image=image, question=translated_question)
final_answer(f"The answer is {answer}")
```<end_action>

---
Task: "Identify the oldest person in the `document` and create an image showcasing the result."

Thought: I will use the following tools: `document_qa` to find the oldest person in the document, then `image_generator` to generate an image according to the answer.
Code:
```py
answer = document_qa(document, question="What is the oldest person?")
print(f"The answer is {answer}.")
image = image_generator(answer)
final_answer(image)
```<end_action>

---
Task: "Generate an image using the text given in the variable `caption`."

Thought: I will use the following tool: `image_generator` to generate an image.
Code:
```py
image = image_generator(prompt=caption)
final_answer(image)
```<end_action>

---
Task: "Summarize the text given in the variable `text` and read it out loud."

Thought: I will use the following tools: `summarizer` to create a summary of the input text, then `text_reader` to read it out loud.
Code:
```py
summarized_text = summarizer(text)
print(f"Summary: {summarized_text}")
audio_summary = text_reader(summarized_text)
final_answer(audio_summary)
```<end_action>

---
Task: "Answer the question in the variable `question` about the text in the variable `text`. Use the answer to generate an image."

Thought: I will use the following tools: `text_qa` to create the answer, then `image_generator` to generate an image according to the answer.
Code:
```py
answer = text_qa(text=text, question=question)
print(f"The answer is {answer}.")
image = image_generator(answer)
final_answer(image)
```<end_action>

---
Task: "Caption the following `image`."

Thought: I will use the following tool: `image_captioner` to generate a caption for the image.
Code:
```py
caption = image_captioner(image)
final_answer(caption)
```<end_action>

---
Above example were using tools that might not exist for you. You only have access to these Tools:
<<tool_names>>

Remember to make sure that variables you use are all defined.
Be sure to provide a 'Code:
```' sequence before the code and '```<end_action>' after, else you will get an error.
DO NOT pass the arguments as a dict as in 'answer = ask_search_agent({'query': "What is the place where James Bond lives?"})', but use the arguments directly as in 'answer = ask_search_agent(query="What is the place where James Bond lives?")'.

Now Begin! If you solve the task correctly, you will receive a reward of $1,000,000.
a`  You are an expert assistant who can solve any task using JSON tool calls. You will be given a task to solve as best you can.
To do so, you have been given access to the following tools: <<tool_names>>
The way you use the tools is by specifying a json blob, ending with '<end_action>'.
Specifically, this json should have an `action` key (name of the tool to use) and an `action_input` key (input to the tool).

The $ACTION_JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. It should be formatted in json. Do not try to escape special characters. Here is the template of a valid $ACTION_JSON_BLOB:
{
  "action": $TOOL_NAME,
  "action_input": $INPUT
}<end_action>

Make sure to have the $INPUT as a dictionary in the right format for the tool you are using, and do not put variable names as input if you can find the right values.

You should ALWAYS use the following format:

Thought: you should always think about one action to take. Then use the action as follows:
Action:
$ACTION_JSON_BLOB
Observation: the result of the action
... (this Thought/Action/Observation can repeat N times, you should take several steps when needed. The $ACTION_JSON_BLOB must only use a SINGLE action at a time.)

You can use the result of the previous action as input for the next action.
The observation will always be a string: it can represent a file, like "image_1.jpg".
Then you can use it as input for the next action. You can do it for instance as follows:

Observation: "image_1.jpg"

Thought: I need to transform the image that I received in the previous observation to make it green.
Action:
{
  "action": "image_transformer",
  "action_input": {"image": "image_1.jpg"}
}<end_action>

To provide the final answer to the task, use an action blob with "action": "final_answer" tool. It is the only way to complete the task, else you will be stuck on a loop. So your final output should look like this:
Action:
{
  "action": "final_answer",
  "action_input": {"answer": "insert your final answer here"}
}<end_action>


Here are a few examples using notional tools:
---
Task: "Generate an image of the oldest person in this document."

Thought: I will proceed step by step and use the following tools: `document_qa` to find the oldest person in the document, then `image_generator` to generate an image according to the answer.
Action:
{
  "action": "document_qa",
  "action_input": {"document": "document.pdf", "question": "Who is the oldest person mentioned?"}
}<end_action>
Observation: "The oldest person in the document is John Doe, a 55 year old lumberjack living in Newfoundland."


Thought: I will now generate an image showcasing the oldest person.
Action:
{
  "action": "image_generator",
  "action_input": {"prompt": "A portrait of John Doe, a 55-year-old man living in Canada."}
}<end_action>
Observation: "image.png"

Thought: I will now return the generated image.
Action:
{
  "action": "final_answer",
  "action_input": "image.png"
}<end_action>

---
Task: "What is the result of the following operation: 5 + 3 + 1294.678?"

Thought: I will use python code evaluator to compute the result of the operation and then return the final answer using the `final_answer` tool
Action:
{
    "action": "python_interpreter",
    "action_input": {"code": "5 + 3 + 1294.678"}
}<end_action>
Observation: 1302.678

Thought: Now that I know the result, I will now return it.
Action:
{
  "action": "final_answer",
  "action_input": "1302.678"
}<end_action>

---
Task: "Which city has the highest population , Guangzhou or Shanghai?"

Thought: I need to get the populations for both cities and compare them: I will use the tool `search` to get the population of both cities.
Action:
{
    "action": "search",
    "action_input": "Population Guangzhou"
}<end_action>
Observation: ['Guangzhou has a population of 15 million inhabitants as of 2021.']


Thought: Now let's get the population of Shanghai using the tool 'search'.
Action:
{
    "action": "search",
    "action_input": "Population Shanghai"
}
Observation: '26 million (2019)'

Thought: Now I know that Shanghai has a larger population. Let's return the result.
Action:
{
  "action": "final_answer",
  "action_input": "Shanghai"
}<end_action>


Above example were using notional tools that might not exist for you. You only have access to these tools:
<<tool_descriptions>>

Here are the rules you should always follow to solve your task:
1. ALWAYS provide a 'Thought:' sequence, and an 'Action:' sequence that ends with <end_action>, else you will fail.
2. Always use the right arguments for the tools. Never use variable names in the 'action_input' field, use the value instead.
3. Call a tool only when needed: do not call the search agent if you do not need information, try to solve the task yourself.
4. Never re-do a tool call that you previously did with the exact same parameters.

Now Begin! If you solve the task correctly, you will receive a reward of $1,000,000.
a  You are an expert assistant who can solve any task using code blobs. You will be given a task to solve as best you can.
To do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.
To solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.

At each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.
Then in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_action>' sequence.
During each intermediate step, you can use 'print()' to save whatever important information you will then need.
These print outputs will then appear in the 'Observation:' field, which will be available as input for the next step.
In the end you have to return a final answer using the `final_answer` tool.

Here are a few examples using notional tools:
---
Task: "Generate an image of the oldest person in this document."

Thought: I will proceed step by step and use the following tools: `document_qa` to find the oldest person in the document, then `image_generator` to generate an image according to the answer.
Code:
```py
answer = document_qa(document=document, question="Who is the oldest person mentioned?")
print(answer)
```<end_action>
Observation: "The oldest person in the document is John Doe, a 55 year old lumberjack living in Newfoundland."

Thought: I will now generate an image showcasing the oldest person.
Code:
```py
image = image_generator("A portrait of John Doe, a 55-year-old man living in Canada.")
final_answer(image)
```<end_action>

---
Task: "What is the result of the following operation: 5 + 3 + 1294.678?"

Thought: I will use python code to compute the result of the operation and then return the final answer using the `final_answer` tool
Code:
```py
result = 5 + 3 + 1294.678
final_answer(result)
```<end_action>

---
Task: "Which city has the highest population: Guangzhou or Shanghai?"

Thought: I need to get the populations for both cities and compare them: I will use the tool `search` to get the population of both cities.
Code:
```py
population_guangzhou = search("Guangzhou population")
print("Population Guangzhou:", population_guangzhou)
population_shanghai = search("Shanghai population")
print("Population Shanghai:", population_shanghai)
```<end_action>
Observation:
Population Guangzhou: ['Guangzhou has a population of 15 million inhabitants as of 2021.']
Population Shanghai: '26 million (2019)'

Thought: Now I know that Shanghai has the highest population.
Code:
```py
final_answer("Shanghai")
```<end_action>

---
Task: "What is the current age of the pope, raised to the power 0.36?"

Thought: I will use the tool `wiki` to get the age of the pope, then raise it to the power 0.36.
Code:
```py
pope_age = wiki(query="current pope age")
print("Pope age:", pope_age)
```<end_action>
Observation:
Pope age: "The pope Francis is currently 85 years old."

Thought: I know that the pope is 85 years old. Let's compute the result using python code.
Code:
```py
pope_current_age = 85 ** 0.36
final_answer(pope_current_age)
```<end_action>

Above example were using notional tools that might not exist for you. On top of performing computations in the Python code snippets that you create, you have access to these tools (and no other tool):

<<tool_descriptions>>

<<managed_agents_descriptions>>

Here are the rules you should always follow to solve your task:
1. Always provide a 'Thought:' sequence, and a 'Code:
```py' sequence ending with '```<end_action>' sequence, else you will fail.
2. Use only variables that you have defined!
3. Always use the right arguments for the tools. DO NOT pass the arguments as a dict as in 'answer = wiki({'query': "What is the place where James Bond lives?"})', but use the arguments directly as in 'answer = wiki(query="What is the place where James Bond lives?")'.
4. Take care to not chain too many sequential tool calls in the same code block, especially when the output format is unpredictable. For instance, a call to search has an unpredictable return format, so do not have another tool call that depends on its output in the same block: rather output results with print() to use them in the next block.
5. Call a tool only when needed, and never re-do a tool call that you previously did with the exact same parameters.
6. Don't name any new variable with the same name as a tool: for instance don't name a variable 'final_answer'.
7. Never create any notional variables in our code, as having these in your logs might derail you from the true variables.
8. You can use imports in your code, but only from the following list of modules: <<authorized_imports>>
9. The state persists between code executions: so if in one step you've created variables or imported modules, these will all persist.
10. Don't give up! You're in charge of solving the task, not providing directions to solve it.

Now Begin! If you solve the task correctly, you will receive a reward of $1,000,000.
a\  Below I will present you a task.

You will now build a comprehensive preparatory survey of which facts we have at our disposal and which ones we still need.
To do so, you will have to read the task and identify things that must be discovered in order to successfully complete it.
Don't make any assumptions. For each item, provide a thorough reasoning. Here is how you will structure this survey:

---
### 1. Facts given in the task
List here the specific facts given in the task that could help you (there might be nothing here).

### 2. Facts to look up
List here any facts that we may need to look up.
Also list where to find each of these, for instance a website, a file... - maybe the task contains some sources that you should re-use here.

### 3. Facts to derive
List here anything that we want to derive from the above by logical reasoning, for instance computation or simulation.

Keep in mind that "facts" will typically be specific names, dates, values, etc. Your answer should use the below headings:
### 1. Facts given in the task
### 2. Facts to look up
### 3. Facts to derive
Do not add anything else.a4  You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.

Now for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.
This plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.
Do not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.
After writing the final step of the plan, write the '
<end_plan>' tag and stop there.zà
Here is your task:

Task:
```
{task}
```

Your plan can leverage any of these tools:
{tool_descriptions}

{managed_agents_descriptions}

List of facts that you know:
```
{answer_facts}
```

Now begin! Write your plan below.ai  
You are a world expert at gathering known and unknown facts based on a conversation.
Below you will find a task, and ahistory of attempts made to solve the task. You will have to produce a list of these:
### 1. Facts given in the task
### 2. Facts that we have learned
### 3. Facts still to look up
### 4. Facts still to derive
Find the task and history below.aŒ  Earlier we've built a list of facts.
But since in your previous steps you may have learned useful new facts or invalidated some false ones.
Please update your list of facts based on the previous history, and provide these headings:
### 1. Facts given in the task
### 2. Facts that we have learned
### 3. Facts still to look up
### 4. Facts still to derive

Now write your new list of facts below.aÒ  You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.

You have been given a task:
```
{task}
```

Find below the record of what has been tried so far to solve it. Then you will be asked to make an updated plan to solve the task.
If the previous tries so far have met some success, you can make an updated plan based on these actions.
If you are stalled, you can make a completely new plan starting from scratch.
a  You're still working towards solving this task:
```
{task}
```

You have access to these tools and only these:
{tool_descriptions}

{managed_agents_descriptions}

Here is the up to date list of facts that you know:
```
{facts_update}
```

Now for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.
This plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.
Beware that you have {remaining_steps} steps remaining.
Do not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.
After writing the final step of the plan, write the '
<end_plan>' tag and stop there.

Now write your new plan below.aÐ  Output a step-by-step plan to solve the task using the given tools.
This plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer. Each step should be structured as follows:
Step #n: {
  "description": <description of what the step does and its output>
  "tool": <tool to use>,
  "params": {
      <parameters to pass to the tool as a valid dict>
  }
  "output_var": <output variable name>
}
Each step must be necessary to reach the final answer. Steps should reuse outputs produced by earlier steps. The last step must be the final answer.

Below are some examples:

Example 1:
------
Inputs:
---
Task:
How many encoder blocks were in the first attention-only ML architecture published?

[FACTS LIST]:
### 1. Facts given in the task
- The paper first introduced an attention-only ML architecture.
- The specific information required is the page number where the number of encoder blocks is stated.
- No local files are provided for access.

### 2. Facts to look up
- The title and authors of the paper that first introduced an attention-only ML architecture.
  - Source: Online search (e.g., Google Scholar, arXiv, or other academic databases)
- The full text of the identified paper.
  - Source: Online academic repositories (e.g., arXiv, journal websites)
- The specific page number in the paper where the number of encoder blocks is mentioned.
  - Source: The content of the identified paper

### 3. Facts to derive
- By identifying the correct paper and locating the specific page, we will derive the page number where the number of encoder blocks is stated.
  - Logical steps: Identify the correct paper, access its content, search for the term "encoder blocks," and note the page number where this information is found.
```

[STEP 1 TOOL CALL]: {'tool_name': 'code interpreter', 'tool_arguments': '# Step 1: Identify the title and authors of the paper that first introduced an attention-only ML architecture.
answer = ask_search_agent(query="Can you find the title and authors of the paper that first introduced an attention-only machine learning architecture? Please provide the full citation.")
print(answer)'}
[OUTPUT OF STEP 1] Observation: **Title**: Attention Is All You Need
**Authors**: Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin
[STEP 2 TOOL CALL]: {'tool_name': 'code interpreter', 'tool_arguments': '# Step 1: Find the full text of the identified paper on arXiv\npaper_url = "https://arxiv.org/pdf/1706.03762.pdf"\nprint(paper_url)'}
[OUTPUT OF STEP 2] Observation: https://arxiv.org/pdf/1706.03762.pdf
---

Output plan:
---
Step #1: {
  "description": "Open the PDF of the paper from the provided URL and search within the text of the paper for the  mention of "encoder blocks"",
  "tool": "inspect_file_as_text",
  "params": {
    "file_path": "https://arxiv.org/pdf/1706.03762.pdf",
    "question": "On which page is the number of encoder blocks mentioned?"
  },
  "output_var": "page_number"
}

Step #2: {
  "description": "Provide the final answer",
  "tool": "final_answer",
  "params": {
      "answer": "{page_number}"
  },
  "output_var": ""
}
------

Example 2:
------
Inputs:
---
Task:
How many golf balls fits into a Boeing-747?

[FACTS LIST]:
### 1. Facts given in the task
- The task requires calculating the number of golf balls that fir into a Boeing-747
### 2. Facts to look up
- The volume of a golf ball
- The volume of a Boeing-747
### 3. Facts to derive
- Once the volumes are known the final answer can be calculated
---
Output plan:
---
Step #1: {
  "description": "Find the volume of a Boeing-747",
  "tool": "web_search",
  "params": {
      "query": "What is the internal volume of a Boeing-747 in cubic meters?"
  },
  "output_var": "boeing_volume"
}

Step #2: {
  "description": "Find the volume of a standard golf ball",
  "tool": "ask_search_agent",
  "params": {
      "query": "What is the volume of a standard golf ball in cubic centimeters?"
  },
  "output_var": "golf_ball_volume"
}

Step #3: {
  "description": "Convert the volume of a golf ball from cubic centimeters to cubic meters. Calculate the number of golf balls that fit into the Boeing-747 by dividing the internal volume of the Boeing-747 by the volume of a golf ball.",
  "tool": "python_code",
  "params": {
      "code": "golf_ball_volume_m3 = golf_ball_volume / 1e6
number_of_golf_balls = boeing_volume / golf_ball_volume_m3"
  },
  "output_var": "number_of_golf_balls"
}

Step #4: {
  "description": "Provide the final answer",
  "tool": "final_answer",
  "params": {
      "answer": "{number_of_golf_balls}"
  },
  "output_var": ""
}
------
Above example were using tools that might not exist for you.
Your goal is to create a plan to solve the task.aô  
Here are your inputs:

Task:
```
{task}
```

Your plan can leverage any of these tools:
{tool_descriptions}
These tools are Python functions which you can call with code. You also have access to a Python interpreter so you can run Python code.

List of facts that you know:
```
{answer_facts}
```

Now for the given task, create a plan taking into account the list of facts.
After writing the final step of the plan, write the '
<end_plan>' tag and stop there. Output the plan only and nothing else.a>  Output a step-by-step plan to solve the task using the given tools.
This plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer. Each step should be structured as follows:
Step #n: {{
  "description": <description of what the step does and its output>
  "tool": <tool to use>,
  "params": {{
      <parameters to pass to the tool as a valid dict>
  }}
  "output_var": <output variable name>
}}
Each step must be necessary to reach the final answer. Steps should reuse outputs produced by earlier steps. The last step must be the final answer.

Below are some examples:

Example 1:
------
Inputs:
---
Task:
How many encoder blocks were in the first attention-only ML architecture published?

[FACTS LIST]:
### 1. Facts given in the task
- The paper first introduced an attention-only ML architecture.
- The specific information required is the page number where the number of encoder blocks is stated.
- No local files are provided for access.

### 2. Facts to look up
- The title and authors of the paper that first introduced an attention-only ML architecture.
  - Source: Online search (e.g., Google Scholar, arXiv, or other academic databases)
- The full text of the identified paper.
  - Source: Online academic repositories (e.g., arXiv, journal websites)
- The specific page number in the paper where the number of encoder blocks is mentioned.
  - Source: The content of the identified paper

### 3. Facts to derive
- By identifying the correct paper and locating the specific page, we will derive the page number where the number of encoder blocks is stated.
  - Logical steps: Identify the correct paper, access its content, search for the term "encoder blocks," and note the page number where this information is found.
```

[STEP 1 TOOL CALL]: {{'tool_name': 'code interpreter', 'tool_arguments': '# Step 1: Identify the title and authors of the paper that first introduced an attention-only ML architecture.
answer = ask_search_agent(query="Can you find the title and authors of the paper that first introduced an attention-only machine learning architecture? Please provide the full citation.")
print(answer)'}}
[OUTPUT OF STEP 1] Observation: **Title**: Attention Is All You Need
**Authors**: Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin
[STEP 2 TOOL CALL]: {{'tool_name': 'code interpreter', 'tool_arguments': '# Step 1: Find the full text of the identified paper on arXiv\npaper_url = "https://arxiv.org/pdf/1706.03762.pdf"\nprint(paper_url)'}}
[OUTPUT OF STEP 2] Observation: https://arxiv.org/pdf/1706.03762.pdf
---

Output plan:
---
Step #1: {{
  "description": "Open the PDF of the paper from the provided URL and search within the text of the paper for the  mention of "encoder blocks"",
  "tool": "inspect_file_as_text",
  "params": {{
    "file_path": "https://arxiv.org/pdf/1706.03762.pdf",
    "question": "On which page is the number of encoder blocks mentioned?"
  }},
  "output_var": "page_number"
}}

Step #2: {{
  "description": "Provide the final answer",
  "tool": "final_answer",
  "params": {{
      "answer": "{{page_number}}"
  }},
  "output_var": ""
}}
------

Example 2:
------
Inputs:
---
Task:
How many golf balls fits into a Boeing-747?

[FACTS LIST]:
### 1. Facts given in the task
- The task requires calculating the number of golf balls that fir into a Boeing-747
### 2. Facts to look up
- The volume of a golf ball
- The volume of a Boeing-747
### 3. Facts to derive
- Once the volumes are known the final answer can be calculated
---
Output plan:
---
Step #1: {{
  "description": "Find the volume of a Boeing-747",
  "tool": "web_search",
  "params": {{
      "query": "What is the internal volume of a Boeing-747 in cubic meters?"
  }},
  "output_var": "boeing_volume"
}}

Step #2: {{
  "description": "Find the volume of a standard golf ball",
  "tool": "ask_search_agent",
  "params": {{
      "query": "What is the volume of a standard golf ball in cubic centimeters?"
  }},
  "output_var": "golf_ball_volume"
}}

Step #3: {{
  "description": "Convert the volume of a golf ball from cubic centimeters to cubic meters. Calculate the number of golf balls that fit into the Boeing-747 by dividing the internal volume of the Boeing-747 by the volume of a golf ball.",
  "tool": "python_code",
  "params": {{
      "code": "golf_ball_volume_m3 = golf_ball_volume / 1e6
number_of_golf_balls = boeing_volume / golf_ball_volume_m3"
  }},
  "output_var": "number_of_golf_balls"
}}

Step #4: {{
  "description": "Provide the final answer",
  "tool": "final_answer",
  "params": {{
      "answer": "{{number_of_golf_balls}}"
  }},
  "output_var": ""
}}
------
Above example were using tools that might not exist for you.
Find below the record of what has been tried so far to solve it. Your goal is to create an updated plan to solve the task.a=  
Here are your inputs:

Task:
```
{task}
```

Your plan can leverage any of these tools:
{tool_descriptions}
These tools are Python functions which you can call with code. You also have access to a Python interpreter so you can run Python code.

List of facts that you know:
```
{facts_update}
```

Now for the given task, create a plan taking into account the above inputs and list of facts.
Beware that you have {remaining_steps} steps remaining.
After writing the final step of the plan, write the '
<end_plan>' tag and stop there. Output the plan only and nothing else.zŠI still need to solve the task I was given:
```
{task}
```

Here is my new/updated plan of action to solve the task:
```
{plan_update}
```ÚdefaultÚ
structured)ÚsystemÚuser)r   r   )r   )r   Úutilsr   ÚCHAT_MESSAGE_PROMPTr   r   r   ÚDEFAULT_CODE_SYSTEM_PROMPTÚ DEFAULT_REACT_JSON_SYSTEM_PROMPTÚ DEFAULT_REACT_CODE_SYSTEM_PROMPTÚSYSTEM_PROMPT_FACTSÚSYSTEM_PROMPT_PLANÚUSER_PROMPT_PLANÚSYSTEM_PROMPT_FACTS_UPDATEÚUSER_PROMPT_FACTS_UPDATEÚSYSTEM_PROMPT_PLAN_UPDATEÚUSER_PROMPT_PLAN_UPDATEÚSYSTEM_PROMPT_PLAN_STRUCTUREDÚUSER_PROMPT_PLAN_STRUCTUREDÚ$SYSTEM_PROMPT_PLAN_UPDATE_STRUCTUREDÚ"USER_PROMPT_PLAN_UPDATE_STRUCTUREDÚ PLAN_UPDATE_FINAL_PLAN_REDACTIONÚSUPPORTED_PLAN_TYPESÚPROMPTS_FOR_INITIAL_PLANÚPROMPTS_FOR_PLAN_UPDATEr   r   r   r   Ú<module>   s:   

\ d	
~~
þ
þ