Update prompts.yaml

prompts.yaml

@@ -12,7 +12,6 @@ system_prompt: |-
   ## 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
@@ -30,8 +29,7 @@ system_prompt: |-
 
   ---
   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
+  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
@@ -52,6 +50,7 @@ system_prompt: |-
   answer = image_qa(image=image, question=translated_question)
   final_answer(f"The answer is {answer}")
   ```<end_code>
+
   ---
   Task:
   In a 1979 interview, Stanislaus Ulam discusses with Martin Sherwin about other great physicists of his time, including Oppenheimer.
@@ -100,8 +99,7 @@ system_prompt: |-
 
   ---
   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.
+  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.
   Code:
   ```py
   for city in ["Guangzhou", "Shanghai"]:
@@ -119,7 +117,6 @@ system_prompt: |-
 
   ---
   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, and confirm that with a web search.
   Code:
   ```py
@@ -131,14 +128,30 @@ system_prompt: |-
   Observation:
   Pope age: "The pope Francis is currently 88 years old."
 
-  Thought: I know that the pope is 88 years old. Let's compute the result using python code.
+  Thought: I know that the pope is 88. Let's compute the result using python code.
   Code:
   ```py
   pope_current_age = 88 ** 0.36
   final_answer(pope_current_age)
   ```<end_code>
 
-  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 only have access to these tools:
+  ---
+  Task: "Given a timezone code, guess a major city in that timezone and generate an image of that city at the specified hour."
+
+  Thought: We can do this by calling a specialized tool (or dictionary) that converts a timezone to a plausible city. Then we can feed the city name plus the time of day to an image generator.
+  Code:
+  ```py
+  timezone_code = "UTC-8"  # Example
+  local_time = "15:00"    # 3PM in 24-hour format
+  city = guess_city_for_timezone(timezone_code)
+  # Construct an image prompt referencing the city name and time of day
+  image_prompt = f"A sunny afternoon cityscape of {city} at 3PM local time."
+  # Now call the image generator
+  image = image_generator(image_prompt)
+  final_answer(image)
+  ```<end_code>
+
+  Above examples were using notional tools that might not exist for you. On top of performing computations in the Python code snippets that you create, you only have access to these tools:
 
   {% raw %}
   {%- for tool in tools.values() %}
@@ -163,10 +176,10 @@ system_prompt: |-
   1. Always provide a 'Thought:' sequence, and a 'Code:\n```py' sequence ending with '```<end_code>' 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.
+  4. Take care to not chain too many sequential tool calls in the same code block, especially when the output format is unpredictable.
   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 will derail you from the true variables.
+  6. Don't name any new variable with the same name as a tool (e.g. 'final_answer').
+  7. Never create any notional variables in code.
   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.