feat: improve prompts

prompts.yaml

@@ -7,7 +7,7 @@
   Then in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_code>' 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.
+  In the end you have to return a final answer using the `final_answer` tool. Make sure to provide a detailed explanation in the final answer.
 
   Here are a few examples using notional tools:
   ---
@@ -25,17 +25,17 @@
   Code:
   ```py
   image = image_generator("A portrait of John Doe, a 55-year-old man living in Canada.")
-  final_answer(image)
+  final_answer(f"The oldest person in the document is John Doe, a 55-year-old lumberjack living in Newfoundland. Here is an image of him: {image}")
   ```<end_code>
 
   ---
   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
-  final_answer(result)
+  final_answer(f"The result of the operation 5 + 3 + 1294.678 is {result}.")
   ```<end_code>
 
   ---
@@ -50,7 +50,7 @@
   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}")
+  final_answer(f"The answer to the question 'Quel est l'animal sur l'image?' is {answer}.")
   ```<end_code>
 
   ---
@@ -98,7 +98,7 @@
   Thought: I now have the final answer: from the webpages visited, Stanislaus Ulam says of Einstein: "He learned too much mathematics and sort of diminished, it seems to me personally, it seems to me his purely physics creativity." Let's answer in one word.
   Code:
   ```py
-  final_answer("diminished")
+  final_answer("The consequence of Einstein learning too much math on his creativity was that it 'diminished'.")
   ```<end_code>
 
   ---
@@ -117,7 +117,7 @@
   Thought: Now I know that Shanghai has the highest population.
   Code:
   ```py
-  final_answer("Shanghai")
+  final_answer("Shanghai has the highest population with 26 million inhabitants compared to Guangzhou's 15 million.")
   ```<end_code>
 
   ---
@@ -138,7 +138,7 @@
   Code:
   ```py
   pope_current_age = 88 ** 0.36
-  final_answer(pope_current_age)
+  final_answer(f"The current age of the pope raised to the power 0.36 is {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: