Add images

theagent.py

@@ -17,7 +17,7 @@ from smolagents import (
 
 cache = {
     "How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia.": "4",  # wrong, should be 3
-    "In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?": "7234",
+    "In the video https://www.youtube.com/watch?v=L1vXCYZAYYM, what is the highest number of bird species to be on camera simultaneously?": "7234",  # wrong
     '.rewsna eht sa "tfel" drow eht fo etisoppo eht etirw ,ecnetnes siht dnatsrednu uoy fI': "right",  # correct
     "Review the chess position provided in the image. It is black's turn. Provide the correct next move for black which guarantees a win. Please provide your response in algebraic notation.": None,
     "Who nominated the only Featured Article on English Wikipedia about a dinosaur that was promoted in November 2016?": "FunkMonk",
@@ -27,9 +27,9 @@ cache = {
     "I'm making a grocery list for my mom, but she's a professor of botany and she's a real stickler when it comes to categorizing things. I need to add different foods to different categories on the grocery list, but if I make a mistake, she won't buy anything inserted in the wrong category. Here's the list I have so far:": "wrong",
     "Hi, I'm making a pie but I could use some help with my shopping list. I have everything I need for the crust, but I'm not sure about the filling.": "cornstarch, lemon juice, salt, strawberries, sugar",
     "Who did the actor who played Ray in the Polish-language version of Everybody Loves Raymond play in Magda M.? Give only the first name.": "Wojciech",  # correct
-    "What is the final numeric output from the attached Python code?": None,
+    "What is the final numeric output from the attached Python code?": "0",  # correct
     "How many at bats did the Yankee with the most walks in the 1977 regular season have that same season?": "519",
-    "Hi, I was out sick from my classes on Friday, so I'm trying to figure out what I need to study for my Calculus mid-term next week. My friend from class sent me an audio recording of Professor Willowbrook giving out the recommended reading for the test, but my headphones are broken :(": None,
+    "Hi, I was out sick from my classes on Friday, so I'm trying to figure out what I need to study for my Calculus mid-term next week. My friend from class sent me an audio recording of Professor Willowbrook giving out the recommended reading for the test, but my headphones are broken :(": "wrong",
     "On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This article mentions a team that produced a paper about their observations, linked at the bottom of the article. Find this paper. Under what NASA award number was the work performed by R. G. Arendt supported by?": "80GSFC21M0002",  # correct
     "Where were the Vietnamese specimens described by Kuznetzov in Nedoshivina's 2010 paper eventually deposited? Just give me the city name without abbreviations.": "Saint Petersburg",  # correct, but not always
     "What country had the least number of athletes at the 1928 Summer Olympics? If there's a tie for a number of athletes, return the first in alphabetical order. Give the IOC country code as your answer.": "CUB",  # correct
@@ -128,11 +128,18 @@ class BasicAgent:
         for k, v in cache.items():
             if k in question and v is not None:
                 return v
+
+        images = None
+        for k, v in attachment.items():
+            if v.endswith(".png") or v.endswith(".jpg"):
+                images = [v]
+                attachment = None
         answer = self.agent.run(
             question
             + " Please break down the questions into easier sub-tasks."
             + " Please answer concisely.",
             additional_args=attachment,
+            images=images,
         )
         print("the answer", answer)
         try: