Update app.py

app.py

@@ -12,11 +12,39 @@ import yaml
 # from tools.final_answer import FinalAnswerTool
 from PIL import Image
 from io import BytesIO
+from smolagents.tools import BaseTool
+import requests
+from bs4 import BeautifulSoup
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+class VisitWebpageTool(BaseTool):
+    name = "visit_webpage"
+    description = "Fetch and read the content of a webpage"
+    inputs = {"url": {"type": "string"}}
+    output_type = "string"
+
+    def __call__(self, url: str):
+        # response = requests.get(url)
+        # soup = BeautifulSoup(response.text, "html.parser")
+        # return soup.get_text()[:5000]  # truncate for safety
+
+        headers = {
+            "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120 Safari/537.36"
+        }
+        response = requests.get(url, headers=headers, timeout=10)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.text, "html.parser")
+
+        # Extract only readable text
+        paragraphs = [p.get_text() for p in soup.find_all("p")]
+        text = "\n".join(paragraphs)
+
+        return text[:5000]  # limit size
+
+
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
@@ -49,7 +77,7 @@ class BasicAgent:
         # Only call `final_answer` and do a final reason to make sure that you answer the question clearly and directly without additional information if not requested."""
         # }
 
-        self.prompt_templates = {'system_prompt': '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.\nTo do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.\nTo solve the task, you must plan forward to proceed in a series of steps, in a cycle of \'Thought:\', \'Code:\', and \'Observation:\' sequences.\nAt each step, in the \'Thought:\' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.\nThen in the \'Code:\' sequence, you should write the code in simple Python. The code sequence must end with \'<end_code>\' sequence.\nDuring each intermediate step, you can use \'print()\' to save whatever important information you will then need.\nThese print outputs will then appear in the \'Observation:\' field, which will be available as input for the next step.\nIn the end you have to return a final answer using the `final_answer` tool.\n\nYou must follow EXACTLY this format:\n\nThought:\n<code>\n# Python code here\n</code>\n\nRules:\n- ALWAYS use <code> and </code>\n- DO NOT use markdown code blocks\n- Use only valid Python\n\nCRITICAL:\n- If the answer requires external information (facts, data, current info), you MUST use a tool.\n- DO NOT guess or hallucinate.\n- DO NOT answer from memory if unsure.\n- Prefer using tools over guessing.\n\nHere are the rules you should always follow to solve your task:\n1. Use only variables that you have defined!\n2. 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?")\'.\n3. 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.\n4. Call a tool only when needed, and never re-do a tool call that you previously did with the exact same parameters.\n5. Don\'t name any new variable with the same name as a tool: for instance don\'t name a variable \'final_answer\'.\n6. Never create any notional variables in our code, as having these in your logs will derail you from the true variables.\n7. You can use imports in your code, but only from the following list of modules: {{authorized_imports}}\n8. The state persists between code executions: so if in one step you\'ve created variables or imported modules, these will all persist.\n9. Don\'t give up! You\'re in charge of solving the task, not providing directions to solve it.\n\n\nExample:\n\nTask: What is the population of Paris?\n\nThought:\n<code>\nresult = web_search("Paris population")\nprint(result)\n</code>\n\nWhen the task is solved, return:\n<code>\nfinal_answer(result)\n</code>\n',
+        self.prompt_templates = {'system_prompt': '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.\nTo do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.\nTo solve the task, you must plan forward to proceed in a series of steps, in a cycle of \'Thought:\', \'Code:\', and \'Observation:\' sequences.\nAt each step, in the \'Thought:\' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.\nThen in the \'Code:\' sequence, you should write the code in simple Python. The code sequence must end with \'<end_code>\' sequence.\nDuring each intermediate step, you can use \'print()\' to save whatever important information you will then need.\nThese print outputs will then appear in the \'Observation:\' field, which will be available as input for the next step.\nIn the end you have to return a final answer using the `final_answer` tool.\n\nYou must follow EXACTLY this format:\n\nThought:\n<code>\n# Python code here\n</code>\n\nRules:\n- ALWAYS use <code> and </code>\n- DO NOT use markdown code blocks\n- Use only valid Python\n\nCRITICAL:\n- If the answer requires external information (facts, data, current info), you MUST use a tool.\n- DO NOT guess or hallucinate.\n- DO NOT answer from memory if unsure.\n- Prefer using tools over guessing.\n– If a search result contains a useful link, you MUST use visit_webpage(url) to read it. Do not stop at search results.\n\nYou are NOT allowed to use requests, urllib, or any direct HTTP calls.\n\nAvailable tools:\n- duckduckgo_search(query: str)\n- visit_webpage(url: str)\n\nTo access web content, you MUST use:\n- web_search(query)\n- visit_webpage(url)\n\nAny other method is invalid.\n\nHere are the rules you should always follow to solve your task:\n1. Use only variables that you have defined!\n2. 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?")\'.\n3. 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.\n4. Call a tool only when needed, and never re-do a tool call that you previously did with the exact same parameters.\n5. Don\'t name any new variable with the same name as a tool: for instance don\'t name a variable \'final_answer\'.\n6. Never create any notional variables in our code, as having these in your logs will derail you from the true variables.\n7. You can use imports in your code, but only from the following list of modules: {{authorized_imports}}\n8. The state persists between code executions: so if in one step you\'ve created variables or imported modules, these will all persist.\n9. Don\'t give up! You\'re in charge of solving the task, not providing directions to solve it.\n\n\nExample:\n\nTask: What is the population of Paris?\n\nThought:\n<code>\nresult = web_search("Paris population")\nprint(result)\n</code>\n\nExample:\n\nTask: Who wrote the novel "1984"?\n\nThought:\n<code>\nresults = web_search("1984 novel author")\nprint(results)\n</code>\n\nThought:\n<code>\npage = visit_webpage(url=results[0])\nprint(page)\n</code>\n\nThought:\n<code>\nfinal_answer("George Orwell")\n</code>\n\nWhen the task is solved, return:\n<code>\nfinal_answer(result)\n</code>\n',
  'planning': {'initial_facts': 'Below I will present you a task.\nYou will now build a comprehensive preparatory survey of which facts we have at our disposal and which ones we still need.\nTo do so, you will have to read the task and identify things that must be discovered in order to successfully complete it.\nDon\'t make any assumptions. For each item, provide a thorough reasoning. Here is how you will structure this survey:\n\n---\n### 1. Facts given in the task\nList here the specific facts given in the task that could help you (there might be nothing here).\n\n### 2. Facts to look up\nList here any facts that we may need to look up.\nAlso 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.\n\n### 3. Facts to derive\nList here anything that we want to derive from the above by logical reasoning, for instance computation or simulation.\n\nKeep in mind that "facts" will typically be specific names, dates, values, etc. Your answer should use the below headings:\n### 1. Facts given in the task\n### 2. Facts to look up\n### 3. Facts to derive\nDo not add anything else.',
   'initial_plan': "You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.\nNow for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.\nThis plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.\nDo not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.\nAfter writing the final step of the plan, write the '\\n<end_plan>' tag and stop there.\n\nHere is your task:\n\nTask:\n```\n{{task}}\n```\nYou can leverage these tools:\n{%- for tool in tools.values() %}\n- {{ tool.name }}: {{ tool.description }}\n    Takes inputs: {{tool.inputs}}\n    Returns an output of type: {{tool.output_type}}\n{%- endfor %}\n\n{%- if managed_agents and managed_agents.values() | list %}\nYou can also give tasks to team members.\nCalling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'request', a long string explaining your request.\nGiven that this team member is a real human, you should be very verbose in your request.\nHere is a list of the team members that you can call:\n{%- for agent in managed_agents.values() %}\n- {{ agent.name }}: {{ agent.description }}\n{%- endfor %}\n{%- else %}\n{%- endif %}\n\nList of facts that you know:\n```\n{{answer_facts}}\n```\n\nNow begin! Write your plan below.",
   'update_facts_pre_messages': 'You are a world expert at gathering known and unknown facts based on a conversation.\nBelow you will find a task, and a history of attempts made to solve the task. You will have to produce a list of these:\n### 1. Facts given in the task\n### 2. Facts that we have learned\n### 3. Facts still to look up\n### 4. Facts still to derive\nFind the task and history below:',
@@ -62,13 +90,14 @@ class BasicAgent:
   'post_messages': 'Write:\n\n<code>\nfinal_answer(result)\n</code>\n\nWhere result is:\n- a string\n- or a number\n- NEVER a list or array\n'}}
 
         self.web_search = DuckDuckGoSearchTool()
+        self.visit_webpage = VisitWebpageTool()
 
         self.agent = CodeAgent(
             model=self.model,
-            tools=[self.web_search,],
-            max_steps=3,
+            tools=[self.web_search, self.visit_webpage,],
+            max_steps=10,
             verbosity_level=1,
-            additional_authorized_imports=["requests", "bs4", "json", "pandas", "wiki", 'random', 'time', 'itertools', 'statistics', 'queue', 'math', 'collections', 'datetime', 'unicodedata', 're', 'stat'],
+            additional_authorized_imports=["json", "pandas", "wiki", 'random', 'time', 'itertools', 'statistics', 'queue', 'math', 'collections', 'datetime', 'unicodedata', 're', 'stat'],
             prompt_templates=self.prompt_templates,
         )
 
@@ -80,7 +109,8 @@ class BasicAgent:
 
 
         # if question == "Given this table defining * on the set S = {a, b, c, d, e}\n\n|*|a|b|c|d|e|\n|---|---|---|---|---|---|\n|a|a|b|c|b|d|\n|b|b|c|a|e|c|\n|c|c|a|b|b|a|\n|d|b|e|b|e|d|\n|e|d|b|a|d|c|\n\nprovide the subset of S involved in any possible counter-examples that prove * is not commutative. Provide your answer as a comma separated list of the elements in the set in alphabetical order.":
-        if " image " not in question and " video " not in question:
+        # if " image " not in question and " video " not in question:
+        if question == "Who nominated the only Featured Article on English Wikipedia about a dinosaur that was promoted in November 2016?":
             agent_answer = self.agent.run(question)
         else:
             agent_answer = fixed_answer