Update app.py

app.py

@@ -21,53 +21,68 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-
-
-        model = TransformersModel(
-            # model_id="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
-            # model_id="mistralai/Mistral-7B-Instruct-v0.2",
+        self.model = TransformersModel(
             model_id="Qwen/Qwen2.5-Coder-7B-Instruct",
-            max_new_tokens=128,
+            max_new_tokens=512,
             temperature=0.1,
         )
 
-        with open("prompts.yaml", 'r') as stream:
-            prompt_templates = yaml.safe_load(stream)
+        # with open("prompts.yaml", 'r') as stream:
+        #     prompt_templates = yaml.safe_load(stream)
 
-        prompt_templates["final_answer"] = {
-            "pre_messages": """You have reached the end of the task.
+        # prompt_templates["final_answer"] = {
+        #     "pre_messages": """You have reached the end of the task.
         
-        Review your reasoning and ensure that your result is correct.
-        You must now return the final answer using the `final_answer()` tool.
+        # Review your reasoning and ensure that your result is correct.
+        # You must now return the final answer using the `final_answer()` tool.
         
-        Do not output plain text — only use the tool.""",
+        # Do not output plain text — only use the tool.""",
         
-            "post_messages": """Write Python code that calls:
+        #     "post_messages": """Write Python code that calls:
         
-        final_answer(result)
+        # final_answer(result)
         
-        Where `result` is the final answer to the task.
+        # Where `result` is the final answer to the task.
         
-        Do not print anything else.
-        Do not return explanations.
-        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."""
-        }
-
-        agent = CodeAgent(
-            model=model,
-            tools=[DuckDuckGoSearchTool(),],
+        # Do not print anything else.
+        # Do not return explanations.
+        # 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."""
+        # }
+
+        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',
+ '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:',
+  'update_facts_post_messages': "Earlier we've built a list of facts.\nBut since in your previous steps you may have learned useful new facts or invalidated some false ones.\nPlease update your list of facts based on the previous history, and provide these headings:\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\nNow write your new list of facts below.",
+  'update_plan_pre_messages': 'You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.\nYou have been given a task:\n```\n{{task}}\n```\n\nFind 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.\nIf the previous tries so far have met some success, you can make an updated plan based on these actions.\nIf you are stalled, you can make a completely new plan starting from scratch.',
+  'update_plan_post_messages': "You're still working towards solving this task:\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 'task'.\nGiven that this team member is a real human, you should be very verbose in your task, it should be a long string providing informations as detailed as necessary.\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\nHere is the up to date list of facts that you know:\n```\n{{facts_update}}\n```\n\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.\nBeware that you have {remaining_steps} steps remaining.\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\nNow write your new plan below."},
+ 'managed_agent': {'task': "You're a helpful agent named '{{name}}'.\nYou have been submitted this task by your manager.\n---\nTask:\n{{task}}\n---\nYou're helping your manager solve a wider task: so make sure to not provide a one-line answer, but give as much information as possible to give them a clear understanding of the answer.\nYour final_answer WILL HAVE to contain these parts:\n### 1. Task outcome (short version):\n### 2. Task outcome (extremely detailed version):\n### 3. Additional context (if relevant):\n\nPut all these in your final_answer tool, everything that you do not pass as an argument to final_answer will be lost.\nAnd even if your task resolution is not successful, please return as much context as possible, so that your manager can act upon this feedback.",
+  'report': "Here is the final answer from your managed agent '{{name}}':\n{{final_answer}}"},
+ 'final_answer': {'pre_messages': 'You are done.\n\nReturn the final answer using final_answer().\nDo not output anything else.',
+  'post_messages': 'Write:\n\nfinal_answer(result)\n\nOnly include the result.'}}
+
+        web_search = DuckDuckGoSearchTool()
+
+        self.agent = CodeAgent(
+            model=self.model,
+            tools=[web_search,],
             max_steps=3,
             verbosity_level=1,
-            additional_authorized_imports=["pandas", "wiki", 'random', 'time', 'itertools', 'statistics', 'queue', 'math', 'collections', 'datetime', 'unicodedata', 're', 'stat'],
+            additional_authorized_imports=["requests", "bs4", "json", "pandas", "wiki", 'random', 'time', 'itertools', 'statistics', 'queue', 'math', 'collections', 'datetime', 'unicodedata', 're', 'stat'],
             prompt_templates=prompt_templates,
         )
 
-        agent_answer = agent.run(question)
+        print("BasicAgent initialized.")
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        fixed_answer = "This is a default answer."
+        print(f"Agent returning fixed answer: {fixed_answer}")
+
+
+        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.":
+            agent_answer = self.agent.run(question)
+        else:
+            agent_answer = fixed_answer
 
         # print(f"Agent Answer: {agent_answer}")