Got it

README.md

@@ -12,4 +12,110 @@ hf_oauth: true
 hf_oauth_expiration_minutes: 480
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+---
+QWEN 3 jinja
+
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+
+{#— scan backward without using reverse filter —#}
+{%- for i in range(messages|length - 1, -1, -1) %}
+    {%- set message = messages[i] %}
+    {%- set index = i %}
+    {%- set tool_start = "<tool_response>" %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = message.content[:tool_start_length] %}
+    {%- set tool_end = "</tool_response>" %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (message.content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = message.content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not (start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

app.py

@@ -11,16 +11,61 @@ from smolagents import (
     FinalAnswerTool,
     VisitWebpageTool,
     LiteLLMModel,
+    WikipediaSearchTool,
     tool
 )
 from markdownify import markdownify
 from litellm import completion
 from qwen_vl_utils import process_vision_info
+from urllib.parse import urlparse
+from typing import List, Optional, Dict, Any
+import tempfile
+from io import BytesIO
+from PIL import Image
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+@tool
+def download_file_from_url(url: str, filename: Optional[str] = None) -> str:
+    """
+    Download a file from a URL and save it to a temporary location.
+
+    Args:
+        url: The URL to download from
+        filename: Optional filename, will generate one based on URL if not provided
+
+    Returns:
+        Path to the downloaded file
+    """
+    try:
+        # Parse URL to get filename if not provided
+        if not filename:
+            path = urlparse(url).path
+            filename = os.path.basename(path)
+            if not filename:
+                # Generate a random name if we couldn't extract one
+                import uuid
+                filename = f"downloaded_{uuid.uuid4().hex[:8]}"
+
+        # Create temporary file
+        temp_dir = tempfile.gettempdir()
+        filepath = os.path.join(temp_dir, filename)
+
+        # Download the file
+        response = requests.get(url, stream=True)
+        response.raise_for_status()
+
+        # Save the file
+        with open(filepath, 'wb') as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+
+        return f"File downloaded to {filepath}. You can now process this file."
+    except Exception as e:
+        return f"Error downloading file: {str(e)}"
+
 @tool
 def analyze_video(url: str, question: str) -> str:
     """Analyze a video and answer the question.
@@ -56,7 +101,7 @@ def analyze_video(url: str, question: str) -> str:
     # }
 
     response = completion(
-        api_base="http://192.168.1.82:1234/v1",
+        api_base="http://192.168.1.183:1234/v1",
         model="lm_studio/qwen2.5-vl-7b-instruct",
         messages=messages,
     )
@@ -68,13 +113,13 @@ class BasicAgent:
     def __init__(self):
         with open("prompts.yaml", 'r') as stream:
             prompt_templates = yaml.safe_load(stream)
-        model = LiteLLMModel(model_id="lm_studio/qwen2.5-coder-14b-instruct", api_base="http://192.168.1.82:1234/v1")
+        model = LiteLLMModel(model_id="lm_studio/qwen2.5-coder-14b-instruct", api_base="http://192.168.1.183:1234/v1")
         self.agent = CodeAgent(
             model=model,
-            additional_authorized_imports=["time", "pandas", "numpy"],
-            tools=[DuckDuckGoSearchTool(),VisitWebpageTool(),FinalAnswerTool()], ## add your tools here (don't remove final answer)
-            max_steps=6,
-            verbosity_level=2,
+            additional_authorized_imports=["time", "pandas", "numpy", "re", "openpyxl"],
+            tools=[DuckDuckGoSearchTool(),VisitWebpageTool(),WikipediaSearchTool(), download_file_from_url, FinalAnswerTool()], ## add your tools here (don't remove final answer)
+            max_steps=16,
+            verbosity_level=1,
             grammar=None,
             planning_interval=None,
             name=None,
@@ -82,8 +127,15 @@ class BasicAgent:
             prompt_templates=prompt_templates
         )
         print("BasicAgent initialized.")
-    def __call__(self, question: str):
+    def __call__(self, question: str, file: str, taskId: str):
         print(f"Agent received question (first 100 chars): {question[:100]}...")
+        if file :
+            if file.endswith('png') :
+                images = [Image.open(BytesIO(requests.get(f"{DEFAULT_API_URL}/files/{taskId}", timeout=10).content)).convert("RGB")]
+                fixed_answer_pict = self.agent.run(question, False, True, images);
+                return fixed_answer_pict;
+            else:
+                question = question + f" You can donwload the file associated at {DEFAULT_API_URL}/files/{taskId}"
         fixed_answer = self.agent.run(question, False, True);
         print(f"Agent returning fixed answer: {fixed_answer}")
         return fixed_answer
@@ -93,7 +145,6 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
     """
-
     # --- Determine HF Space Runtime URL and Repo URL ---
     space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
 
@@ -105,8 +156,8 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         return "Please Login to Hugging Face with the button.", None
 
     api_url = DEFAULT_API_URL
-    # questions_url = f"{api_url}/questions"
-    questions_url = f"{api_url}/random-question"
+    questions_url = f"{api_url}/questions"
+    # questions_url = f"{api_url}/random-question"
     submit_url = f"{api_url}/submit"
 
     # 1. Instantiate Agent ( modify this part to create your agent)
@@ -143,15 +194,16 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     # 3. Run your Agent
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len([questions_data])} questions...")
-    for item in [questions_data]:
+    print(f"Running agent on {len(questions_data)} questions...")
+    for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
+        question_file = item.get("file_name")
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = agent(question_text, question_file, task_id)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             print(f"Question: {item}, Task ID: {task_id}, Submitted Answer: {submitted_answer}")
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})

prompts.yaml

@@ -9,28 +9,7 @@ system_prompt: |-
   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.
 
-  You may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags.
-
-
   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
-  answer = document_qa(document=document, question="Who is the oldest person mentioned?")
-  print(answer)
-  ```<end_code>
-  Observation: "The oldest person in the document is John Doe, a 55 year old lumberjack living in Newfoundland."
-
-  Thought: I will now generate an image showcasing the oldest person.
-  Code:
-  ```py
-  image = image_generator("A portrait of John Doe, a 55-year-old man living in Canada.")
-  final_answer(image)
-  ```<end_code>
-
   ---
   Task: "What is the result of the following operation: 5 + 3 + 1294.678?"
 
@@ -183,8 +162,7 @@ system_prompt: |-
   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.
 
-  Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
-
+  Be careful to follow the exact submission format and instruction.
   Now Begin!
 planning:
   initial_plan: |-
@@ -225,6 +203,7 @@ planning:
         """
     {% endfor %}
     ```
+    You must prefer generic tools over specific one: for example prefer search or visit web page instead of wikipedia. Use wikipedia only when stated.
 
     {%- if managed_agents and managed_agents.values() | list %}
     You can also give tasks to team members.
@@ -287,6 +266,7 @@ planning:
         {%- endfor %}"""
     {% endfor %}
     ```
+    You must prefer generic tools over specific one: for example prefer search or visit web page instead of wikipedia. Use wikipedia only when stated.
 
     {%- if managed_agents and managed_agents.values() | list %}
     You can also give tasks to team members.
@@ -317,6 +297,10 @@ managed_agent:
     ### 2. Task outcome (extremely detailed version):
     ### 3. Additional context (if relevant):
 
+    Be careful to follow the exact submission format and instruction.
+
+    Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+
     Put all these in your final_answer tool, everything that you do not pass as an argument to final_answer will be lost.
     And 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: |-
@@ -326,7 +310,7 @@ final_answer:
   pre_messages: |-
     An agent tried to answer a user query but it got stuck and failed to do so. You are tasked with providing an answer instead. Here is the agent's memory:
   post_messages: |-
+    Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+
     Based on the above, please provide an answer to the following user task:
     {{task}}
-    We expect submissions to be json-line files with the following format. The first two fields are mandatory, reasoning_trace is optional:
-    ```{"model_answer": "Answer 1 from your model", "reasoning_trace": ""}```

requirements.txt

@@ -3,10 +3,29 @@ gradio[oauth]
 requests
 duckduckgo-search
 smolagents
+smolagents[litellm]
 markdownify
 typing
 numpy
 pandas
-smolagents[litellm]
 numpy
+wikipedia-api
+openpyxl
+openai
+yfinance
+lancedb
+tantivy
+pypdf
+exa-py
+newspaper4k
+lxml_html_clean
+sqlalchemy
+agno
+beautifulsoup4
+wikipedia
+langchain-community
 qwen_vl_utils
+langgraph
+langchain[openai]
+rizaio
+google-search-results