New tool to create linkedin posts

.gitignore

@@ -0,0 +1,2 @@
+__pycache__
+venv

app.py

@@ -1,40 +1,16 @@
 from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
-import datetime
-import requests
-import pytz
 import yaml
 from tools.final_answer import FinalAnswerTool
+from tools.visit_webpage import VisitWebpageTool
+from tools.linkedin_post_composer import LinkedInPostPromptComposerTool
 
 from Gradio_UI import GradioUI
 
-# Below is an example of a tool that does nothing. Amaze us with your creativity !
-@tool
-def my_custom_tool(arg1:str, arg2:int)-> str: #it's import to specify the return type
-    #Keep this format for the description / args / args description but feel free to modify the tool
-    """A tool that does nothing yet 
-    Args:
-        arg1: the first argument
-        arg2: the second argument
-    """
-    return "What magic will you build ?"
-
-@tool
-def get_current_time_in_timezone(timezone: str) -> str:
-    """A tool that fetches the current local time in a specified timezone.
-    Args:
-        timezone: A string representing a valid timezone (e.g., 'America/New_York').
-    """
-    try:
-        # Create timezone object
-        tz = pytz.timezone(timezone)
-        # Get current time in that timezone
-        local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
-        return f"The current local time in {timezone} is: {local_time}"
-    except Exception as e:
-        return f"Error fetching time for timezone '{timezone}': {str(e)}"
-
 
 final_answer = FinalAnswerTool()
+visit_web_page = VisitWebpageTool()
+linkedin_post_composer = LinkedInPostPromptComposerTool()
+search = DuckDuckGoSearchTool()
 
 # If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:
 # model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud' 
@@ -42,7 +18,7 @@ final_answer = FinalAnswerTool()
 model = HfApiModel(
 max_tokens=2096,
 temperature=0.5,
-model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
+model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud',# it is possible that this model may be overloaded
 custom_role_conversions=None,
 )
 
@@ -55,7 +31,7 @@ with open("prompts.yaml", 'r') as stream:
     
 agent = CodeAgent(
     model=model,
-    tools=[final_answer], ## add your tools here (don't remove final answer)
+    tools=[linkedin_post_composer, visit_web_page, search, image_generation_tool, final_answer], ## add your tools here (don't remove final answer)
     max_steps=6,
     verbosity_level=1,
     grammar=None,

tools/linkedin_post_composer.py

@@ -0,0 +1,56 @@
+from smolagents.tools import Tool
+
+class LinkedInPostPromptComposerTool(Tool):
+    name = "linkedin_post_prompt_composer"
+    description = (
+        "Generates a detailed prompt by synthesizing conversation context, extracted webpage insights, "
+        "and additional instructions. This prompt can then be used by a separate final answer tool to produce "
+        "a polished LinkedIn post."
+    )
+    inputs = {
+        "context": {
+            "type": "string",
+            "description": (
+                "A summary of your brainstorming or discussion context. Include key ideas, opinions, "
+                "and relevant back-and-forth that should influence the final post."
+            )
+        },
+        "extracted_info": {
+            "type": "string",
+            "description": (
+                "Key points, data, or insights extracted from webpages, reports, or articles that provide "
+                "the factual basis for the post."
+            )
+        },
+        "instructions": {
+            "type": "string",
+            "description": (
+                "Additional guidance such as desired tone, target audience, style, or specific calls-to-action. "
+                "For example: 'Make it conversational yet authoritative, include a compelling hook, and end with a question.'"
+            ),
+            "nullable": True
+        }
+    }
+    output_type = "string"
+
+    def forward(self, context: str, extracted_info: str, instructions: str = "") -> str:
+        prompt = (
+            "You are an experienced LinkedIn content strategist and influencer. Using the inputs provided, "
+            "generate a comprehensive prompt for an LLM to produce a final LinkedIn post that meets the following criteria:\n\n"
+            "1. **Compelling Hook:** Begin with a strong headline or opening line that grabs attention.\n"
+            "2. **Coherent Narrative:** Seamlessly blend the discussion context and the extracted information into a clear, engaging story.\n"
+            "3. **Actionable Insights:** Offer actionable advice or takeaways that provide real value to a professional audience.\n"
+            "4. **Call-to-Action:** Include a call-to-action to encourage comments, shares, or further engagement.\n"
+            "5. **Trending Hashtags:** Append 3-5 relevant and trending LinkedIn hashtags at the end.\n\n"
+            "The final post should be approximately 200–300 words, using a professional yet conversational tone.\n\n"
+            "### Input Sections:\n"
+            "**Discussion Context:**\n" + context + "\n\n"
+            "**Extracted Information:**\n" + extracted_info + "\n\n"
+        )
+        if instructions:
+            prompt += "**Additional Instructions:**\n" + instructions + "\n\n"
+        prompt += "Now, produce the final answer generating the LinkedIn post based on the above inputs."
+        return prompt
+
+    def __init__(self, *args, **kwargs):
+        self.is_initialized = False