Upload folder using huggingface_hub

.gitignore

@@ -0,0 +1 @@
+.env

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----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=
+-----END CERTIFICATE-----

company_info_search.py

@@ -0,0 +1,206 @@
+import gradio as gr
+from swarm import Swarm, Agent
+from openai import OpenAI
+from exa_py import Exa
+import os
+from dotenv import load_dotenv
+import tweepy
+import json
+
+load_dotenv()
+
+openai_client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+client = Swarm(client=openai_client)
+exa_client = Exa(api_key=os.getenv("EXA_API_KEY"))
+
+# Twitter API setup
+bearer_token = os.getenv('bearer_token')
+twitter_client = tweepy.Client(bearer_token=bearer_token)
+
+def search_prop_firm_info(query, num_results=5):
+    results = exa_client.search_and_contents(
+        query,
+        type="keyword",
+        num_results=int(num_results),
+        text=True,
+        start_published_date="2023-01-01",
+        category="company",
+        include_domains=["propfirmmatch.com"],
+        summary=True
+    )
+    formatted_results = []
+    for result in results.results:
+        formatted_results.append(f"Title: {result.title}\nURL: {result.url}\nSummary: {result.summary}\n")
+    return "\n".join(formatted_results)
+
+def search_trustpilot_reviews(company_name, num_results=3):
+    query = f"site:trustpilot.com {company_name} reviews"
+    results = exa_client.search_and_contents(
+        query,
+        type="keyword",
+        num_results=int(num_results),
+        text=True,
+        start_published_date="2023-01-01",
+        summary=True
+    )
+    formatted_results = []
+    for result in results.results:
+        formatted_results.append(f"Title: {result.title}\nURL: {result.url}\nSummary: {result.summary}\n")
+    return "\n".join(formatted_results)
+
+def search_tweets(query, max_results=100):
+    try:
+        formatted_query = query.replace('"', '').strip()
+        tweets = twitter_client.search_recent_tweets(query=formatted_query, max_results=max_results)
+        return tweets.data if tweets.data else []
+    except tweepy.errors.BadRequest as e:
+        print(f"BadRequest error: {e}")
+        return []
+    except tweepy.errors.TweepyException as e:
+        print(f"Tweepy error: {e}")
+        return []
+    except Exception as e:
+        print(f"Unexpected error in search_tweets: {e}")
+        return []
+
+twitter_sentiment_agent = Agent(
+    name="Twitter Sentiment Analyzer",
+    instructions="""You are an agent that analyzes Twitter sentiment for proprietary trading firms. 
+    Given a list of tweets about a specific firm, analyze the overall sentiment and provide a summary.
+    Consider the following:
+    1. Overall sentiment (positive, negative, or neutral)
+    2. Common themes or topics mentioned
+    3. Any notable praise or complaints
+    4. Level of engagement (replies, retweets, likes)
+    Provide a concise summary of your findings.""",
+    functions=[search_tweets],
+)
+
+trustpilot_review_agent = Agent(
+    name="TrustPilot Review Analyzer",
+    instructions="""You are an agent that searches for and analyzes TrustPilot reviews for proprietary trading firms. 
+    Use the search_trustpilot_reviews function to find reviews for a given company.
+    Your tasks are to:
+    1. Search for TrustPilot reviews using the provided company name.
+    2. Analyze the overall sentiment of the reviews (positive, negative, or mixed).
+    3. Identify common themes or recurring points in the reviews.
+    4. Note any standout positive or negative comments.
+    5. If available, mention the overall TrustPilot rating for the company.
+    6. Provide a concise summary of your findings, highlighting the most important aspects for a potential trader.
+    
+    Your summary should be informative and balanced, presenting both positives and negatives if they exist.""",
+    functions=[search_trustpilot_reviews],
+)
+
+prop_firm_search_agent = Agent(
+    name="Prop Firm Search",
+    instructions="""You are an agent that searches for proprietary trading firm information on propfirmmatch.com. Use the search_prop_firm_info function to find information based on the user's query. The function takes two parameters: query (string) and num_results (integer, default 5).
+
+    If the user names a specific firm:
+    1. Use the firm's name as the search query.
+    2. Call the search_prop_firm_info function with the firm's name.
+    3. Provide a detailed summary of the information found about the firm from propfirmmatch.com.
+
+    Always include relevant details such as leverage, accepted countries, and any unique features of the firms.""",
+    functions=[search_prop_firm_info],
+)
+
+score_agent = Agent(
+    name="Score Generator",
+    instructions="""You are an agent that generates an overall score for proprietary trading firms based on the information provided.
+    Consider the following factors:
+    1. Information from propfirmmatch.com
+    2. TrustPilot reviews
+    3. Twitter sentiment
+    4. Any unique features or advantages of the firm
+    
+    Generate a score out of 100, where:
+    90-100: Excellent
+    80-89: Very Good
+    70-79: Good
+    60-69: Fair
+    Below 60: Poor
+    
+    Provide a brief explanation for the score.
+    
+    Format your response as follows:
+    **Score:** (your score here)
+    **Twitter:** (Highlights of twitter analysis here)
+    **TrustPilot:** (Highlights / notable reviews here)
+    **PropFirmMatch:** (Summary of firm from search_propfirm_info / propfirmmatch agent)""",
+    functions=[],
+)
+
+def fetch_twitter_sentiment(company_name, num_tweets=100):
+    query = f"{company_name} -is:retweet"
+    tweets = search_tweets(query, max_results=num_tweets)
+    
+    if not tweets:
+        return "No tweets found."
+    
+    tweet_texts = [tweet.text for tweet in tweets]
+    tweet_data = "\n\n".join(tweet_texts)
+    
+    analysis_prompt = f"Analyze the sentiment of the following tweets about {company_name}:\n\n{tweet_data}"
+    
+    sentiment_response = client.run(twitter_sentiment_agent, messages=[{"role": "user", "content": analysis_prompt}])
+    sentiment_analysis = sentiment_response.messages[-1]["content"] if sentiment_response.messages else "No sentiment analysis available."
+    
+    return sentiment_analysis
+
+def search_prop_firms(query):
+    search_response = client.run(prop_firm_search_agent, messages=[{"role": "user", "content": query}])
+    search_results = search_response.messages[-1]["content"] if search_response.messages else "No search results."
+    
+    trustpilot_analysis = get_trustpilot_analysis(query)
+    twitter_sentiment = fetch_twitter_sentiment(query)
+    
+    combined_results = f"{search_results}\n\nTrustPilot Analysis:\n{trustpilot_analysis}\n\nTwitter Sentiment Analysis:\n{twitter_sentiment}"
+    
+    score_prompt = f"Generate a score for {query} based on the following information:\n\n{combined_results}"
+    score_response = client.run(score_agent, messages=[{"role": "user", "content": score_prompt}])
+    score_result = score_response.messages[-1]["content"] if score_response.messages else "No score available."
+    
+    return query, search_results, trustpilot_analysis, twitter_sentiment, score_result
+
+def get_trustpilot_analysis(firm_name):
+    trustpilot_prompt = f"Find and analyze TrustPilot reviews for {firm_name}"
+    trustpilot_response = client.run(trustpilot_review_agent, messages=[{"role": "user", "content": trustpilot_prompt}])
+    return trustpilot_response.messages[-1]["content"] if trustpilot_response.messages else "No TrustPilot analysis available."
+
+def format_report_card(query):
+    firm_name, search_results, trustpilot_analysis, twitter_sentiment, score_result = search_prop_firms(query)
+    
+    report_card = {
+        "firm_name": firm_name,
+        "overall_score": score_result,
+        "firm_info": search_results,
+        "trustpilot_analysis": trustpilot_analysis,
+        "twitter_sentiment": twitter_sentiment
+    }
+    
+    return json.dumps(report_card)
+
+def run_gradio_interface():
+    with gr.Blocks(theme=gr.themes.Soft()) as demo:
+        gr.Markdown("# Proprietary Trading Firm Analysis")
+        
+        with gr.Row():
+            with gr.Column(scale=2):
+                query_input = gr.Textbox(label="Enter firm name", lines=2)
+                search_button = gr.Button("Generate Report", variant="primary")
+            with gr.Column(scale=1):
+                gr.Markdown("### Example Queries")
+                gr.Examples(
+                    examples=["FTMO", "MyForexFunds", "The5ers"],
+                    inputs=query_input
+                )
+        
+        output = gr.JSON(label="Report Card")
+        
+        search_button.click(format_report_card, inputs=[query_input], outputs=[output])
+
+    demo.launch(share=True)
+
+if __name__ == "__main__":
+    run_gradio_interface()

multi_agent_swarm.py

@@ -0,0 +1,150 @@
+from swarm import Swarm, Agent
+from swarm.repl import run_demo_loop
+import os
+from dotenv import load_dotenv
+from openai import OpenAI
+from rich.console import Console
+from rich.panel import Panel
+from rich.text import Text
+from exa_py import Exa
+import json
+
+load_dotenv()  # This loads the variables from .env
+
+# Initialize the OpenAI client
+openai_client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
+
+# Initialize the Swarm client with the OpenAI client
+client = Swarm(client=openai_client)
+
+# Initialize the Exa client
+exa_client = Exa(api_key=os.getenv("EXA_API_KEY"))
+
+def transfer_to_executor(enhanced_prompt):
+    print(f"\nEnhancer Agent output:\n{enhanced_prompt}")
+    return executor_agent, {"prompt": enhanced_prompt}
+
+def transfer_to_planner(executed_response):
+    print(f"\nExecutor Agent output:\n{executed_response}")
+    return planner_agent, {"response": executed_response}
+
+def transfer_to_checker(executed_response):
+    print(f"\nExecutor Agent output:\n{executed_response}")
+    return checker_agent, {"response": executed_response}
+
+def transfer_to_enhancer(checked_response):
+    print(f"\nChecker Agent output:\n{checked_response}")
+    return enhancer_agent, {"response": checked_response}
+
+def search_internet(query, num_results=5):
+    results = exa_client.search(query, num_results=num_results)
+    formatted_results = []
+    for result in results:
+        formatted_results.append(f"Title: {result.title}\nURL: {result.url}\nSnippet: {result.snippet}\n")
+    return "\n".join(formatted_results)
+
+def transfer_to_internet_search(query):
+    print(f"\nTransferring to Internet Search Agent with query:\n{query}")
+    return internet_search_agent, {"query": query}
+
+enhancer_agent = Agent(
+    name="Enhancer",
+    instructions="""You are an agent that enhances user prompts. Your task is to:
+    1. Reword the user's input to be more clear, specific, and thorough.
+    2. Determine if the query requires internet search or not.
+    3. If internet search is required, call the transfer_to_internet_search function with the enhanced query.
+    4. If not, return the enhanced prompt with the following instructions prepended:
+
+    [Instructions for the next agent:
+    1. Begin by enclosing all thoughts within <thinking> tags, exploring multiple angles and approaches.
+    2. Break down the solution into clear steps within <step> tags.
+    3. Use <count> tags after each step to show the remaining budget. Stop when reaching 0.
+    4. Continuously adjust your reasoning based on intermediate results and reflections.
+    5. Regularly evaluate progress using <reflection> tags.
+    6. Synthesize the final answer within <answer> tags, providing a clear, concise summary.
+    7. Conclude with a final reflection on the overall solution.]
+
+    Ensure these instructions are clearly separated from the enhanced user prompt.""",
+    functions=[transfer_to_executor, transfer_to_internet_search],
+)
+
+clarifier_agent = Agent(
+    name="Clarifier",
+    instructions="You are an agent that clarifies and enhances user prompts. Reword the user's input to be more clear, specific, and thorough. Ask for additional information if needed.",
+    functions=[transfer_to_executor],
+)
+
+executor_agent = Agent(
+    name="Executor",
+    instructions="You are an agent that executes enhanced prompts. Provide a detailed, well-thought-out response to the enhanced question or request.",
+    functions=[transfer_to_planner],
+)
+
+checker_agent = Agent(
+    name="Checker",
+    instructions="You are an agent that checks responses for correctness. If correct, approve it. If not, edit and improve it. Always provide your reasoning.",
+    functions=[transfer_to_enhancer],
+)
+
+planner_agent = Agent(
+    name="Planner",
+    instructions="You are an agent that creates action plans based on the user's request and the executor's response. Provide a step-by-step plan with resources and instructions for the user to follow up on their request.",
+    functions=[],
+)
+
+internet_search_agent = Agent(
+    name="Internet Search",
+    instructions="You are an agent that searches the internet for relevant information. Use the search_internet function to find information, then summarize and present the findings. Always include the source URLs in your response.",
+    functions=[search_internet, transfer_to_executor],
+)
+
+if __name__ == "__main__":
+    console = Console()
+    console.print(Panel("Starting Multi-Agent Swarm. Type 'exit' to quit.", style="bold green"))
+
+    while True:
+        user_input = console.input("\n[bold cyan]User:[/bold cyan] ")
+        if user_input.lower() == 'exit':
+            break
+        console.print(Panel(f"[bold cyan]User input:[/bold cyan]\n{user_input}", border_style="cyan"))
+
+        # Enhancer Agent
+        enhanced_response = client.run(enhancer_agent, messages=[{"role": "user", "content": user_input}])
+        if enhanced_response.messages:
+            last_message = enhanced_response.messages[-1]
+            function_call = last_message.get("function_call")
+            if function_call and isinstance(function_call, dict) and function_call.get("name") == "transfer_to_internet_search":
+                # Internet Search Agent
+                search_query = function_call.get("arguments", {}).get("query", user_input)
+                search_response = client.run(internet_search_agent, messages=[{"role": "user", "content": search_query}])
+                search_results = search_response.messages[-1]["content"] if search_response.messages else "No search results."
+                console.print(Panel(f"[bold blue]Internet Search Results:[/bold blue]\n{search_results}", border_style="blue"))
+                
+                # Pass search results to Executor Agent
+                executed_response = client.run(executor_agent, messages=[
+                    {"role": "user", "content": user_input},
+                    {"role": "assistant", "content": f"Based on the internet search, here are the results:\n\n{search_results}\n\nPlease provide a detailed response to the user's query using this information."}
+                ])
+            else:
+                enhanced_prompt = last_message.get("content", user_input)
+                console.print(Panel(f"[bold green]Enhanced Prompt:[/bold green]\n{enhanced_prompt}", border_style="green"))
+                
+                # Executor Agent
+                executed_response = client.run(executor_agent, messages=[{"role": "user", "content": enhanced_prompt}])
+        else:
+            console.print(Panel("[bold red]Error: Enhancer Agent returned no response.[/bold red]", border_style="red"))
+            continue
+
+        executed_output = executed_response.messages[-1]["content"]
+        console.print(Panel(f"[bold yellow]Executor Response:[/bold yellow]\n{executed_output}", border_style="yellow"))
+
+        # Planner Agent
+        plan_response = client.run(planner_agent, messages=[
+            {"role": "user", "content": user_input},
+            {"role": "assistant", "content": executed_output},
+            {"role": "user", "content": "Based on this information, create an action plan with resources and instructions."}
+        ])
+        action_plan = plan_response.messages[-1]["content"]
+        console.print(Panel(f"[bold magenta]Action Plan:[/bold magenta]\n{action_plan}", border_style="magenta"))
+
+        console.print("\n[bold blue]Process Complete[/bold blue]")

readme.md

@@ -0,0 +1,43 @@
+---
+title: multi-agent
+app_file: company_info_search.py
+sdk: gradio
+sdk_version: 5.1.0
+---
+# Multi-Agent Swarm
+
+This example demonstrates a multi-agent swarm with three agents: an Enhancer, an Executor, and a Checker. The agents work together to process user queries and provide well-thought-out, verified responses.
+
+## Setup
+
+To run this example:
+
+1. Ensure you have installed the Swarm framework as described in the main README.
+2. Set up your `.env` file in the root directory with the necessary API key:
+   ```
+   OPENAI_API_KEY=your_openai_api_key_here
+   ```
+3. Navigate to this directory:
+   ```
+   cd examples/multi_agent_swarm
+   ```
+4. Run the example:
+   ```
+   python multi_agent_swarm.py
+   ```
+
+## Agents
+
+1. **Enhancer Agent**: Enhances user prompts by adding instructions for reasoning steps and chain of thought.
+2. **Executor Agent**: Executes the enhanced prompts and provides detailed, well-thought-out responses.
+3. **Checker Agent**: Checks responses for correctness, approves correct ones, and edits/improves incorrect ones.
+
+## Process Flow
+
+1. User input is received by the Enhancer Agent.
+2. Enhancer Agent enhances the prompt and transfers to the Executor Agent.
+3. Executor Agent processes the enhanced prompt and transfers the response to the Checker Agent.
+4. Checker Agent verifies the response. If correct, it's shown to the user. If not, it's edited and the process restarts from the Enhancer Agent.
+
+This example uses the `run_demo_loop` helper function to create an interactive Swarm session.
+

requirements.txt

@@ -0,0 +1,7 @@
+openai
+exa-py
+python-dotenv
+rich
+flask
+flask-cors
+gunicorn

wsgi.py

@@ -0,0 +1,5 @@
+from company_info_search import app
+
+if __name__ == "__main__":
+    app.run()
+