[CODE QUALITY]

playground/agents/mm_agent_example.py

@@ -4,14 +4,16 @@
 
 node = MultiModalAgent(load_dict)
 
-text = node.run_text("What is your name? Generate a picture of yourself")
+text = node.run_text(
+    "What is your name? Generate a picture of yourself"
+)
 
 img = node.run_img("/image1", "What is this image about?")
 
 chat = node.chat(
     (
-        "What is your name? Generate a picture of yourself. What is this image"
-        " about?"
+        "What is your name? Generate a picture of yourself. What is"
+        " this image about?"
     ),
     streaming=True,
 )

playground/demos/accountant_team/account_team2.py

@@ -53,7 +53,8 @@
 pdf_path = "bankstatement.pdf"
 fraud_detection_instructions = "Detect fraud in the document"
 summary_agent_instructions = (
-    "Generate an actionable summary of the document with action steps to take"
+    "Generate an actionable summary of the document with action steps"
+    " to take"
 )
 decision_making_support_agent_instructions = (
     "Provide decision making support to the business owner:"
@@ -77,5 +78,6 @@
 
 # Provide decision making support to the accountant
 decision_making_support_agent_output = decision_making_support_agent.run(
-    f"{decision_making_support_agent_instructions}: {summary_agent_output}"
+    f"{decision_making_support_agent_instructions}:"
+    f" {summary_agent_output}"
 )

playground/demos/accountant_team/accountant_team.py

@@ -81,7 +81,9 @@ def __init__(
         super().__init__()
         self.pdf_path = pdf_path
         self.list_pdfs = list_pdfs
-        self.fraud_detection_instructions = fraud_detection_instructions
+        self.fraud_detection_instructions = (
+            fraud_detection_instructions
+        )
         self.summary_agent_instructions = summary_agent_instructions
         self.decision_making_support_agent_instructions = (
             decision_making_support_agent_instructions
@@ -98,7 +100,8 @@ def run(self):
 
         # Generate an actionable summary of the document
         summary_agent_output = summary_generator_agent.run(
-            f"{self.summary_agent_instructions}: {fraud_detection_agent_output}"
+            f"{self.summary_agent_instructions}:"
+            f" {fraud_detection_agent_output}"
         )
 
         # Provide decision making support to the accountant
@@ -113,7 +116,9 @@ def run(self):
 swarm = AccountantSwarms(
     pdf_path="tesla.pdf",
     fraud_detection_instructions="Detect fraud in the document",
-    summary_agent_instructions="Generate an actionable summary of the document",
+    summary_agent_instructions=(
+        "Generate an actionable summary of the document"
+    ),
     decision_making_support_agent_instructions=(
         "Provide decision making support to the business owner:"
     ),

playground/demos/ad_gen/ad_gen.py

@@ -30,15 +30,34 @@ def __init__(self, product_name):
             "in a luxurious setting", "in a playful and colorful background", "in an ice cave setting",
             "in a serene and calm landscape"
         ]
+<<<<<<< HEAD
+=======
+        self.contexts = [
+            "high realism product ad (extremely creative)"
+        ]
+>>>>>>> 831147e ([CODE QUALITY])
 
     def generate_concept(self):
         theme = random.choice(self.themes)
         context = random.choice(self.contexts)
+<<<<<<< HEAD
         return f"An ad for {self.product_name} that embodies a {theme} theme {context}"
 
 # User input
 product_name = input("Enter a product name for ad creation (e.g., 'PS5', 'AirPods', 'Kirkland Vodka'): ")
 social_media_platform = input("Enter a social media platform (e.g., 'Facebook', 'Twitter', 'Instagram'): ")
+=======
+        return (
+            f"{theme} inside a {style} {self.product_name}, {context}"
+        )
+
+
+# User input
+product_name = input(
+    "Enter a product name for ad creation (e.g., 'PS5', 'AirPods',"
+    " 'Kirkland Vodka'): "
+)
+>>>>>>> 831147e ([CODE QUALITY])
 
 # Generate creative concept
 concept_generator = ProductAdConceptGenerator(product_name)
@@ -53,6 +72,16 @@ def generate_concept(self):
 ad_copy = ad_copy_agent.run(task=ad_copy_prompt)
 
 # Output the results
+<<<<<<< HEAD
 print("Creative Concept:", creative_concept)
 print("Image Path:", image_paths[0] if image_paths else "No image generated")
 print("Ad Copy:", ad_copy)
+=======
+print("Creative Concept:", concept_result)
+print("Design Ideas:", design_result)
+print("Ad Copy:", copywriting_result)
+print(
+    "Image Path:",
+    image_paths[0] if image_paths else "No image generated",
+)
+>>>>>>> 831147e ([CODE QUALITY])

playground/demos/ai_research_team/main.py

@@ -48,7 +48,9 @@
 
 paper = pdf_to_text(PDF_PATH)
 algorithmic_psuedocode_agent = paper_summarizer_agent.run(
-    "Focus on creating the algorithmic pseudocode for the novel method in this"
-    f" paper: {paper}"
+    "Focus on creating the algorithmic pseudocode for the novel"
+    f" method in this paper: {paper}"
+)
+pytorch_code = paper_implementor_agent.run(
+    algorithmic_psuedocode_agent
 )
-pytorch_code = paper_implementor_agent.run(algorithmic_psuedocode_agent)

playground/demos/assembly/assembly.py

@@ -7,10 +7,10 @@
 llm = GPT4VisionAPI()
 
 task = (
-    "Analyze this image of an assembly line and identify any issues such as"
-    " misaligned parts, defects, or deviations from the standard assembly"
-    " process. IF there is anything unsafe in the image, explain why it is"
-    " unsafe and how it could be improved."
+    "Analyze this image of an assembly line and identify any issues"
+    " such as misaligned parts, defects, or deviations from the"
+    " standard assembly process. IF there is anything unsafe in the"
+    " image, explain why it is unsafe and how it could be improved."
 )
 img = "assembly_line.jpg"
 

playground/demos/autobloggen.py

@@ -9,7 +9,8 @@
 
 # Prompts
 topic_selection_task = (
-    "Generate 10 topics on gaining mental clarity using ancient practices"
+    "Generate 10 topics on gaining mental clarity using ancient"
+    " practices"
 )
 
 
@@ -54,7 +55,9 @@ def __init__(
     ):
         self.llm = llm()
         self.topic_selection_task = topic_selection_task
-        self.topic_selection_agent_prompt = topic_selection_agent_prompt
+        self.topic_selection_agent_prompt = (
+            topic_selection_agent_prompt
+        )
         self.objective = objective
         self.iterations = iterations
         self.max_retries = max_retries
@@ -90,7 +93,9 @@ def get_review_prompt(self, article: str):
 
     def step(self):
         """Steps through the task"""
-        topic_selection_agent = self.llm(self.topic_selection_agent_prompt)
+        topic_selection_agent = self.llm(
+            self.topic_selection_agent_prompt
+        )
         topic_selection_agent = self.print_beautifully(
             "Topic Selection Agent", topic_selection_agent
         )
@@ -100,7 +105,9 @@ def step(self):
 
         # Agent that reviews the draft
         review_agent = self.llm(self.get_review_prompt(draft_blog))
-        review_agent = self.print_beautifully("Review Agent", review_agent)
+        review_agent = self.print_beautifully(
+            "Review Agent", review_agent
+        )
 
         # Agent that publishes on social media
         distribution_agent = self.llm(
@@ -119,7 +126,11 @@ def run(self):
             except Exception as error:
                 print(
                     colored(
-                        f"Error while running AutoBlogGenSwarm {error}", "red"
+                        (
+                            "Error while running AutoBlogGenSwarm"
+                            f" {error}"
+                        ),
+                        "red",
                     )
                 )
                 if attempt == self.retry_attempts - 1:

playground/demos/autotemp/autotemp.py

@@ -47,7 +47,11 @@ def evaluate_output(self, output, temperature):
         """
         score_text = self.llm(eval_prompt, temperature=0.5)
         score_match = re.search(r"\b\d+(\.\d)?\b", score_text)
-        return round(float(score_match.group()), 1) if score_match else 0.0
+        return (
+            round(float(score_match.group()), 1)
+            if score_match
+            else 0.0
+        )
 
     def run(self, prompt, temperature_string):
         print("Starting generation process...")

playground/demos/autotemp/blog_gen.py

@@ -12,7 +12,9 @@ def __init__(
         blog_topic,
         temperature_range: str = "0.4,0.6,0.8,1.0,1.2",
     ):  # Add blog_topic as an argument
-        self.openai_chat = OpenAIChat(openai_api_key=api_key, temperature=0.8)
+        self.openai_chat = OpenAIChat(
+            openai_api_key=api_key, temperature=0.8
+        )
         self.auto_temp = AutoTemp(api_key)
         self.temperature_range = temperature_range
         self.workflow = SequentialWorkflow(max_loops=5)
@@ -52,11 +54,15 @@ def run_workflow(self):
             )
 
             chosen_topic = topic_output.split("\n")[0]
-            print(colored("Selected topic: " + chosen_topic, "yellow"))
+            print(
+                colored("Selected topic: " + chosen_topic, "yellow")
+            )
 
             # Initial draft generation with AutoTemp
-            initial_draft_prompt = self.DRAFT_WRITER_SYSTEM_PROMPT.replace(
-                "{{CHOSEN_TOPIC}}", chosen_topic
+            initial_draft_prompt = (
+                self.DRAFT_WRITER_SYSTEM_PROMPT.replace(
+                    "{{CHOSEN_TOPIC}}", chosen_topic
+                )
             )
             auto_temp_output = self.auto_temp.run(
                 initial_draft_prompt, self.temperature_range
@@ -89,13 +95,17 @@ def run_workflow(self):
             )
 
             # Distribution preparation using OpenAIChat
-            distribution_prompt = self.DISTRIBUTION_AGENT_SYSTEM_PROMPT.replace(
-                "{{ARTICLE_TOPIC}}", chosen_topic
+            distribution_prompt = (
+                self.DISTRIBUTION_AGENT_SYSTEM_PROMPT.replace(
+                    "{{ARTICLE_TOPIC}}", chosen_topic
+                )
             )
             distribution_result = self.openai_chat.generate(
                 [distribution_prompt]
             )
-            distribution_output = distribution_result.generations[0][0].text
+            distribution_output = distribution_result.generations[0][
+                0
+            ].text
             print(
                 colored(
                     (

playground/demos/autotemp/blog_gen_example.py

@@ -5,7 +5,9 @@
 def main():
     api_key = os.getenv("OPENAI_API_KEY")
     if not api_key:
-        raise ValueError("OPENAI_API_KEY environment variable not set.")
+        raise ValueError(
+            "OPENAI_API_KEY environment variable not set."
+        )
 
     blog_topic = input("Enter the topic for the blog generation: ")
 

playground/demos/developer_swarm/main.py

@@ -37,12 +37,18 @@
 
 # Documentation agent
 documentation_agent = Agent(
-    llm=llm, sop=DOCUMENTATION_SOP, max_loops=1,
+    llm=llm,
+    sop=DOCUMENTATION_SOP,
+    max_loops=1,
 )
 
 
 # Tests agent
-tests_agent = Agent(llm=llm, sop=TEST_SOP, max_loops=2,)
+tests_agent = Agent(
+    llm=llm,
+    sop=TEST_SOP,
+    max_loops=2,
+)
 
 
 # Run the documentation agent
@@ -52,6 +58,6 @@
 
 # Run the tests agent
 tests = tests_agent.run(
-    f"Write tests for the following code:{TASK} here is the documentation:"
-    f" {documentation}"
+    f"Write tests for the following code:{TASK} here is the"
+    f" documentation: {documentation}"
 )

playground/demos/nutrition/nutrition.py

@@ -12,14 +12,15 @@
 # Define prompts for various tasks
 MEAL_PLAN_PROMPT = (
     "Based on the following user preferences: dietary restrictions as"
-    " vegetarian, preferred cuisines as Italian and Indian, a total caloric"
-    " intake of around 2000 calories per day, and an exclusion of legumes,"
-    " create a detailed weekly meal plan. Include a variety of meals for"
-    " breakfast, lunch, dinner, and optional snacks."
+    " vegetarian, preferred cuisines as Italian and Indian, a total"
+    " caloric intake of around 2000 calories per day, and an"
+    " exclusion of legumes, create a detailed weekly meal plan."
+    " Include a variety of meals for breakfast, lunch, dinner, and"
+    " optional snacks."
 )
 IMAGE_ANALYSIS_PROMPT = (
-    "Identify the items in this fridge, including their quantities and"
-    " condition."
+    "Identify the items in this fridge, including their quantities"
+    " and condition."
 )
 
 
@@ -74,12 +75,15 @@ def generate_integrated_shopping_list(
     meal_plan_output, image_analysis, user_preferences
 ):
     # Prepare the prompt for the LLM
-    fridge_contents = image_analysis["choices"][0]["message"]["content"]
+    fridge_contents = image_analysis["choices"][0]["message"][
+        "content"
+    ]
     prompt = (
-        f"Based on this meal plan: {meal_plan_output}, and the following items"
-        f" in the fridge: {fridge_contents}, considering dietary preferences as"
-        " vegetarian with a preference for Italian and Indian cuisines,"
-        " generate a comprehensive shopping list that includes only the items"
+        f"Based on this meal plan: {meal_plan_output}, and the"
+        f" following items in the fridge: {fridge_contents},"
+        " considering dietary preferences as vegetarian with a"
+        " preference for Italian and Indian cuisines, generate a"
+        " comprehensive shopping list that includes only the items"
         " needed."
     )
 
@@ -124,6 +128,10 @@ def generate_integrated_shopping_list(
 
 with open("nutrition_output.txt", "w") as file:
     file.write("Meal Plan:\n" + meal_plan_output + "\n\n")
-    file.write("Integrated Shopping List:\n" + integrated_shopping_list + "\n")
+    file.write(
+        "Integrated Shopping List:\n"
+        + integrated_shopping_list
+        + "\n"
+    )
 
 print("Outputs have been saved to nutrition_output.txt")

playground/demos/positive_med/positive_med.py

@@ -41,7 +41,9 @@ def get_review_prompt(article):
     return prompt
 
 
-def social_media_prompt(article: str, goal: str = "Clicks and engagement"):
+def social_media_prompt(
+    article: str, goal: str = "Clicks and engagement"
+):
     prompt = SOCIAL_MEDIA_SYSTEM_PROMPT_AGENT.replace(
         "{{ARTICLE}}", article
     ).replace("{{GOAL}}", goal)
@@ -50,11 +52,12 @@ def social_media_prompt(article: str, goal: str = "Clicks and engagement"):
 
 # Agent that generates topics
 topic_selection_task = (
-    "Generate 10 topics on gaining mental clarity using ancient practices"
+    "Generate 10 topics on gaining mental clarity using ancient"
+    " practices"
 )
 topics = llm(
-    f"Your System Instructions: {TOPIC_GENERATOR_SYSTEM_PROMPT}, Your current"
-    f" task: {topic_selection_task}"
+    f"Your System Instructions: {TOPIC_GENERATOR_SYSTEM_PROMPT}, Your"
+    f" current task: {topic_selection_task}"
 )
 
 dashboard = print(