accountant swarm fixes

playground/demos/accountant_team/accountant_team.py

@@ -1,35 +1,96 @@
-import re
 from swarms.models.nougat import Nougat
 from swarms.structs import Flow
-from swarms.models import OpenAIChat
-from swarms.models import LayoutLMDocumentQA
+from swarms.models import OpenAIChat, Anthropic
+from typing import List
 
-# # URL of the image of the financial document
-IMAGE_OF_FINANCIAL_DOC_URL = "bank_statement_2.jpg"
 
-# Example usage
-api_key = ""
+# Base llms
+llm1 = OpenAIChat()
+llm2 = Anthropic()
+nougat = Nougat()
 
-# Initialize the language flow
-llm = OpenAIChat(
-    openai_api_key=api_key,
-)
 
-# LayoutLM Document QA
-pdf_analyzer = LayoutLMDocumentQA()
+# Prompts for each agent
+SUMMARY_AGENT_PROMPT = """
+    Generate an actionable summary of this financial document be very specific and precise, provide bulletpoints be very specific provide methods of lowering expenses: {answer}"
+"""
+
 
-question = "What is the total amount of expenses?"
-answer = pdf_analyzer(
-    question,
-    IMAGE_OF_FINANCIAL_DOC_URL,
+# Agents
+user_consultant_agent = Flow(
+    llm=llm1,
+)
+doc_analyzer_agent = Flow(
+    llm=llm1,
+)
+summary_generator_agent = Flow(
+    llm=llm2,
+)
+fraud_detection_agent = Flow(
+    llm=llm2,
+)
+decision_making_support_agent = Flow(
+    llm=llm2,
 )
 
-# Initialize the Flow with the language flow
-agent = Flow(llm=llm)
-SUMMARY_AGENT_PROMPT = f"""
-Generate an actionable summary of this financial document be very specific and precise, provide bulletpoints be very specific provide methods of lowering expenses: {answer}"
-"""
 
-# Add tasks to the workflow
-summary_agent = agent.run(SUMMARY_AGENT_PROMPT)
-print(summary_agent)
+class AccountantSwarms:
+    """
+    Accountant Swarms is a collection of agents that work together to help
+    accountants with their work.
+
+    Flow: analyze doc -> detect fraud -> generate summary -> decision making support
+
+    The agents are:
+    - User Consultant: Asks the user many questions
+    - Document Analyzer: Extracts text from the image of the financial document
+    - Fraud Detection: Detects fraud in the document
+    - Summary Agent: Generates an actionable summary of the document
+    - Decision Making Support: Provides decision making support to the accountant
+
+    The agents are connected together in a workflow that is defined in the
+    run method.
+
+    The workflow is as follows:
+    1. The Document Analyzer agent extracts text from the image of the
+    financial document.
+    2. The Fraud Detection agent detects fraud in the document.
+    3. The Summary Agent generates an actionable summary of the document.
+    4. The Decision Making Support agent provides decision making support
+    to the accountant.
+
+    Example:
+    >>> accountant_swarms = AccountantSwarms(
+
+
+    """
+
+    def __init__(
+        self,
+        financial_document_img: str,
+        financial_document_list_img: List[str] = None,
+        fraud_detection_instructions: str = None,
+        summary_agent_instructions: str = None,
+        decision_making_support_agent_instructions: str = None,
+    ):
+        super().__init__()
+        self.financial_document_img = financial_document_img
+        self.fraud_detection_instructions = fraud_detection_instructions
+        self.summary_agent_instructions = summary_agent_instructions
+
+    def run(self):
+        # Extract text from the image
+        analyzed_doc = self.nougat(self.financial_document_img)
+
+        # Detect fraud in the document
+        fraud_detection_agent_output = self.fraud_detection_agent(analyzed_doc)
+
+        # Generate an actionable summary of the document
+        summary_agent_output = self.summary_agent(fraud_detection_agent_output)
+
+        # Provide decision making support to the accountant
+        decision_making_support_agent_output = self.decision_making_support_agent(
+            summary_agent_output
+        )
+
+        return decision_making_support_agent_output

playground/demos/paper_to_code.py

@@ -0,0 +1,19 @@
+from swarms.structs import Flow, SequentialWorkflow
+from swarms.models import OpenAIChat, Anthropic
+
+# llm
+llm = OpenAIChat()
+llm2 = Anthropic()
+
+# 2 Flows, one that creates an algorithmic pseuedocode and another that creates the pytorch code
+flow1 = Flow(llm2, max_loops=1)
+flow2 = Flow(llm, max_loops=1)
+
+# SequentialWorkflow
+workflow = SequentialWorkflow(
+    [flow1, flow2],
+    max_loops=1,
+    name="Paper to Code",
+    autosave=True,
+    description="This workflow takes a paper and converts it to code.",
+)

playground/structs/fuyu_flow.py

@@ -0,0 +1,10 @@
+from swarms import Flow, Fuyu
+
+llm = Fuyu()
+
+flow = Flow(max_loops="auto", llm=llm)
+
+flow.run(
+    task="Describe this image in a few sentences: ",
+    img="https://unsplash.com/photos/0pIC5ByPpZY",
+)

playground/structs/multi_modal_flow.py

@@ -0,0 +1,14 @@
+# This might not work in the beginning but it's a starting point
+from swarms.structs import Flow, GPT4V
+
+llm = GPT4V()
+
+flow = Flow(
+    max_loops="auto",
+    llm=llm,
+)
+
+flow.run(
+    task="Describe this image in a few sentences: ",
+    img="https://unsplash.com/photos/0pIC5ByPpZY",
+)

swarms/structs/flow.py

@@ -46,6 +46,7 @@ commands: {
     }
 }
 
+-------------TOOLS---------------------------
 {tools}
 """
 
@@ -149,14 +150,16 @@ class Flow:
         dynamic_loops: Optional[bool] = False,
         interactive: bool = False,
         dashboard: bool = False,
-        agent_name: str = "Flow agent",
+        agent_name: str = " Autonomous Agent XYZ1B",
         system_prompt: str = FLOW_SYSTEM_PROMPT,
         # tools: List[Any] = None,
         dynamic_temperature: bool = False,
+        SOP: str = None,
         saved_state_path: Optional[str] = "flow_state.json",
         autosave: bool = False,
         context_length: int = 8192,
-        user_name: str = "Human",
+        user_name: str = "Human:",
+        self_healing: bool = False,
         **kwargs: Any,
     ):
         self.llm = llm
@@ -175,6 +178,9 @@ class Flow:
         self.dynamic_temperature = dynamic_temperature
         self.dynamic_loops = dynamic_loops
         self.user_name = user_name
+        self.context_length = context_length
+        # SOPS to inject into the system prompt
+        self.SOP = SOP
         # The max_loops will be set dynamically if the dynamic_loop
         if self.dynamic_loops:
             self.max_loops = "auto"
@@ -184,6 +190,7 @@ class Flow:
         self.saved_state_path = saved_state_path
         self.autosave = autosave
         self.response_filters = []
+        self.self_healing = self_healing
 
     def provide_feedback(self, feedback: str) -> None:
         """Allow users to provide feedback on the responses."""
@@ -688,14 +695,6 @@ class Flow:
             return "Timeout"
         return response
 
-    # def backup_memory_to_s3(self, bucket_name: str, object_name: str):
-    #     """Backup the memory to S3"""
-    #     import boto3
-
-    #     s3 = boto3.client("s3")
-    #     s3.put_object(Bucket=bucket_name, Key=object_name, Body=json.dumps(self.memory))
-    #     print(f"Backed up memory to S3: {bucket_name}/{object_name}")
-
     def analyze_feedback(self):
         """Analyze the feedback for issues"""
         feedback_counts = {}
@@ -920,3 +919,40 @@ class Flow:
     def update_retry_interval(self, retry_interval: int):
         """Update the retry interval"""
         self.retry_interval = retry_interval
+
+    def self_healing(self, **kwargs):
+        """
+        Self healing by debugging errors and refactoring its own code
+
+        Args:
+            **kwargs (Any): Any additional keyword arguments
+        """
+        # Run the flow
+        response = self.run_with_timeout("flow")
+
+        # If an error occurs, save the state
+        if not self.validate_response(response):
+            self.save_state("previous_state.txt")
+
+        # Refactor the code
+        self.refactor_code()
+
+        # Run the flow again
+        response = self.run_with_timeout("flow")
+
+        # If the error occurs again, revert to the previous state
+        if not self.validate_response(response):
+            self.load_state("previous_state.txt")
+
+        # If the error does not occur, continue
+        else:
+            print("Self-healing successful! Bug fixed!")
+
+        return response
+
+    def refactor_code(self):
+        """
+        Refactor the code
+        """
+        # Add your code here to refactor the code
+        pass

swarms/structs/sequential_workflow.py

@@ -107,6 +107,8 @@ class SequentialWorkflow:
     tasks: List[Task] = field(default_factory=list)
     max_loops: int = 1
     autosave: bool = False
+    name: str = (None,)
+    description: str = (None,)
     saved_state_filepath: Optional[str] = "sequential_workflow_state.json"
     restore_state_filepath: Optional[str] = None
     dashboard: bool = False
@@ -248,6 +250,8 @@ class SequentialWorkflow:
                 f"""
                 Sequential Workflow Dashboard
                 --------------------------------
+                Name: {self.name}
+                Description: {self.description}
                 Tasks: {len(self.tasks)}
                 Max Loops: {self.max_loops}
                 Autosave: {self.autosave}