account swarm + layout document fix

.gitignore

@@ -28,6 +28,7 @@ error.txt
 
 # C extensions
 *.so
+.ruff_cache
 
 
 errors.txt

CONTRIBUTING.md

@@ -111,7 +111,7 @@ You can learn more about mkdocs on the [mkdocs website](https://www.mkdocs.org/)
 
 3. Make sure the script has execute permissions:
    ```sh
-   chmod +x quality.sh
+   chmod +x code_quality.sh
    ```
 
 4. Run the script:

demos/accountant_team/accountant_team.py

@@ -1,50 +1,35 @@
-# !pip install --upgrade swarms==2.0.6
+import re
-
-from swarms.models import BioGPT
 from swarms.models.nougat import Nougat
 from swarms.structs import Flow
+from swarms.models import OpenAIChat
+from swarms.models import LayoutLMDocumentQA
 
 # # URL of the image of the financial document
 IMAGE_OF_FINANCIAL_DOC_URL = "bank_statement_2.jpg"
 
 # Example usage
-api_key = ""  # Your actual API key here
+api_key = ""
-
-# Initialize the OCR model
-
 
 # Initialize the language flow
-llm = BioGPT()
+llm = OpenAIChat(
-
+    openai_api_key=api_key,
-
+)
-# Create a prompt for the language model
-def summary_agent_prompt(analyzed_doc: str):
-    model = Nougat(
-        max_new_tokens=5000,
-    )
-
-    out = model(analyzed_doc)
-
-    return f"""
-    Generate an actionable summary of this financial document, provide bulletpoints:
 
-    Here is the Analyzed Document:
+# LayoutLM Document QA
-    ---
+pdf_analyzer = LayoutLMDocumentQA()
-    {out}
-    """
 
+question = "What is the total amount of expenses?"
+answer = pdf_analyzer(
+    question,
+    IMAGE_OF_FINANCIAL_DOC_URL,
+)
 
 # Initialize the Flow with the language flow
-flow1 = Flow(llm=llm, max_loops=1, dashboard=False)
+agent = Flow(llm=llm)
-
+SUMMARY_AGENT_PROMPT = f"""
-# Create another Flow for a different task
+Generate an actionable summary of this financial document be very specific and precise, provide bulletpoints be very specific provide methods of lowering expenses: {answer}"
-flow2 = Flow(llm=llm, max_loops=1, dashboard=False)
+"""
-
 
 # Add tasks to the workflow
-summary_agent = flow1.run(summary_agent_prompt(IMAGE_OF_FINANCIAL_DOC_URL))
+summary_agent = agent.run(SUMMARY_AGENT_PROMPT)
-
+print(summary_agent)
-# Suppose the next task takes the output of the first task as input
-out = flow2.run(
-    f"Provide an actionable step by step plan on how to cut costs from the analyzed financial document. {summary_agent}"
-)

example.py

@@ -1,7 +1,7 @@
 from swarms.models import OpenAIChat
 from swarms.structs import Flow
 
-api_key = "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"
+api_key = ""
 
 # Initialize the language model, this model can be swapped out with Anthropic, ETC, Huggingface Models like Mistral, ETC
 llm = OpenAIChat(

pyproject.toml

@@ -24,7 +24,7 @@ classifiers = [
 [tool.poetry.dependencies]
 python = "^3.8.1"
 transformers = "*"
-openai = "*"
+openai = "0.28.1"
 langchain = "*"
 asyncio = "*"
 nest_asyncio = "*"

sequential_workflow_example.py

@@ -3,7 +3,7 @@ from swarms.structs import Flow
 from swarms.structs.sequential_workflow import SequentialWorkflow
 
 # Example usage
-api_key = ""  # Your actual API key here
+api_key = ""  
 
 # Initialize the language flow
 llm = OpenAIChat(

swarms/__init__.py

@@ -1,9 +1,3 @@
-from swarms.agents import *
-from swarms.swarms import *
-from swarms.structs import *
-from swarms.models import *  # import * only works when __all__ = [] is defined in __init__.py
-from swarms.chunkers import *
-from swarms.workers import *
 import os
 import warnings
 
@@ -12,3 +6,9 @@ warnings.filterwarnings("ignore", category=UserWarning)
 # disable tensorflow warnings
 
 os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
+from swarms.agents import *
+from swarms.swarms import *
+from swarms.structs import *
+from swarms.models import *  # import * only works when __all__ = [] is defined in __init__.py
+from swarms.chunkers import *
+from swarms.workers import *

swarms/models/layoutlm_document_qa.py

@@ -3,10 +3,8 @@ LayoutLMDocumentQA is a multimodal good for
 visual question answering on real world docs lik invoice, pdfs, etc
 """
 from transformers import pipeline
-from swarms.models.base import AbstractModel
 
-
+class LayoutLMDocumentQA:
-class LayoutLMDocumentQA(AbstractModel):
     """
     LayoutLMDocumentQA for document question answering:
 

swarms/models/nougat.py

@@ -8,7 +8,7 @@ format
 - Extracting metadata from pdfs
 
 """
-
+import re
 import torch
 from PIL import Image
 from transformers import NougatProcessor, VisionEncoderDecoderModel
@@ -70,5 +70,18 @@ class Nougat:
         sequence = self.processor.post_process_generation(sequence,
                                                           fix_markdown=False)
 
-        out = print(repr(sequence))
+        out = print(sequence)
         return out
+
+    def clean_nougat_output(raw_output):
+        # Define the pattern to extract the relevant data
+        daily_balance_pattern = r"\*\*(\d{2}/\d{2}/\d{4})\*\*\n\n\*\*([\d,]+\.\d{2})\*\*"
+        
+        # Find all matches of the pattern
+        matches = re.findall(daily_balance_pattern, raw_output)
+        
+        # Convert the matches to a readable format
+        cleaned_data = ["Date: {}, Amount: {}".format(date, amount.replace(',', '')) for date, amount in matches]
+        
+        # Join the cleaned data with new lines for readability
+        return '\n'.join(cleaned_data)