[DEPENDENCY CHECK]

Dockerfile

@@ -1,42 +0,0 @@
-
-# ==================================
-# Use an official Python runtime as a parent image
-FROM python:3.9-slim
-
-# Set environment variables
-ENV PYTHONDONTWRITEBYTECODE 1
-ENV PYTHONUNBUFFERED 1
-
-# Set the working directory in the container
-WORKDIR /usr/src/swarm_cloud
-
-
-# Install Python dependencies
-# COPY requirements.txt and pyproject.toml if you're using poetry for dependency management
-COPY requirements.txt .
-RUN pip install --upgrade pip
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Install the 'swarms' package, assuming it's available on PyPI
-RUN pip install swarms
-
-# Copy the rest of the application
-COPY . .
-
-# Add entrypoint script if needed
-# COPY ./entrypoint.sh .
-# RUN chmod +x /usr/src/swarm_cloud/entrypoint.sh
-
-# Expose port if your application has a web interface
-# EXPOSE 5000
-
-# # Define environment variable for the swarm to work
-# ENV SWARM_API_KEY=your_swarm_api_key_here
-
-# # Add Docker CMD or ENTRYPOINT script to run the application
-# CMD python your_swarm_startup_script.py
-# Or use the entrypoint script if you have one
-# ENTRYPOINT ["/usr/src/swarm_cloud/entrypoint.sh"]
-
-# If you're using `CMD` to execute a Python script, make sure it's executable
-# RUN chmod +x your_swarm_startup_script.py

example.py

@@ -17,6 +17,7 @@ llm = OpenAIChat(
     temperature=0.5,
     model_name="gpt-4",
     openai_api_key=api_key,
+    max_tokens=1000,
 )
 
 

playground/demos/accountant_team/accountant_team.py

@@ -1,125 +0,0 @@
-import os
-from typing import List
-
-from dotenv import load_dotenv
-
-from swarms.models import Anthropic, OpenAIChat
-from swarms.prompts.accountant_swarm_prompts import (
-    DECISION_MAKING_PROMPT,
-    DOC_ANALYZER_AGENT_PROMPT,
-    FRAUD_DETECTION_AGENT_PROMPT,
-    SUMMARY_GENERATOR_AGENT_PROMPT,
-)
-from swarms.structs import Agent
-from swarms.utils.pdf_to_text import pdf_to_text
-
-# Environment variables
-load_dotenv()
-anthropic_api_key = os.getenv("ANTHROPIC_API_KEY")
-openai_api_key = os.getenv("OPENAI_API_KEY")
-
-
-# Base llms
-llm1 = OpenAIChat(
-    openai_api_key=openai_api_key,
-)
-
-llm2 = Anthropic(
-    anthropic_api_key=anthropic_api_key,
-)
-
-
-# Agents
-doc_analyzer_agent = Agent(
-    llm=llm1,
-    sop=DOC_ANALYZER_AGENT_PROMPT,
-)
-summary_generator_agent = Agent(
-    llm=llm2,
-    sop=SUMMARY_GENERATOR_AGENT_PROMPT,
-)
-decision_making_support_agent = Agent(
-    llm=llm2,
-    sop=DECISION_MAKING_PROMPT,
-)
-
-
-class AccountantSwarms:
-    """
-    Accountant Swarms is a collection of agents that work together to help
-    accountants with their work.
-
-    Agent: 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
-
-    """
-
-    def __init__(
-        self,
-        pdf_path: str,
-        list_pdfs: List[str] = None,
-        fraud_detection_instructions: str = None,
-        summary_agent_instructions: str = None,
-        decision_making_support_agent_instructions: str = None,
-    ):
-        super().__init__()
-        self.pdf_path = pdf_path
-        self.list_pdfs = list_pdfs
-        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
-        )
-
-    def run(self):
-        # Transform the pdf to text
-        pdf_text = pdf_to_text(self.pdf_path)
-
-        # Detect fraud in the document
-        fraud_detection_agent_output = doc_analyzer_agent.run(
-            f"{self.fraud_detection_instructions}: {pdf_text}"
-        )
-
-        # Generate an actionable summary of the document
-        summary_agent_output = summary_generator_agent.run(
-            f"{self.summary_agent_instructions}:"
-            f" {fraud_detection_agent_output}"
-        )
-
-        # Provide decision making support to the accountant
-        decision_making_support_agent_output = decision_making_support_agent.run(
-            f"{self.decision_making_support_agent_instructions}:"
-            f" {summary_agent_output}"
-        )
-
-        return decision_making_support_agent_output
-
-
-swarm = AccountantSwarms(
-    pdf_path="tesla.pdf",
-    fraud_detection_instructions="Detect fraud in 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/logistics/logistics.py

@@ -11,50 +11,67 @@ from swarms.prompts.logistics import (
     Sustainability_Agent_Prompt,
     Efficiency_Agent_Prompt,
 )
+# from swarms.utils.phoenix_handler import phoenix_trace_decorator
+# from swarms.utils.banana_wrapper import banana
 
 load_dotenv()
 api_key = os.getenv("OPENAI_API_KEY")
 
+# GPT4VisionAPI or llama
+# @banana #- deploy to banana
 llm = GPT4VisionAPI(openai_api_key=api_key)
 
 # Image for analysis
 factory_image = "factory_image1.jpg"
 
 # Initialize agents with respective prompts
+# @phoenix_trace_decorator("This function is an agent and is traced by Phoenix.")
 health_security_agent = Agent(
     llm=llm,
     sop=Health_Security_Agent_Prompt,
-    max_loops=3,
+    max_loops=1,
     multi_modal=True,
 )
+
+#@phoenix_trace_decorator("This function is an agent and is traced by Phoenix.")
 quality_control_agent = Agent(
     llm=llm,
     sop=Quality_Control_Agent_Prompt,
-    max_loops=3,
+    max_loops=1,
     multi_modal=True,
 )
+
+#@phoenix_trace_decorator("This function is an agent and is traced by Phoenix.")
 productivity_agent = Agent(
     llm=llm,
     sop=Productivity_Agent_Prompt,
-    max_loops=3,
+    max_loops=1,
     multi_modal=True,
 )
+
+#@phoenix_trace_decorator("This function is an agent and is traced by Phoenix.")
 safety_agent = Agent(
-    llm=llm, sop=Safety_Agent_Prompt, max_loops=3, multi_modal=True
+    llm=llm, sop=Safety_Agent_Prompt, max_loops=1, multi_modal=True
 )
+
+#@phoenix_trace_decorator("This function is an agent and is traced by Phoenix.")
 security_agent = Agent(
-    llm=llm, sop=Security_Agent_Prompt, max_loops=3, multi_modal=True
+    llm=llm, sop=Security_Agent_Prompt, max_loops=1, multi_modal=True
 )
+
+#@phoenix_trace_decorator("This function is an agent and is traced by Phoenix.")
 sustainability_agent = Agent(
     llm=llm,
     sop=Sustainability_Agent_Prompt,
-    max_loops=3,
+    max_loops=1,
     multi_modal=True,
 )
+
+#@phoenix_trace_decorator("This function is an agent and is traced by Phoenix.")
 efficiency_agent = Agent(
     llm=llm,
     sop=Efficiency_Agent_Prompt,
-    max_loops=3,
+    max_loops=1,
     multi_modal=True,
 )
 

playground/demos/optimize_llm_stack/vortex.py

@@ -5,9 +5,8 @@ from dotenv import load_dotenv
 
 from swarms.models import OpenAIChat
 from swarms.structs import Agent
-from swarms.utils.phoenix_handler import phoenix_trace_decorator
+# from swarms.utils.phoenix_handler import phoenix_trace_decorator
-
+# import modal
-import modal
 
 load_dotenv()
 
@@ -15,22 +14,23 @@ load_dotenv()
 llm = OpenAIChat(
     openai_api_key=os.getenv("OPENAI_API_KEY"),
     model_name="gpt-4",
-    max_tokens=4000,
+    max_tokens=1000,
 )
 
 # Modal
-stub = modal.Stub(name="swarms")
+# stub = modal.Stub(name="swarms")
 
 
 # Agent
-@phoenix_trace_decorator(
+# @phoenix_trace_decorator(
-    "This function is an agent and is traced by Phoenix."
+#     "This function is an agent and is traced by Phoenix."
+# )
+# @stub.function(gpu="any")
+agent = Agent(
+    llm=llm,
+    max_loops=2,
+    autosave=True,
+    dashboard=True,
 )
-@stub.function(gpu="any")
+out = agent.run("Generate a 5,000 word blog on how swarms of autonomous agents can be used to solve the world's problems.")
-def agent(task: str):
+print(out)
-    agent = Agent(
-        llm=llm,
-        max_loops=1,
-    )
-    out = agent.run(task=task)
-    return out

playground/demos/swarm_of_mma_manufacturing/main.py

@@ -20,6 +20,7 @@ from termcolor import colored
 
 from swarms.models import GPT4VisionAPI
 from swarms.structs import Agent
+from swarms.utils.phoenix_handler import phoenix_trace_decorator
 
 load_dotenv()
 api_key = os.getenv("OPENAI_API_KEY")

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "swarms"
-version = "2.6.7"
+version = "2.7.0"
 description = "Swarms - Pytorch"
 license = "MIT"
 authors = ["Kye Gomez <kye@apac.ai>"]
@@ -33,6 +33,7 @@ einops = "*"
 google-generativeai = "*"
 langchain-experimental = "*"
 playwright = "*"
+weaviate-client = "*"
 duckduckgo-search = "*"
 opencv-python-headless = "*"
 faiss-cpu = "*"
@@ -42,9 +43,11 @@ datasets = "*"
 optimum = "*"
 diffusers = "*"
 PyPDF2 = "*"
+vllm = "*"
 accelerate = "*"
 sentencepiece = "*"
 wget = "*"
+arize-phoenix = "*"
 tensorflow = "*"
 httpx = "*"
 tiktoken = "*"
@@ -94,8 +97,3 @@ target-version = ['py38']
 preview = true
 
 
-[tool.poetry.scripts]
-swarms = "swarms.cli.run_file:run_file"
-
-
-

requirements.txt

@@ -19,11 +19,14 @@ attrs
 datasets
 pydantic==1.10.12
 soundfile
+arize-phoenix
+weaviate-client 
 huggingface-hub
 google-generativeai
 sentencepiece
 PyPDF2
 accelerate
+vllm
 chromadb
 tensorflow
 optimum

swarms/models/__init__.py

@@ -8,11 +8,7 @@ from swarms.models.openai_models import (
     AzureOpenAI,
     OpenAIChat,
 )  # noqa: E402
-
+from swarms.models.vllm import vLLM  # noqa: E402
-# try:
-#     from swarms.models.vllm import vLLM  # noqa: E402
-# except ImportError:
-#     pass
 
 # from swarms.models.zephyr import Zephyr  # noqa: E402
 from swarms.models.biogpt import BioGPT  # noqa: E402
@@ -64,5 +60,5 @@ __all__ = [
     # "Dalle3",
     # "DistilWhisperModel",
     "GPT4VisionAPI",
-    # "vLLM",
+    "vLLM",
 ]

swarms/structs/agent.py

@@ -583,7 +583,10 @@ class Agent:
         return agent_system_prompt_2(self.agent_name)
 
     def run(
-        self, task: Optional[str], img: Optional[str] = None, **kwargs
+        self, 
+        task: Optional[str] = None, 
+        img: Optional[str] = None, 
+        **kwargs
     ):
         """
         Run the autonomous agent loop
@@ -639,9 +642,9 @@ class Agent:
                     AGENT_SYSTEM_PROMPT_3, response
                 )
 
-                # Retreiving long term memory
+                # # Retreiving long term memory
-                if self.memory:
+                # if self.memory:
-                    task = self.agent_memory_prompt(response, task)
+                #     task = self.agent_memory_prompt(response, task)
 
                 attempt = 0
                 while attempt < self.retry_attempts:
@@ -652,11 +655,13 @@ class Agent:
                                 img,
                                 **kwargs,
                             )
+                            print(response)
                         else:
                             response = self.llm(
                                 task,
                                 **kwargs,
                             )
+                            print(response)
 
                         # If code interpreter is enabled then run the code
                         if self.code_interpreter:

swarms/utils/__init__.py

@@ -1,14 +1,10 @@
-from swarms.utils.markdown_message import display_markdown_message
 from swarms.utils.code_interpreter import SubprocessCodeInterpreter
+from swarms.utils.markdown_message import display_markdown_message
 from swarms.utils.parse_code import (
     extract_code_in_backticks_in_string,
 )
 from swarms.utils.pdf_to_text import pdf_to_text
-
+from swarms.utils.phoenix_handler import phoenix_trace_decorator
-try:
-    from swarms.utils.phoenix_handler import phoenix_trace_decorator
-except ImportError:
-    pass
 
 __all__ = [
     "display_markdown_message",

swarms/utils/phoenix_handler.py

@@ -1,8 +1,5 @@
-import subprocess
-import sys
-import traceback
 import functools
-
+import traceback
 import phoenix as px