Merge c0d9979858 into 76a140508f

.env.example

@@ -1,4 +1,5 @@
 OPENAI_API_KEY=""
+OPENAI_ORG_ID=""
 GOOGLE_API_KEY=""
 ANTHROPIC_API_KEY=""
 AI21_API_KEY="your_api_key_here"

.github/workflows/python-app.yml

@@ -26,7 +26,7 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install flake8 pytest swarms
+        pip install flake8 pytest swarms torchfix
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
     - name: Lint with flake8
       run: |

.github/workflows/python-package.yml

@@ -28,7 +28,7 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         python -m pip install --upgrade swarms
-        python -m pip install flake8 pytest swarms
+        python -m pip install flake8 pytest swarms torchfix
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
     - name: Lint with flake8
       run: |

playground/agents/multi_modal_auto_agent_example.py

@@ -9,10 +9,12 @@ load_dotenv()
 
 # Get the API key from the environment
 api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize the language model
 llm = GPT4VisionAPI(
     openai_api_key=api_key,
+    openai_org_id=org_id,
     max_tokens=500,
 )
 

playground/agents/simple_agent_example.py

@@ -21,9 +21,10 @@ load_dotenv()
 
 # Get the API key from the environment
 api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize the language model
-llm = OpenAIChat(openai_api_key=api_key)
+llm = OpenAIChat(openai_api_key=api_key, openai_org_id=org_id, max_tokens=500,)
 
 
 # Run the language model in a loop

playground/agents/worker_example.py

@@ -9,6 +9,7 @@ load_dotenv()
 
 # Retrieving the OpenAI API key from environment variables
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Creating a Worker instance
 worker = Worker(
@@ -17,7 +18,7 @@ worker = Worker(
     human_in_the_loop=False,
     tools=[],
     temperature=0.5,
-    llm=OpenAIChat(openai_api_key=api_key),
+    llm=OpenAIChat(openai_api_key=api_key, openai_org_id=org_id, max_tokens=500,),
     verbose=True,
 )
 

playground/demos/accountant_team/account_team2_example.py

@@ -13,11 +13,13 @@ from swarms.utils.pdf_to_text import pdf_to_text
 load_dotenv()
 anthropic_api_key = os.getenv("ANTHROPIC_API_KEY")
 openai_api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 
 # Base llms
 llm1 = OpenAIChat(
     openai_api_key=openai_api_key,
+    openai_org_id=org_id,
     max_tokens=5000,
 )
 

playground/demos/ad_gen/ad_gen_example.py

@@ -7,11 +7,12 @@ from swarms.models.stable_diffusion import StableDiffusion
 
 load_dotenv()
 openai_api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 stability_api_key = os.getenv("STABILITY_API_KEY")
 
 # Initialize the language model and image generation model
 llm = OpenAIChat(
-    openai_api_key=openai_api_key, temperature=0.5, max_tokens=3000
+    openai_api_key=openai_api_key, openai_org_id=org_id, temperature=0.5, max_tokens=3000
 )
 sd_api = StableDiffusion(api_key=stability_api_key)
 
@@ -41,7 +42,7 @@ class ProductAdConceptGenerator:
             "serene",
             "lasers,lightning",
         ]
-        self.contexts = [
+        self.style = [
             "in an everyday setting",
             "in a rave setting",
             "in an abstract environment",
@@ -62,10 +63,21 @@ class ProductAdConceptGenerator:
         self.contexts = [
             "high realism product ad (extremely creative)"
         ]
+        self.social_media_platforms = [
+            "Facebook",
+            "Instagram",
+            "Twitter",
+            "LinkedIn",
+            "Snapchat",
+            "TikTok",
+            "Pinterest",
+            "YouTube",
+        ]
 
     def generate_concept(self):
         theme = random.choice(self.themes)
         context = random.choice(self.contexts)
+        style = random.choice(self.style)
         return (
             f"{theme} inside a {style} {self.product_name}, {context}"
         )
@@ -93,8 +105,7 @@ ad_copy_prompt = (
 ad_copy = ad_copy_agent.run(task=ad_copy_prompt)
 
 # Output the results
-print("Creative Concept:", concept_result)
+print("Creative Concept:", concept_concept)
-print("Design Ideas:", design_result)
 print("Ad Copy:", copywriting_result)
 print(
     "Image Path:",

playground/demos/ai_research_team/main_example.py

@@ -15,6 +15,7 @@ from swarms.utils.pdf_to_text import pdf_to_text
 load_dotenv()
 anthropic_api_key = os.getenv("ANTHROPIC_API_KEY")
 openai_api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 PDF_PATH = "fasterffn.pdf"
 
@@ -22,6 +23,7 @@ PDF_PATH = "fasterffn.pdf"
 # Base llms
 llm1 = OpenAIChat(
     openai_api_key=openai_api_key,
+    openai_org_id=org_id,
 )
 
 llm2 = Anthropic(

playground/demos/autotemp/autotemp_example.py

@@ -11,12 +11,14 @@ class AutoTemp:
     def __init__(
         self,
         api_key,
+        org_id,
         default_temp=0.0,
         alt_temps=None,
         auto_select=True,
         max_workers=6,
     ):
         self.api_key = api_key
+        self.org_id = org_id
         self.default_temp = default_temp
         self.alt_temps = (
             alt_temps if alt_temps else [0.4, 0.6, 0.8, 1.0, 1.2, 1.4]
@@ -24,7 +26,7 @@ class AutoTemp:
         self.auto_select = auto_select
         self.max_workers = max_workers
         self.llm = OpenAIChat(
-            openai_api_key=self.api_key, temperature=self.default_temp
+            openai_api_key=self.api_key, openai_org_id=org_id, temperature=self.default_temp
         )
 
     def evaluate_output(self, output, temperature):

playground/demos/autotemp/blog_gen_example.py

@@ -9,11 +9,14 @@ class BlogGen:
     def __init__(
         self,
         api_key,
+        org_id,
         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
+            openai_api_key=api_key, 
+            openai_org_id=org_id,
+            temperature=0.8
         )
         self.auto_temp = AutoTemp(api_key)
         self.temperature_range = temperature_range
@@ -134,5 +137,6 @@ class BlogGen:
 
 if __name__ == "__main__":
     api_key = os.environ["OPENAI_API_KEY"]
+    org_id = os.environ["OPENAI_ORG_ID"]
     blog_generator = BlogGen(api_key)
     blog_generator.run_workflow()

playground/demos/developer_swarm/main_example.py

@@ -24,6 +24,7 @@ from swarms.structs import Agent
 
 load_dotenv()
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 
 TASK = """
@@ -32,7 +33,9 @@ CODE
 """
 
 # Initialize the language model
-llm = OpenAIChat(openai_api_key=api_key, max_tokens=5000)
+llm = OpenAIChat(openai_api_key=api_key,
+    openai_org_id=org_id,
+    max_tokens=5000)
 
 
 # Documentation agent

playground/demos/education/education_example.py

@@ -7,11 +7,15 @@ import swarms.prompts.education as edu_prompts
 # Load environment variables
 load_dotenv()
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
 stability_api_key = os.getenv("STABILITY_API_KEY")
 
 # Initialize language model
 llm = OpenAIChat(
-    openai_api_key=api_key, temperature=0.5, max_tokens=3000
+    openai_api_key=api_key, 
+    openai_org_id=org_id,
+    temperature=0.5, 
+    max_tokens=3000
 )
 
 # User preferences (can be dynamically set in a real application)

playground/demos/grupa/app_example.py

@@ -43,11 +43,13 @@ export default MainPanel;
 
 # Load the environment variables
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize the language agent
 llm = OpenAIChat(
     model_name="gpt-4",
     openai_api_key=api_key,
+    openai_org_id=org_id,
     temperature=0.5,
     max_tokens=4000,
 )

playground/demos/langchain_example/langchain_example.py

@@ -9,6 +9,7 @@ load_dotenv()
 # Initialize the model
 llm = OpenAIChat(
     openai_api_key=os.getenv("OPENAI_API_KEY"),
+    openai_org_id=os.getenv("OPENAI_ORG_ID"),
     max_tokens=1000,
 )
 

playground/demos/llm_with_conversation/main_example.py

@@ -10,11 +10,13 @@ load_dotenv()
 
 # Get the API key from the environment
 api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize the language model
 llm = OpenAIChat(
     temperature=0.5,
     model_name="gpt-4",
     openai_api_key=api_key,
+    openai_org_id=org_id,
     max_tokens=1000,
 )

playground/demos/logistics/logistics_example.py

@@ -16,10 +16,11 @@ from swarms.prompts.logistics import (
 
 load_dotenv()
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # GPT4VisionAPI or llama
 # @banana #- deploy to banana
-llm = GPT4VisionAPI(openai_api_key=api_key)
+llm = GPT4VisionAPI(openai_api_key=api_key, openai_org_id=org_id)
 
 # Image for analysis
 factory_image = "factory_image1.jpg"

playground/demos/multi_modal_chain_of_thought/vcot_example.py

@@ -11,10 +11,12 @@ load_dotenv()
 
 # Get the API key from the environment
 api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize the language model
 llm = GPT4VisionAPI(
     openai_api_key=api_key,
+    openai_org_id=org_id,
     max_tokens=500,
 )
 

playground/demos/multimodal_tot/idea2img_example.py

@@ -12,12 +12,13 @@ from swarms.structs import Agent
 # Load environment variables
 load_dotenv()
 openai_api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 stability_api_key = os.getenv("STABLE_API_KEY")
 
 # Initialize the models
-vision_api = GPT4VisionAPI(api_key=openai_api_key)
+vision_api = GPT4VisionAPI(api_key=openai_api_key, org_id=org_id)
 sd_api = StableDiffusion(api_key=stability_api_key)
-gpt_api = OpenAIChat(openai_api_key=openai_api_key)
+gpt_api = OpenAIChat(openai_api_key=openai_api_key, org_id=org_id)
 
 
 class Idea2Image(Agent):

playground/demos/multimodal_tot/main_example.py

@@ -26,12 +26,14 @@ load_dotenv()
 
 # Get the API key from the environment
 api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 stable_api_key = os.environ.get("STABLE_API_KEY")
 
 
 # Initialize the language model
 llm = GPT4VisionAPI(
     openai_api_key=api_key,
+    openai_org_id=org_id,
     max_tokens=500,
 )
 

playground/demos/nutrition/nutrition_example.py

@@ -8,6 +8,7 @@ from swarms.structs import Agent
 # Load environment variables
 load_dotenv()
 openai_api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Define prompts for various tasks
 MEAL_PLAN_PROMPT = (
@@ -33,6 +34,7 @@ def encode_image(image_path):
 # Initialize Language Model (LLM)
 llm = OpenAIChat(
     openai_api_key=openai_api_key,
+    openai_org_id=org_id,
     max_tokens=3000,
 )
 
@@ -43,6 +45,7 @@ def create_vision_agent(image_path):
     headers = {
         "Content-Type": "application/json",
         "Authorization": f"Bearer {openai_api_key}",
+        "OpenAI-Organization": f"{openai_org_id}"
     }
     payload = {
         "model": "gpt-4-vision-preview",

playground/demos/optimize_llm_stack/vortex_example.py

@@ -12,6 +12,7 @@ load_dotenv()
 # Model
 llm = OpenAIChat(
     openai_api_key=os.getenv("OPENAI_API_KEY"),
+    openai_org_id=os.getenv("OPENAI_ORG_ID"),
     model_name="gpt-4",
     max_tokens=1000,
 )

playground/demos/optimize_llm_stack/weaviate_example.py

@@ -8,7 +8,7 @@ weaviate_client = WeaviateDB(
     grpc_port="YOUR_gRPC_PORT",
     grpc_secure=True,
     auth_client_secret="YOUR_APIKEY",
-    additional_headers={"X-OpenAI-Api-Key": "YOUR_OPENAI_APIKEY"},
+    additional_headers={"X-OpenAI-Api-Key": "YOUR_OPENAI_APIKEY","OpenAI-Organization": "YOUR_OPENAI_ORG_ID"},
     additional_config=None,  # You can pass additional configuration here
 )
 

playground/demos/personal_assistant/better_communication_example.py

@@ -13,10 +13,12 @@ load_dotenv()
 
 # Get the API key from the environment
 openai_api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize the language model
 llm = OpenAIChat(
     openai_api_key=openai_api_key,
+    openai_org_id=org_id,
 )
 
 # Initialize the text-to-speech model
@@ -24,6 +26,7 @@ tts = OpenAITTS(
     model_name="tts-1-1106",
     voice="onyx",
     openai_api_key=openai_api_key,
+    openai_org_id=org_id,
     saved_filepath="runs/tts_speech.wav",
 )
 

playground/demos/personal_stylist/personal_stylist_example.py

@@ -13,9 +13,10 @@ from swarms.prompts.personal_stylist import (
 # Load environment variables
 load_dotenv()
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize GPT4VisionAPI
-llm = GPT4VisionAPI(openai_api_key=api_key)
+llm = GPT4VisionAPI(openai_api_key=api_key, openai_org_id=org_id)
 
 # User selfie and clothes images
 user_selfie = "user_image.jpg"

playground/demos/positive_med/positive_med_example.py

@@ -33,7 +33,9 @@ from swarms.prompts.autobloggen import (
 )
 
 api_key = os.environ["OPENAI_API_KEY"]
-llm = OpenAIChat(openai_api_key=api_key)
+org_id = os.environ["OPENAI_ORG_ID"]
+llm = OpenAIChat(openai_api_key=api_key, openai_org_id=org_id)
+
 
 
 def get_review_prompt(article):

playground/demos/security_team/security_team_example.py

@@ -7,8 +7,9 @@ import swarms.prompts.security_team as stsp
 # Load environment variables and initialize the Vision API
 load_dotenv()
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
-llm = GPT4VisionAPI(openai_api_key=api_key)
+llm = GPT4VisionAPI(openai_api_key=api_key, openai_org_id=org_id)
 
 # Image for analysis
 img = "bank_robbery.jpg"

playground/demos/swarm_of_mma_manufacturing/main_example.py

@@ -23,9 +23,12 @@ from swarms.structs import Agent
 
 load_dotenv()
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # GPT4VisionAPI
-llm = GPT4VisionAPI(openai_api_key=api_key, max_tokens=2000)
+llm = GPT4VisionAPI(openai_api_key=api_key,
+    openai_org_id=org_id,
+    max_tokens=2000)
 
 assembly_line = (
     "playground/demos/swarm_of_mma_manufacturing/assembly_line.jpg"

playground/demos/urban_planning/urban_planning_example.py

@@ -7,15 +7,19 @@ import swarms.prompts.urban_planning as upp
 # Load environment variables
 load_dotenv()
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 stability_api_key = os.getenv("STABILITY_API_KEY")
 
 # Initialize language model
 llm = OpenAIChat(
-    openai_api_key=api_key, temperature=0.5, max_tokens=3000
+    openai_api_key=api_key, 
+    openai_org_id=org_id,
+    temperature=0.5, 
+    max_tokens=3000
 )
 
 # Initialize Vision model
-vision_api = GPT4VisionAPI(api_key=api_key)
+vision_api = GPT4VisionAPI(api_key=api_key, org_id=org_id)
 
 # Initialize agents for urban planning tasks
 architecture_analysis_agent = Agent(

playground/demos/visuo/text_to_sql_agent_example.py

@@ -10,6 +10,7 @@ load_dotenv()
 
 # Get the API key from the environment
 api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize the language model
 llm = HuggingfaceLLM(

playground/demos/xray/xray_example.py

@@ -12,15 +12,18 @@ from swarms.structs.agent import Agent
 # Load environment variables
 load_dotenv()
 openai_api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Function to analyze an X-ray image
 multimodal_llm = GPT4VisionAPI(
     openai_api_key=openai_api_key,
+    openai_org_id=org_id,
 )
 
 # Initialize Language Model (LLM)
 llm = OpenAIChat(
     openai_api_key=openai_api_key,
+    openai_org_id=org_id,
     max_tokens=3000,
 )
 

playground/diy/hierchical_example.py

@@ -3,6 +3,7 @@ from swarms import HierarchicalSwarm
 
 swarm = HierarchicalSwarm(
     openai_api_key="key",
+    openai_org_id="org_id",
     model_type="openai",
     model_id="gpt-4",
     use_vectorstore=False,

playground/models/bingchat_example.py

@@ -5,6 +5,7 @@ from swarms.models import OpenAIChat
 import os
 
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize the EdgeGPTModel
 edgegpt = BingChat(cookies_path="./cookies.txt")
@@ -20,6 +21,7 @@ def edgegpt(task: str = None):
 # This model can be swapped out with Anthropic, ETC, Huggingface Models like Mistral, ETC
 llm = OpenAIChat(
     openai_api_key=api_key,
+    openai_org_id=org_id,
     temperature=0.5,
 )
 

playground/models/dall3_example.py

@@ -1,6 +1,6 @@
 from swarms.models import Dalle3
 
-dalle3 = Dalle3(openai_api_key="")
+dalle3 = Dalle3(openai_api_key="", openai_org_id="")
 task = "A painting of a dog"
 image_url = dalle3(task)
 print(image_url)

playground/models/dalle3_concurrent_example.py

@@ -8,8 +8,9 @@ from swarms.models.dalle3 import Dalle3
 import os
 
 api_key = os.environ["OPENAI_API_KEY"]
+org_id = os.environ["OPENAI_ORG_ID"]
 
-dalle3 = Dalle3(openai_api_key=api_key, n=1)
+dalle3 = Dalle3(openai_api_key=api_key, openai_org_id=org_id, n=1)
 
 # task = "Swarm of robots working super industrial ambience concept art"
 

playground/models/gpt4_v_example.py

@@ -1,7 +1,7 @@
 from swarms.models.gpt4v import GPT4Vision
 
 
-gpt4vision = GPT4Vision(openai_api_key="")
+gpt4vision = GPT4Vision(openai_api_key="" , openai_org_id="")
 
 img = "https://upload.wikimedia.org/wikipedia/commons/thumb/0/0d/VFPt_Solenoid_correct2.svg/640px-VFPt_Solenoid_correct2.svg.png"
 

playground/models/openai_example.py

@@ -1,6 +1,6 @@
 from swarms.models.openai_chat import OpenAIChat
 
-model = OpenAIChat()
+model = OpenAIChat(openai_api_key="", openai_org_id="")
 
 out = model("Hello, how are you?")
 

playground/models/openai_model_example.py

@@ -1,6 +1,7 @@
 from swarms.models.openai_models import OpenAIChat
 
-openai = OpenAIChat(openai_api_key="", verbose=False)
+openai = OpenAIChat(openai_api_key="", openai_org_id="", verbose=False)
+
 
 chat = openai("What are quantum fields?")
 print(chat)

playground/models/tts_speech_example.py

@@ -8,6 +8,7 @@ tts = OpenAITTS(
     model_name="tts-1-1106",
     voice="onyx",
     openai_api_key=os.getenv("OPENAI_API_KEY"),
+    openai_org_id=os.getenv("OPENAI_ORG_ID"),
 )
 
 out = tts.run_and_save("Dammmmmm those tacos were good")

playground/structs/agent_with_longterm.py

@@ -10,6 +10,7 @@ load_dotenv()
 
 # Get the API key from the environment
 api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 
 # Initilaize the chromadb client
@@ -23,6 +24,7 @@ llm = OpenAIChat(
     temperature=0.5,
     model_name="gpt-4",
     openai_api_key=api_key,
+    openai_org_id=org_id,
     max_tokens=1000,
 )
 

playground/structs/agent_with_tools_example.py

@@ -58,11 +58,13 @@ def rapid_api(query: str):
 
 # Get the API key from the environment
 api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize the language model
 llm = OpenAIChat(
     temperature=0.5,
     openai_api_key=api_key,
+    openai_org_id=org_id,
 )
 
 

playground/structs/autoscaler_example.py

@@ -13,11 +13,13 @@ load_dotenv()
 
 # Get the API key from the environment
 api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize the language model
 llm = OpenAIChat(
     temperature=0.5,
     openai_api_key=api_key,
+    openai_org_id=org_id,
 )
 
 

playground/structs/company_example.py

@@ -10,7 +10,9 @@ from swarms.structs.company import Company
 load_dotenv()
 
 llm = OpenAIChat(
-    openai_api_key=os.getenv("OPENAI_API_KEY"), max_tokens=4000
+    openai_api_key=os.getenv("OPENAI_API_KEY"), 
+    openai_org_id=os.getenv("OPENAI_ORG_ID"),
+    max_tokens=4000
 )
 
 ceo = Agent(llm=llm, ai_name="CEO")

playground/structs/concurrent_workflow_example.py

@@ -6,7 +6,8 @@ from swarms import OpenAIChat, Task, ConcurrentWorkflow, Agent
 load_dotenv()
 
 # Load environment variables
-llm = OpenAIChat(openai_api_key=os.getenv("OPENAI_API_KEY"))
+llm = OpenAIChat(openai_api_key=os.getenv("OPENAI_API_KEY"),
+                 openai_org_id=os.getenv("OPENAI_ORG_ID"))
 agent = Agent(llm=llm, max_loops=1)
 
 # Create a workflow

playground/structs/dialogue_simulator_example.py

@@ -1,9 +1,16 @@
 from swarms.swarms import DialogueSimulator
 from swarms.workers.worker import Worker
 from swarms.models import OpenAIChat
+import os
+
+api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 llm = OpenAIChat(
-    model_name="gpt-4", openai_api_key="api-key", temperature=0.5
+    model_name="gpt-4", 
+    openai_api_key=api_key, 
+    openai_org_id=org_id,
+    temperature=0.5
 )
 
 worker1 = Worker(

playground/structs/flow_example.py

@@ -1,12 +1,16 @@
 from swarms.models import OpenAIChat
 from swarms.structs import Agent
 
-api_key = ""
+import os
+
+api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize the language model, this model can be swapped out with Anthropic, ETC, Huggingface Models like Mistral, ETC
 llm = OpenAIChat(
     # model_name="gpt-4"
     openai_api_key=api_key,
+    openai_org_id=org_id,
     temperature=0.5,
     # max_tokens=100,
 )

playground/structs/godmode_example.py

@@ -10,10 +10,11 @@ load_dotenv()
 # API Keys
 anthropic_api_key = os.getenv("ANTHROPIC_API_KEY")
 openai_api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 gemini_api_key = os.getenv("GEMINI_API_KEY")
 
 # Initialize the models
-llm = OpenAIChat(openai_api_key=openai_api_key)
+llm = OpenAIChat(openai_api_key=openai_api_key, openai_org_id=org_id)
 anthropic = Anthropic(anthropic_api_key=anthropic_api_key)
 mixtral = Mixtral()
 gemini = Gemini(gemini_api_key=gemini_api_key)

playground/structs/groupchat_example.py

@@ -2,10 +2,12 @@ from swarms import OpenAI, Agent
 from swarms.structs.groupchat import GroupChatManager, GroupChat
 
 
-api_key = ""
+api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 llm = OpenAI(
     openai_api_key=api_key,
+    openai_org_id=org_id,
     temperature=0.5,
     max_tokens=3000,
 )

playground/structs/gui_app_example.py

@@ -5,7 +5,7 @@ from swarms import HierarchicalSwarm
 api_key = "sksdsds"
 
 # Initialize HierarchicalSwarm with your API key
-swarm = HierarchicalSwarm(openai_api_key=api_key)
+swarm = HierarchicalSwarm(openai_api_key=api_key, openai_org_id="org-id")
 
 # Define an objective
 objective = """

playground/structs/majority_voting.py

@@ -1,7 +1,9 @@
 from swarms import Agent, OpenAIChat, MajorityVoting
 
+api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
 # Initialize the llm
-llm = OpenAIChat()
+llm = OpenAIChat(openai_api_key=api_key, openai_org_id=org_id, max_tokens=150)
 
 # Initialize the agents
 agent1 = Agent(llm=llm, max_loops=1)

playground/structs/multi_agent_debate_example.py

@@ -5,7 +5,11 @@ from swarms.swarms.multi_agent_debate import (
 from swarms.workers.worker import Worker
 from swarms.models import OpenAIChat
 
-llm = OpenAIChat()
+api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
+
+
+llm = OpenAIChat(openai_api_key=api_key, openai_org_id=org_id)
 
 worker1 = Worker(
     llm=llm,

playground/structs/multi_modal_rag_agent.py

@@ -12,9 +12,11 @@ load_dotenv()
 # Getting the Gemini API key from environment variables
 gemini_api_key = os.getenv("GEMINI_API_KEY")
 openai_api_key = os.getenv("OPENAI_API_KEY")
+openai_org_id = os.getenv("OPENAI_ORG_ID")
 
 llm = OpenAIChat(
     openai_api_key=openai_api_key,
+    openai_org_id=openai_org_id,
     max_tokens=1000,
     temperature=0.2,
 )

playground/structs/orchestrate_example.py

@@ -1,7 +1,11 @@
 from swarms import Worker, Orchestrator
 
+api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
+
 node = Worker(
-    openai_api_key="",
+    openai_api_key=api_key,
+    openai_org_id=org_id,
     ai_name="Optimus Prime",
 )
 

playground/structs/orchestrator_example.py

@@ -1,7 +1,11 @@
 from swarms import Worker, Orchestrator
 
+api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
+
 node = Worker(
-    openai_api_key="",
+    openai_api_key=api_key,
+    openai_org_id=org_id,
     ai_name="Optimus Prime",
 )
 

playground/structs/recursive_example.py

@@ -6,7 +6,7 @@ from swarms import OpenAIChat, Task, RecursiveWorkflow, Agent
 load_dotenv()
 
 # Load environment variables
-llm = OpenAIChat(openai_api_key=os.getenv("OPENAI_API_KEY"))
+llm = OpenAIChat(openai_api_key=os.getenv("OPENAI_API_KEY"), openai_org_id=os.getenv("OPENAI_ORG_ID"))
 agent = Agent(llm=llm, max_loops=1)
 
 # Create a workflow

playground/structs/sequential_workflow_example.py

@@ -1,7 +1,12 @@
 from swarms import OpenAIChat, Agent, Task, SequentialWorkflow
 
+api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
+
 # Example usage
 llm = OpenAIChat(
+    openai_api_key=api_key,
+    openai_org_id=org_id,
     temperature=0.5,
     max_tokens=3000,
 )

playground/structs/social_app_example.py

@@ -1,10 +1,11 @@
 from ..swarms import HierarchicalSwarm
 
 # Retrieve your API key from the environment or replace with your actual key
-api_key = "sksdsds"
+api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
 
 # Initialize HierarchicalSwarm with your API key
-swarm = HierarchicalSwarm(openai_api_key=api_key)
+swarm = HierarchicalSwarm(openai_api_key=api_key, openai_org_id=org_id, max_loops=1)
 
 # Define an objective
 objective = """

playground/structs/swarm_network_example.py

@@ -10,11 +10,13 @@ load_dotenv()
 
 # Get the API key from the environment
 api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
 # Initialize the language model
 llm = OpenAIChat(
     temperature=0.5,
     openai_api_key=api_key,
+    openai_org_id=org_id,
 )
 
 ## Initialize the workflow

playground/structs/task_example.py

@@ -22,6 +22,7 @@ def my_condition():
 # Create an agent
 agent = Agent(
     llm=OpenAIChat(openai_api_key=os.environ["OPENAI_API_KEY"]),
+    openai_org_id=os.environ["OPENAI_ORG_ID"],
     max_loops=1,
     dashboard=False,
 )

playground/structs/todo_app_example.py

@@ -2,10 +2,11 @@ from swarms import HierarchicalSwarm
 
 
 # Retrieve your API key from the environment or replace with your actual key
-api_key = "sksdsds"
+api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
 
 # Initialize HierarchicalSwarm with your API key
-swarm = HierarchicalSwarm(openai_api_key=api_key)
+swarm = HierarchicalSwarm(openai_api_key=api_key, openai_org_id=org_id, max_loops=1)
 
 # Define an objective
 objective = """

playground/structs/workflow_example.py

@@ -1,8 +1,11 @@
 from swarms.structs.workflow import Workflow
 from swarms.models import OpenAIChat
+import os
 
+api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
 
-llm = OpenAIChat()
+llm = OpenAIChat(openai_api_key=api_key, openai_org_id=org_id)
 
 
 workflow = Workflow(llm)

playground/tools/agent_with_tools_example.py

@@ -6,9 +6,9 @@ from dotenv import load_dotenv
 load_dotenv()
 
 api_key = os.environ.get("OPENAI_API_KEY")
+org_id = os.environ.get("OPENAI_ORG_ID")
 
-
+llm = OpenAIChat(openai_api_key=api_key, openai_org_id=org_id)
-llm = OpenAIChat(api_key=api_key)
 
 # @tool
 # def search_api(query: str) -> str:

pyproject.toml

@@ -23,9 +23,9 @@ classifiers = [
 
 
 [tool.poetry.dependencies]
-python = "^3.6.1"
+python = ">=3.9,<4.0.0"
 torch = "2.1.1"
-transformers = "4.37.1"
+transformers = "4.37.2"
 openai = "0.28.0"
 langchain = "0.0.333"
 asyncio = "3.4.3"
@@ -45,7 +45,7 @@ PyPDF2 = "3.0.1"
 accelerate = "*"
 anthropic = "*"
 sentencepiece = "0.1.98"
-httpx = "0.24.1"
+httpx = "0.25.0"
 tiktoken = "0.4.0"
 attrs = "22.2.0"
 ratelimit = "2.2.1"
@@ -54,7 +54,7 @@ huggingface-hub = "*"
 pydantic = "1.10.12"
 tenacity = "8.2.2"
 Pillow = "9.4.0"
-chromadb = "*"
+chromadb = "0.4.14"
 termcolor = "2.2.0"
 black = "23.3.0"
 soundfile = "0.12.1"
@@ -72,8 +72,11 @@ timm = "*"
 supervision = "*"
 scikit-image = "*"
 pinecone-client = "*"
-roboflow = "*"
+roboflow = "1.1.4"
+python-dotenv = "0.19.1"
 
+[tool.poetry.extras]
+playground = ["streamlit", "requests", "pygame", "speechrecognition", "playsound", "numpy"]
 
 
 [tool.poetry.group.lint.dependencies]
@@ -96,6 +99,10 @@ aggressive = 3
 [tool.ruff]
 line-length = 70
 
+[tool.flake8]
+line-length = 70
+ignore = "E501,W6"  # or ["E501", "W6"]
+
 [tool.black]
 line-length = 70
 target-version = ['py38']
@@ -104,3 +111,5 @@ preview = true
 
 [tool.poetry.scripts]
 swarms = 'swarms.cli._cli:main'
+
+

requirements.txt

@@ -1,6 +1,5 @@
 torch==2.1.1
-transformers
+transformers==4.37.2
-pandas==1.5.3
 langchain==0.0.333
 langchain-experimental==0.0.10
 httpx==0.24.1
@@ -30,7 +29,6 @@ diffusers
 einops==0.7.0
 opencv-python-headless==4.8.1.78
 numpy
-openai==0.28.0
 opencv-python==4.7.0.72
 timm
 yapf

scripts/auto_docs.py

@@ -26,9 +26,11 @@ from swarms.tokenizers.cohere_tokenizer import CohereTokenizer
 load_dotenv()
 
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
 
 model = OpenAIChat(
     openai_api_key=api_key,
+    openai_org_id=org_id,
     max_tokens=4000,
 )
 

scripts/auto_tests_docs/auto_docs_functions.py

@@ -11,10 +11,12 @@ from swarms import OpenAIChat
 load_dotenv()
 
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
 
 model = OpenAIChat(
     model_name="gpt-4",
     openai_api_key=api_key,
+    openai_org_id=org_id,
     max_tokens=4000,
 )
 

scripts/auto_tests_docs/auto_docs_omni.py

@@ -15,10 +15,12 @@ from swarms import OpenAIChat
 load_dotenv()
 
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
 
 model = OpenAIChat(
     model_name="gpt-4-1106-preview",
     openai_api_key=api_key,
+    openai_org_id=org_id,
     max_tokens=4000,
 )
 

scripts/auto_tests_docs/auto_tests.py

@@ -24,10 +24,12 @@ from dotenv import load_dotenv
 load_dotenv()
 
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
 
 model = OpenAIChat(
     model_name="gpt-4",
     openai_api_key=api_key,
+    openai_org_id=org_id,
     max_tokens=4000,
 )
 

scripts/auto_tests_docs/auto_tests_functions.py

@@ -12,10 +12,12 @@ from swarms.utils.parse_code import extract_code_from_markdown
 load_dotenv()
 
 api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
 
 model = OpenAIChat(
     model_name="gpt-4",
     openai_api_key=api_key,
+    openai_org_id=org_id,
     max_tokens=4000,
 )
 

swarms/agents/worker_agent.py

@@ -9,6 +9,10 @@ from langchain_experimental.autonomous_agents import AutoGPT
 
 from swarms.utils.decorators import error_decorator, timing_decorator
 
+import os
+
+api_key = os.getenv("OPENAI_API_KEY")
+org_id = os.getenv("OPENAI_ORG_ID")
 
 class Worker:
     """
@@ -48,6 +52,7 @@ class Worker:
         temperature: float = 0.5,
         llm=None,
         openai_api_key: str = None,
+        openai_org_id: str = None,
         tools: List[Any] = None,
         embedding_size: int = 1536,
         search_kwargs: dict = {"k": 8},
@@ -62,6 +67,7 @@ class Worker:
         self.temperature = temperature
         self.llm = llm
         self.openai_api_key = openai_api_key
+        self.openai_org_id = openai_org_id
         self.tools = tools
         self.embedding_size = embedding_size
         self.search_kwargs = search_kwargs
@@ -103,6 +109,7 @@ class Worker:
         external_tools = [MyTool1(), MyTool2()]
         worker = Worker(model_name="gpt-4",
                 openai_api_key="my_key",
+                openai_org_id="my_org_id",
                 name="My Worker",
                 role="Worker",
                 external_tools=external_tools,
@@ -123,9 +130,13 @@ class Worker:
         openai_api_key = (
             os.getenv("OPENAI_API_KEY") or self.openai_api_key
         )
+        openai_org_id = (
+            os.getenv("OPENAI_ORG_ID") or self.openai_org_id
+        )
         try:
             embeddings_model = OpenAIEmbeddings(
-                openai_api_key=openai_api_key
+                openai_api_key=openai_api_key,
+                openai_org_id=openai_org_id,
             )
             embedding_size = self.embedding_size
             index = faiss.IndexFlatL2(embedding_size)

swarms/memory/__init__.py

@@ -5,7 +5,7 @@ from swarms.memory.sqlite import SQLiteDB
 from swarms.memory.weaviate_db import WeaviateDB
 from swarms.memory.visual_memory import VisualShortTermMemory
 from swarms.memory.action_subtask import ActionSubtaskEntry
-from swarms.memory.chroma_db import ChromaDB
+# from swarms.memory.chroma_db import ChromaDB
 
 __all__ = [
     "AbstractVectorDatabase",
@@ -15,5 +15,5 @@ __all__ = [
     "WeaviateDB",
     "VisualShortTermMemory",
     "ActionSubtaskEntry",
-    "ChromaDB",
+    #"ChromaDB",
 ]

swarms/memory/chroma_db.py

@@ -41,6 +41,7 @@ class ChromaDB:
         >>>     output="results",
         >>>     llm="gpt3",
         >>>     openai_api_key=OPENAI_API_KEY,
+        >>>     openai_org_id=OPENAI_ORG_ID,
         >>> )
         >>> chromadb.add(task, result, result_id)
     """

swarms/models/dalle3.py

@@ -65,13 +65,15 @@ class Dalle3:
     max_retries: int = 3
     quality: str = "standard"
     openai_api_key: str = None or os.getenv("OPENAI_API_KEY")
+    openai_org_id: str = None or os.getenv("OPENAI_ORG_ID")
     n: int = 1
     save_path: str = "images"
     max_time_seconds: int = 60
     save_folder: str = "images"
     image_format: str = "png"
     client = OpenAI(
-        api_key=openai_api_key,
+        openai_api_key=openai_api_key,
+        openai_org_id=openai_org_id,
     )
     cache = TTLCache(maxsize=100, ttl=3600)
     dashboard: bool = False

swarms/models/gpt4_vision_api.py

@@ -22,6 +22,7 @@ except ImportError:
 # Load environment variables
 load_dotenv()
 openai_api_key = os.getenv("OPENAI_API_KEY")
+openai_org_id = os.getenv("OPENAI_ORG_ID")
 
 
 gpt4_vision_system_prompt = """
@@ -67,6 +68,7 @@ class GPT4VisionAPI(BaseMultiModalModel):
     def __init__(
         self,
         openai_api_key: str = openai_api_key,
+        openai_org_id: str = openai_org_id,
         model_name: str = "gpt-4-vision-preview",
         logging_enabled: bool = False,
         max_workers: int = 10,
@@ -81,6 +83,7 @@ class GPT4VisionAPI(BaseMultiModalModel):
     ):
         super(GPT4VisionAPI).__init__(*args, **kwargs)
         self.openai_api_key = openai_api_key
+        self.openai_org_id = openai_org_id
         self.logging_enabled = logging_enabled
         self.model_name = model_name
         self.max_workers = max_workers
@@ -127,6 +130,7 @@ class GPT4VisionAPI(BaseMultiModalModel):
             headers = {
                 "Content-Type": "application/json",
                 "Authorization": f"Bearer {self.openai_api_key}",
+                "OpenAI-Organization": f"{self.openai_org_id}"
             }
             payload = {
                 "model": self.model_name,
@@ -203,7 +207,6 @@ class GPT4VisionAPI(BaseMultiModalModel):
         """
         PROMPT = f"""
         These are frames from a video that I want to upload. Generate a compelling description that I can upload along with the video:
-        
         {frames}
         """
         return PROMPT
@@ -266,6 +269,7 @@ class GPT4VisionAPI(BaseMultiModalModel):
         headers = {
             "Content-Type": "application/json",
             "Authorization": f"Bearer {openai_api_key}",
+            "OpenAI-Organization": f"{self.openai_org_id}"
         }
         payload = {
             "model": self.model_name,
@@ -328,6 +332,7 @@ class GPT4VisionAPI(BaseMultiModalModel):
             headers = {
                 "Content-Type": "application/json",
                 "Authorization": f"Bearer {openai_api_key}",
+                "OpenAI-Organization": f"{self.openai_org_id}"
             }
             payload = {
                 "model": self.model_name,

swarms/models/kosmos_two.py

@@ -209,19 +209,8 @@ class Kosmos(BaseMultiModalModel):
                 x1 = orig_x1 - l_o
                 y1 = orig_y1 - l_o
 
-                if (
+                if (y1 < text_height + text_offset_original + 2 * text_spaces):
-                    y1
+                    y1 = (orig_y1 + r_o + text_height + text_offset_original + 2 * text_spaces)
-                    < text_height
-                    + text_offset_original
-                    + 2 * text_spaces
-                ):
-                    y1 = (
-                        orig_y1
-                        + r_o
-                        + text_height
-                        + text_offset_original
-                        + 2 * text_spaces
-                    )
                     x1 = orig_x1 + r_o
 
                 # add text background
@@ -233,12 +222,7 @@ class Kosmos(BaseMultiModalModel):
                 )
                 text_bg_x1, text_bg_y1, text_bg_x2, text_bg_y2 = (
                     x1,
-                    y1
+                    y1 - (text_height + text_offset_original + 2 * text_spaces),
-                    - (
-                        text_height
-                        + text_offset_original
-                        + 2 * text_spaces
-                    ),
                     x1 + text_width,
                     y1,
                 )
@@ -253,31 +237,14 @@ class Kosmos(BaseMultiModalModel):
                         ),
                         prev_bbox,
                     ):
-                        text_bg_y1 += (
+                        text_bg_y1 += (text_height + text_offset_original + 2 * text_spaces)
-                            text_height
+                        text_bg_y2 += (text_height + text_offset_original + 2 * text_spaces)
-                            + text_offset_original
+                        y1 += (text_height + text_offset_original + 2 * text_spaces)
-                            + 2 * text_spaces
-                        )
-                        text_bg_y2 += (
-                            text_height
-                            + text_offset_original
-                            + 2 * text_spaces
-                        )
-                        y1 += (
-                            text_height
-                            + text_offset_original
-                            + 2 * text_spaces
-                        )
 
                         if text_bg_y2 >= image_h:
                             text_bg_y1 = max(
                                 0,
-                                image_h
+                                image_h - (text_height + text_offset_original + 2 * text_spaces),
-                                - (
-                                    text_height
-                                    + text_offset_original
-                                    + 2 * text_spaces
-                                ),
                             )
                             text_bg_y2 = image_h
                             y1 = image_h
@@ -294,8 +261,7 @@ class Kosmos(BaseMultiModalModel):
                                 # white
                                 bg_color = [255, 255, 255]
                             new_image[i, j] = (
-                                alpha * new_image[i, j]
+                                alpha * new_image[i, j] + (1 - alpha) * np.array(bg_color)
-                                + (1 - alpha) * np.array(bg_color)
                             ).astype(np.uint8)
 
                 cv2.putText(

swarms/models/openai_embeddings.py

@@ -63,9 +63,7 @@ def _create_retry_decorator(
             | retry_if_exception_type(llm.error.APIError)
             | retry_if_exception_type(llm.error.APIConnectionError)
             | retry_if_exception_type(llm.error.RateLimitError)
-            | retry_if_exception_type(
+            | retry_if_exception_type(llm.error.ServiceUnavailableError)
-                llm.error.ServiceUnavailableError
-            )
         ),
         before_sleep=before_sleep_log(logger, logging.WARNING),
     )
@@ -171,6 +169,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
             os.environ["OPENAI_API_TYPE"] = "azure"
             os.environ["OPENAI_API_BASE"] = "https://<your-endpoint.openai.azure.com/"
             os.environ["OPENAI_API_KEY"] = "your AzureOpenAI key"
+            os.environ["OPENAI_ORG_ID"] = "your AzureOpenAI organization id"
             os.environ["OPENAI_API_VERSION"] = "2023-05-15"
             os.environ["OPENAI_PROXY"] = "http://your-corporate-proxy:8080"
 
@@ -199,6 +198,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
     embedding_ctx_length: int = 8191
     """The maximum number of tokens to embed at once."""
     openai_api_key: Optional[str] = None
+    openai_org_id: Optional[str] = None
     openai_organization: Optional[str] = None
     allowed_special: Union[Literal["all"], Set[str]] = set()
     disallowed_special: Union[
@@ -270,6 +270,9 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
         values["openai_api_key"] = get_from_dict_or_env(
             values, "openai_api_key", "OPENAI_API_KEY"
         )
+        values["openai_org_id"] = get_from_dict_or_env(
+            values, "openai_org_id", "OPENAI_ORG_ID", default=""
+        )
         values["openai_api_base"] = get_from_dict_or_env(
             values,
             "openai_api_base",
@@ -326,6 +329,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
             "request_timeout": self.request_timeout,
             "headers": self.headers,
             "api_key": self.openai_api_key,
+            "org_id" : self.openai_org_id,
             "organization": self.openai_organization,
             "api_base": self.openai_api_base,
             "api_type": self.openai_api_type,
@@ -386,7 +390,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
             )
             for j in range(0, len(token), self.embedding_ctx_length):
                 tokens.append(
-                    token[j : j + self.embedding_ctx_length]
+                    token[j: j + self.embedding_ctx_length]
                 )
                 indices.append(i)
 
@@ -406,7 +410,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
         for i in _iter:
             response = embed_with_retry(
                 self,
-                input=tokens[i : i + _chunk_size],
+                input=tokens[i: i + _chunk_size],
                 **self._invocation_params,
             )
             batched_embeddings.extend(
@@ -486,7 +490,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
             )
             for j in range(0, len(token), self.embedding_ctx_length):
                 tokens.append(
-                    token[j : j + self.embedding_ctx_length]
+                    token[j: j + self.embedding_ctx_length]
                 )
                 indices.append(i)
 
@@ -495,7 +499,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
         for i in range(0, len(tokens), _chunk_size):
             response = await async_embed_with_retry(
                 self,
-                input=tokens[i : i + _chunk_size],
+                input=tokens[i: i + _chunk_size],
                 **self._invocation_params,
             )
             batched_embeddings.extend(

swarms/models/openai_function_caller.py

@@ -113,6 +113,7 @@ class OpenAIFunctionCaller:
     def __init__(
         self,
         openai_api_key: str,
+        openai_org_id: str,
         model: str = "text-davinci-003",
         max_tokens: int = 3000,
         temperature: float = 0.5,
@@ -131,6 +132,7 @@ class OpenAIFunctionCaller:
         timeout_sec: Union[float, None] = None,
     ):
         self.openai_api_key = openai_api_key
+        self.openai_org_id = openai_org_id
         self.model = model
         self.max_tokens = max_tokens
         self.temperature = temperature
@@ -164,6 +166,7 @@ class OpenAIFunctionCaller:
         headers = {
             "Content-Type": "application/json",
             "Authorization": "Bearer " + openai.api_key,
+            "OpenAI-Organization": f"{self.openai_org_id}"
         }
         json_data = {"model": self.model, "messages": messages}
         if tools is not None:

swarms/models/openai_models.py

@@ -45,15 +45,12 @@ from tenacity import (
     wait_exponential,
 )
 
-logger = logging.getLogger(__name__)
-
 from importlib.metadata import version
 
 from packaging.version import parse
 
 logger = logging.getLogger(__name__)
 
-
 @functools.lru_cache
 def _log_error_once(msg: str) -> None:
     """Log an error once."""
@@ -281,6 +278,7 @@ class BaseOpenAI(BaseLLM):
     model_kwargs: Dict[str, Any] = Field(default_factory=dict)
     """Holds any model parameters valid for `create` call not explicitly specified."""
     openai_api_key: Optional[str] = None
+    openai_org_id: Optional[str] = None
     openai_api_base: Optional[str] = None
     openai_organization: Optional[str] = None
     # to support explicit proxy for OpenAI
@@ -340,6 +338,9 @@ class BaseOpenAI(BaseLLM):
         values["openai_api_key"] = get_from_dict_or_env(
             values, "openai_api_key", "OPENAI_API_KEY"
         )
+        values["openai_org_id"] = get_from_dict_or_env(
+            values, "openai_org_id", "OPENAI_ORG_ID"
+        )
         values["openai_api_base"] = get_from_dict_or_env(
             values,
             "openai_api_base",
@@ -650,6 +651,7 @@ class BaseOpenAI(BaseLLM):
         """Get the parameters used to invoke the model."""
         openai_creds: Dict[str, Any] = {
             "api_key": self.openai_api_key,
+            "org_id" : self.openai_org_id,
             "api_base": self.openai_api_base,
             "organization": self.openai_organization,
         }
@@ -905,6 +907,7 @@ class OpenAIChat(BaseLLM):
     model_name: str = "gpt-4-1106-preview"
     model_kwargs: Dict[str, Any] = Field(default_factory=dict)
     openai_api_key: Optional[str] = None
+    openai_org_id: Optional[str] = None
     openai_api_base: Optional[str] = None
     openai_proxy: Optional[str] = None
     max_retries: int = 6
@@ -942,6 +945,9 @@ class OpenAIChat(BaseLLM):
         openai_api_key = get_from_dict_or_env(
             values, "openai_api_key", "OPENAI_API_KEY"
         )
+        openai_org_id = get_from_dict_or_env(
+            values, "openai_org_id", "OPENAI_ORG_ID"
+        )
         openai_api_base = get_from_dict_or_env(
             values,
             "openai_api_base",
@@ -964,6 +970,7 @@ class OpenAIChat(BaseLLM):
             import openai
 
             openai.api_key = openai_api_key
+            openai.org_id = openai_org_id
             if openai_api_base:
                 openai.api_base = openai_api_base
             if openai_organization:

swarms/models/openai_tts.py

@@ -25,6 +25,9 @@ def openai_api_key_env():
     openai_api_key = os.getenv("OPENAI_API_KEY")
     return openai_api_key
 
+def openai_org_id_env():
+    openai_org_id = os.getenv("OPENAI_ORG_ID")
+    return openai_org_id
 
 class OpenAITTS(AbstractLLM):
     """OpenAI TTS model
@@ -33,6 +36,7 @@ class OpenAITTS(AbstractLLM):
         model_name (str): _description_
         proxy_url (str): _description_
         openai_api_key (str): _description_
+        openai_org_id (str): _description_
         voice (str): _description_
         chunk_size (_type_): _description_
 
@@ -46,6 +50,7 @@ class OpenAITTS(AbstractLLM):
     ...     model_name = "tts-1-1106",
     ...     proxy_url = "https://api.openai.com/v1/audio/speech",
     ...     openai_api_key = openai_api_key_env,
+    ...     openai_org_id = openai_org_id_env,
     ...     voice = "onyx",
     ... )
     >>> tts.run("Hello world")
@@ -57,6 +62,7 @@ class OpenAITTS(AbstractLLM):
         model_name: str = "tts-1-1106",
         proxy_url: str = "https://api.openai.com/v1/audio/speech",
         openai_api_key: str = openai_api_key_env,
+        openai_org_id: str = openai_org_id_env,
         voice: str = "onyx",
         chunk_size=1024 * 1024,
         autosave: bool = False,
@@ -68,6 +74,7 @@ class OpenAITTS(AbstractLLM):
         self.model_name = model_name
         self.proxy_url = proxy_url
         self.openai_api_key = openai_api_key
+        self.openai_org_id = openai_org_id
         self.voice = voice
         self.chunk_size = chunk_size
         self.autosave = autosave

swarms/models/palm.py

@@ -41,15 +41,9 @@ def _create_retry_decorator() -> Callable[[Any], Any]:
             multiplier=multiplier, min=min_seconds, max=max_seconds
         ),
         retry=(
-            retry_if_exception_type(
+            retry_if_exception_type(google.api_core.exceptions.ResourceExhausted)
-                google.api_core.exceptions.ResourceExhausted
+            | retry_if_exception_type(google.api_core.exceptions.ServiceUnavailable)
-            )
+            | retry_if_exception_type(google.api_core.exceptions.GoogleAPIError)
-            | retry_if_exception_type(
-                google.api_core.exceptions.ServiceUnavailable
-            )
-            | retry_if_exception_type(
-                google.api_core.exceptions.GoogleAPIError
-            )
         ),
         before_sleep=before_sleep_log(logger, logging.WARNING),
     )
@@ -123,30 +117,17 @@ class GooglePalm(BaseLLM, BaseModel):
 
         values["client"] = genai
 
-        if (
+        if (values["temperature"] is not None and not 0 <= values["temperature"] <= 1):
-            values["temperature"] is not None
+            raise ValueError("temperature must be in the range [0.0, 1.0]")
-            and not 0 <= values["temperature"] <= 1
-        ):
-            raise ValueError(
-                "temperature must be in the range [0.0, 1.0]"
-            )
 
-        if (
+        if (values["top_p"] is not None and not 0 <= values["top_p"] <= 1):
-            values["top_p"] is not None
-            and not 0 <= values["top_p"] <= 1
-        ):
             raise ValueError("top_p must be in the range [0.0, 1.0]")
 
         if values["top_k"] is not None and values["top_k"] <= 0:
             raise ValueError("top_k must be positive")
 
-        if (
+        if (values["max_output_tokens"] is not None and values["max_output_tokens"] <= 0):
-            values["max_output_tokens"] is not None
+            raise ValueError("max_output_tokens must be greater than zero")
-            and values["max_output_tokens"] <= 0
-        ):
-            raise ValueError(
-                "max_output_tokens must be greater than zero"
-            )
 
         return values
 

swarms/models/sampling_params.py

@@ -209,10 +209,7 @@ class SamplingParams:
             raise ValueError(
                 f"logprobs must be non-negative, got {self.logprobs}."
             )
-        if (
+        if (self.prompt_logprobs is not None and self.prompt_logprobs < 0):
-            self.prompt_logprobs is not None
-            and self.prompt_logprobs < 0
-        ):
             raise ValueError(
                 "prompt_logprobs must be non-negative, got "
                 f"{self.prompt_logprobs}."
@@ -248,10 +245,7 @@ class SamplingParams:
                 "early_stopping is not effective and must be "
                 "False when not using beam search."
             )
-        if (
+        if (self.length_penalty < 1.0 - _SAMPLING_EPS or self.length_penalty > 1.0 + _SAMPLING_EPS):
-            self.length_penalty < 1.0 - _SAMPLING_EPS
-            or self.length_penalty > 1.0 + _SAMPLING_EPS
-        ):
             raise ValueError(
                 "length_penalty is not effective and must be the "
                 "default value of 1.0 when not using beam search."

swarms/models/vip_llava.py

@@ -83,7 +83,7 @@ class VipLlavaMultiModal(BaseMultiModalModel):
             )
 
             return self.processor.decode(
-                generate_ids[0][len(inputs["input_ids"][0]) :],
+                generate_ids[0][len(inputs["input_ids"][0]):],
                 skip_special_tokens=True,
             )
 

swarms/structs/SWARMS.md

@@ -292,7 +292,7 @@ class Orchestrator:
                     self.condition.notify()
 
     def embed(self, input):
-        openai = embedding_functions.OpenAIEmbeddingFunction(api_key=self.api_key, model_name=self.model_name)
+        openai = embedding_functions.OpenAIEmbeddingFunction(api_key=self.api_key, org_id=self.org_id, model_name=self.model_name)
         embedding = openai(input)
         return embedding
 

swarms/structs/autoscaler.py

@@ -79,6 +79,7 @@ class AutoScaler(BaseStructure):
     >>> llm = OpenAIChat(
     ...     temperature=0.5,
     ...     openai_api_key=api_key,
+    ...     openai_org_id=org_id,
     ... )
     >>> ## Initialize the workflow
     >>> agent = Agent(llm=llm, max_loops=1, dashboard=True)

swarms/structs/base_workflow.py

@@ -138,7 +138,7 @@ class BaseWorkflow(BaseStructure):
         Examples:
         >>> from swarms.models import OpenAIChat
         >>> from swarms.structs import SequentialWorkflow
-        >>> llm = OpenAIChat(openai_api_key="")
+        >>> llm = OpenAIChat(openai_api_key="",openai_org_id="")
         >>> workflow = SequentialWorkflow(max_loops=1)
         >>> workflow.add("What's the weather in miami", llm)
         >>> workflow.add("Create a report on these metrics", llm)
@@ -176,7 +176,7 @@ class BaseWorkflow(BaseStructure):
         Examples:
         >>> from swarms.models import OpenAIChat
         >>> from swarms.structs import SequentialWorkflow
-        >>> llm = OpenAIChat(openai_api_key="")
+        >>> llm = OpenAIChat(openai_api_key="", openai_org_id="")
         >>> workflow = SequentialWorkflow(max_loops=1)
         >>> workflow.add("What's the weather in miami", llm)
         >>> workflow.add("Create a report on these metrics", llm)
@@ -215,7 +215,7 @@ class BaseWorkflow(BaseStructure):
         Examples:
         >>> from swarms.models import OpenAIChat
         >>> from swarms.structs import SequentialWorkflow
-        >>> llm = OpenAIChat(openai_api_key="")
+        >>> llm = OpenAIChat(openai_api_key="", openai_org_id="")
         >>> workflow = SequentialWorkflow(max_loops=1)
         >>> workflow.add("What's the weather in miami", llm)
         >>> workflow.add("Create a report on these metrics", llm)
@@ -287,7 +287,7 @@ class BaseWorkflow(BaseStructure):
         Examples:
         >>> from swarms.models import OpenAIChat
         >>> from swarms.structs import SequentialWorkflow
-        >>> llm = OpenAIChat(openai_api_key="")
+        >>> llm = OpenAIChat(openai_api_key="", openai_org_id="")
         >>> workflow = SequentialWorkflow(max_loops=1)
         >>> workflow.add("What's the weather in miami", llm)
         >>> workflow.add("Create a report on these metrics", llm)

swarms/structs/concurrent_workflow.py

@@ -24,7 +24,7 @@ class ConcurrentWorkflow(BaseStructure):
     Examples:
     >>> from swarms.models import OpenAIChat
     >>> from swarms.structs import ConcurrentWorkflow
-    >>> llm = OpenAIChat(openai_api_key="")
+    >>> llm = OpenAIChat(openai_api_key="", openai_org_id="")
     >>> workflow = ConcurrentWorkflow(max_workers=5)
     >>> workflow.add("What's the weather in miami", llm)
     >>> workflow.add("Create a report on these metrics", llm)

swarms/structs/debate.py

@@ -21,6 +21,7 @@ class DebatePlayer(Agent):
             name (str): name of this player
             temperature (float): higher values make the output more random, while lower values make it more focused and deterministic
             openai_api_key (str): As the parameter name suggests
+            openai_org_id (str): As the parameter name suggests
             sleep_time (float): sleep because of rate limits
         """
         super(DebatePlayer, self).__init__(
@@ -37,6 +38,7 @@ class Debate:
         num_players (int): num of players
         save_file_dir (str): dir path to json file
         openai_api_key (str): As the parameter name suggests
+        openai_org_id (str): As the parameter name suggests
         prompts_path (str): prompts path (json file)
         max_round (int): maximum Rounds of Debate
         sleep_time (float): sleep because of rate limits
@@ -277,6 +279,7 @@ class Debate:
                 name="Judge",
                 temperature=self.temperature,
                 openai_api_key=self.openai_api_key,
+                openai_org_id=self.openai_org_id,
                 sleep_time=self.sleep_time,
             )
             aff_ans = self.affirmative.memory_lst[2]["content"]

swarms/structs/model_parallizer.py

@@ -36,10 +36,12 @@ class ModelParallelizer:
     ...     OpenAIChat(
     ...         temperature=0.5,
     ...         openai_api_key="OPENAI_API_KEY",
+    ...         openai_org_id="OPENAI_ORG_ID",
     ...     ),
     ...     OpenAIChat(
     ...         temperature=0.5,
     ...         openai_api_key="OPENAI_API_KEY",
+    ...         openai_org_id="OPENAI_ORG_ID",
     ...     ),
     ... ]
     >>> mp = ModelParallelizer(llms)

swarms/structs/multi_agent_collab.py

@@ -61,6 +61,8 @@ class MultiAgentCollaboration:
     >>>
     >>> # Initialize the language model
     >>> llm = OpenAIChat(
+    >>>     openai_api_key="OPENAI_API_KEY",
+    >>>     openai_org_id="OPENAI_ORG_ID",
     >>>     temperature=0.5,
     >>> )
     >>>

swarms/structs/nonlinear_workflow.py

@@ -18,7 +18,7 @@ class NonlinearWorkflow(BaseStructure):
     Examples:
     >>> from swarms.models import OpenAIChat
     >>> from swarms.structs import NonlinearWorkflow, Task
-    >>> llm = OpenAIChat(openai_api_key="")
+    >>> llm = OpenAIChat(openai_api_key="", openai_org_id="")
     >>> task = Task(llm, "What's the weather in miami")
     >>> workflow = NonlinearWorkflow()
     >>> workflow.add(task)

swarms/structs/recursive_workflow.py

@@ -24,7 +24,7 @@ class RecursiveWorkflow(BaseStructure):
     Examples:
     >>> from swarms.models import OpenAIChat
     >>> from swarms.structs import RecursiveWorkflow, Task
-    >>> llm = OpenAIChat(openai_api_key="")
+    >>> llm = OpenAIChat(openai_api_key="", openai_org_id="")
     >>> task = Task(llm, "What's the weather in miami")
     >>> workflow = RecursiveWorkflow()
     >>> workflow.add(task)

swarms/structs/schemas.py

@@ -155,3 +155,12 @@ class Step(StepRequestBody):
         False,
         description="Whether this is the last step in the task.",
     )
+
+class Skill(BaseModel):
+    name: str
+    level: int
+
+class Agent(BaseModel):
+    name: str
+    age: int
+    skills: List[Skill]

swarms/structs/sequential_workflow.py

@@ -28,7 +28,7 @@ class SequentialWorkflow:
     Examples:
     >>> from swarms.models import OpenAIChat
     >>> from swarms.structs import SequentialWorkflow
-    >>> llm = OpenAIChat(openai_api_key="")
+    >>> llm = OpenAIChat(openai_api_key="", openai_org_id="")
     >>> workflow = SequentialWorkflow(max_loops=1)
     >>> workflow.add("What's the weather in miami", llm)
     >>> workflow.add("Create a report on these metrics", llm)
@@ -158,7 +158,7 @@ class SequentialWorkflow:
         Examples:
         >>> from swarms.models import OpenAIChat
         >>> from swarms.structs import SequentialWorkflow
-        >>> llm = OpenAIChat(openai_api_key="")
+        >>> llm = OpenAIChat(openai_api_key="", openai_org_id="")
         >>> workflow = SequentialWorkflow(max_loops=1)
         >>> workflow.add("What's the weather in miami", llm)
         >>> workflow.add("Create a report on these metrics", llm)
@@ -220,7 +220,7 @@ class SequentialWorkflow:
         Examples:
         >>> from swarms.models import OpenAIChat
         >>> from swarms.structs import SequentialWorkflow
-        >>> llm = OpenAIChat(openai_api_key="")
+        >>> llm = OpenAIChat(openai_api_key="", openai_org_id="")
         >>> workflow = SequentialWorkflow(max_loops=1)
         >>> workflow.add("What's the weather in miami", llm)
         >>> workflow.add("Create a report on these metrics", llm)
@@ -271,7 +271,7 @@ class SequentialWorkflow:
         Examples:
         >>> from swarms.models import OpenAIChat
         >>> from swarms.structs import SequentialWorkflow
-        >>> llm = OpenAIChat(openai_api_key="")
+        >>> llm = OpenAIChat(openai_api_key="", openai_org_id="")
         >>> workflow = SequentialWorkflow(max_loops=1)
         >>> workflow.add("What's the weather in miami", llm)
         >>> workflow.add("Create a report on these metrics", llm)

swarms/structs/task.py

@@ -50,7 +50,7 @@ class Task:
     Examples:
     >>> from swarms.structs import Task, Agent
     >>> from swarms.models import OpenAIChat
-    >>> agent = Agent(llm=OpenAIChat(openai_api_key=""), max_loops=1, dashboard=False)
+    >>> agent = Agent(llm=OpenAIChat(openai_api_key="", openai_org_id=""), max_loops=1, dashboard=False)
     >>> task = Task(description="What's the weather in miami", agent=agent)
     >>> task.execute()
     >>> task.result
@@ -81,7 +81,7 @@ class Task:
         Examples:
         >>> from swarms.structs import Task, Agent
         >>> from swarms.models import OpenAIChat
-        >>> agent = Agent(llm=OpenAIChat(openai_api_key=""), max_loops=1, dashboard=False)
+        >>> agent = Agent(llm=OpenAIChat(openai_api_key="", openai_org_id=""), max_loops=1, dashboard=False)
         >>> task = Task(description="What's the weather in miami", agent=agent)
         >>> task.execute()
         >>> task.result

swarms/tokenizers/anthropic_tokenizer.py

@@ -61,10 +61,7 @@ class AnthropicTokenizer(BaseTokenizer):
         }
         self.model = self.model  # or self.DEFAULT_MODEL
         self.max_tokens = self.max_tokens or self.default_max_tokens()
-        self.client = (
+        self.client = (self.client or import_optional_dependency("anthropic").Anthropic())
-            self.client
-            or import_optional_dependency("anthropic").Anthropic()
-        )
 
     def default_max_tokens(self) -> int:
         """

swarms/tokenizers/openai_tokenizers.py

@@ -1,3 +1,6 @@
+# noqa: E501
+""" A module for OpenAI tokenizers. """
+
 from __future__ import annotations
 import logging
 from dataclasses import dataclass, field

swarms/tokenizers/r_tokenizers.py

@@ -58,11 +58,7 @@ class SentencePieceTokenizer:
 
     def _maybe_add_prefix_space(self, tokens, decoded):
         """maybe add prefix space for incremental decoding."""
-        if (
+        if (len(tokens) and not decoded.startswith(" ") and tokens[0] in self.prefix_space_tokens):
-            len(tokens)
-            and not decoded.startswith(" ")
-            and tokens[0] in self.prefix_space_tokens
-        ):
             return " " + decoded
         else:
             return decoded
@@ -151,10 +147,7 @@ class HuggingFaceTokenizer:
         backend_tokenizer_file = osp.join(model_dir, "tokenizer.json")
         model_file_exists = osp.exists(model_file)
         self.logger = get_logger("lmdeploy")
-        if (
+        if (not osp.exists(backend_tokenizer_file) and model_file_exists):
-            not osp.exists(backend_tokenizer_file)
-            and model_file_exists
-        ):
             self.logger.warning(
                 "Can not find tokenizer.json. "
                 "It may take long time to initialize the tokenizer."
@@ -164,15 +157,10 @@ class HuggingFaceTokenizer:
         )
         self._prefix_space_tokens = None
         # save tokenizer.json to reuse
-        if (
+        if (not osp.exists(backend_tokenizer_file) and model_file_exists):
-            not osp.exists(backend_tokenizer_file)
-            and model_file_exists
-        ):
             if hasattr(self.model, "backend_tokenizer"):
                 if os.access(model_dir, os.W_OK):
-                    self.model.backend_tokenizer.save(
+                    self.model.backend_tokenizer.save(backend_tokenizer_file)
-                        backend_tokenizer_file
-                    )
 
         if self.model.eos_token_id is None:
             generation_config_file = osp.join(
@@ -227,11 +215,7 @@ class HuggingFaceTokenizer:
         self, tokens: List[int], decoded: str
     ):
         """maybe add prefix space for incremental decoding."""
-        if (
+        if (len(tokens) and not decoded.startswith(" ") and tokens[0] in self.prefix_space_tokens):
-            len(tokens)
-            and not decoded.startswith(" ")
-            and tokens[0] in self.prefix_space_tokens
-        ):
             return " " + decoded
         else:
             return decoded
@@ -241,9 +225,7 @@ class HuggingFaceTokenizer:
         """Check if self.model.convert_ids_to_tokens return not a str value."""
         if self._maybe_decode_bytes is None:
             self._maybe_decode_bytes = False
-            vocab = self.model.convert_ids_to_tokens(
+            vocab = self.model.convert_ids_to_tokens(list(range(self.vocab_size)))
-                list(range(self.vocab_size))
-            )
             for tok in vocab:
                 if not isinstance(tok, str):
                     self._maybe_decode_bytes = True

swarms/utils/load_model_torch.py

@@ -38,13 +38,14 @@ def load_model_torch(
     try:
         if model is None:
             model = torch.load(
-                model_path, map_location=map_location, *args, **kwargs
+                model_path, map_location=map_location, weights_only=True, *args, **kwargs
             )
         else:
             model.load_state_dict(
                 torch.load(
                     model_path,
                     map_location=map_location,
+                    weights_only=True,
                     *args,
                     **kwargs,
                 ),

tests/memory/test_weaviate.py

@@ -15,7 +15,9 @@ def weaviate_client_mock():
         grpc_secure=False,
         auth_client_secret="mock_api_key",
         additional_headers={
-            "X-OpenAI-Api-Key": "mock_openai_api_key"
+            "X-OpenAI-Api-Key": "mock_openai_api_key",
+            "X-OpenAI-Organization": "mock_openai_org_id",
+
         },
         additional_config=Mock(),
     )