diff --git a/crypto_tax.py b/crypto_tax.py
new file mode 100644
index 00000000..cf887e31
--- /dev/null
+++ b/crypto_tax.py
@@ -0,0 +1,56 @@
+import os
+from dotenv import load_dotenv
+from swarm_models import OpenAIChat
+from swarms import Agent, GroupChat, expertise_based
+
+if __name__ == "__main__":
+
+ load_dotenv()
+
+ # Get the OpenAI API key from the environment variable
+ api_key = os.getenv("GROQ_API_KEY")
+
+ # Model
+ model = OpenAIChat(
+ openai_api_base="https://api.groq.com/openai/v1",
+ openai_api_key=api_key,
+ model_name="llama-3.1-70b-versatile",
+ temperature=0.1,
+ )
+
+ # Example agents
+ agent1 = Agent(
+ agent_name="Crypto-Tax-Optimization-Agent",
+ system_prompt="You are a friendly tax expert specializing in cryptocurrency investments. Provide approachable insights on optimizing tax savings for crypto transactions.",
+ llm=model,
+ max_loops=1,
+ dynamic_temperature_enabled=True,
+ user_name="User",
+ output_type="string",
+ streaming_on=True,
+ )
+
+ agent2 = Agent(
+ agent_name="Crypto-Investment-Strategies-Agent",
+ system_prompt="You are a conversational financial analyst focused on cryptocurrency investments. Offer debatable advice on investment strategies that minimize tax liabilities.",
+ llm=model,
+ max_loops=1,
+ dynamic_temperature_enabled=True,
+ user_name="User",
+ output_type="string",
+ streaming_on=True,
+ )
+
+ agents = [agent1, agent2]
+
+ chat = GroupChat(
+ name="Crypto Tax Optimization Debate",
+ description="Debate on optimizing tax savings for cryptocurrency transactions and investments",
+ agents=agents,
+ speaker_fn=expertise_based,
+ )
+
+ history = chat.run(
+ "How can one optimize tax savings for cryptocurrency transactions and investments? I bought some Bitcoin and Ethereum last year and want to minimize my tax liabilities this year."
+ )
+ print(history.model_dump_json(indent=2))
diff --git a/group_chat_example.py b/group_chat_example.py
index dbe508bb..830594f4 100644
--- a/group_chat_example.py
+++ b/group_chat_example.py
@@ -10,58 +10,62 @@ if __name__ == "__main__":
load_dotenv()
# Get the OpenAI API key from the environment variable
- api_key = os.getenv("OPENAI_API_KEY")
+ api_key = os.getenv("GROQ_API_KEY")
- # Create an instance of the OpenAIChat class
+ # Model
model = OpenAIChat(
+ openai_api_base="https://api.groq.com/openai/v1",
openai_api_key=api_key,
- model_name="gpt-4o-mini",
+ model_name="llama-3.1-70b-versatile",
temperature=0.1,
)
# Example agents
agent1 = Agent(
agent_name="Financial-Analysis-Agent",
- system_prompt="You are a financial analyst specializing in investment strategies.",
+ system_prompt="You are a friendly financial analyst specializing in investment strategies. Be approachable and conversational.",
llm=model,
max_loops=1,
- autosave=False,
- dashboard=False,
- verbose=True,
dynamic_temperature_enabled=True,
user_name="swarms_corp",
- retry_attempts=1,
- context_length=200000,
output_type="string",
- streaming_on=False,
+ streaming_on=True,
)
agent2 = Agent(
agent_name="Tax-Adviser-Agent",
- system_prompt="You are a tax adviser who provides clear and concise guidance on tax-related queries.",
+ system_prompt="You are a tax adviser who provides clear, concise, and approachable guidance on tax-related queries.",
llm=model,
max_loops=1,
- autosave=False,
- dashboard=False,
- verbose=True,
dynamic_temperature_enabled=True,
user_name="swarms_corp",
- retry_attempts=1,
- context_length=200000,
output_type="string",
- streaming_on=False,
+ streaming_on=True,
)
+ # agent3 = Agent(
+ # agent_name="Stock-Buying-Agent",
+ # system_prompt="You are a stock market expert who provides insights on buying and selling stocks. Be informative and concise.",
+ # llm=model,
+ # max_loops=1,
+ # dynamic_temperature_enabled=True,
+ # user_name="swarms_corp",
+ # retry_attempts=1,
+ # context_length=200000,
+ # output_type="string",
+ # streaming_on=True,
+ # )
+
agents = [agent1, agent2]
chat = GroupChat(
name="Investment Advisory",
- description="Financial and tax analysis group",
+ description="Financial, tax, and stock analysis group",
agents=agents,
speaker_fn=expertise_based,
)
history = chat.run(
- "How to optimize tax strategy for investments?"
+ "How to save on taxes for stocks, ETFs, and mutual funds?"
)
print(history.model_dump_json(indent=2))
diff --git a/pyproject.toml b/pyproject.toml
index d2353214..5904f1b9 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -5,7 +5,7 @@ build-backend = "poetry.core.masonry.api"
[tool.poetry]
name = "swarms"
-version = "6.7.6"
+version = "6.7.7"
description = "Swarms - TGSC"
license = "MIT"
authors = ["Kye Gomez <kye@apac.ai>"]
diff --git a/swarm_arange_demo.py b/swarm_arange_demo.py
index d9457ac5..f900abcc 100644
--- a/swarm_arange_demo.py
+++ b/swarm_arange_demo.py
@@ -213,6 +213,6 @@ swarm_arrange = SwarmRearrange(
print(
swarm_arrange.run(
- "Analyze swarms, 150k revenue with 45m+ agents build, with 1.4m downloads since march 2024"
+ "Analyze AI ETFs, focusing on their performance, market trends, and potential for growth"
)
)
diff --git a/swarms/structs/__init__.py b/swarms/structs/__init__.py
index 234fb72c..dbae2f48 100644
--- a/swarms/structs/__init__.py
+++ b/swarms/structs/__init__.py
@@ -17,6 +17,7 @@ from swarms.structs.groupchat import (
ChatHistory,
ChatTurn,
AgentResponse,
+ expertise_based
)
from swarms.structs.majority_voting import (
MajorityVoting,
@@ -152,4 +153,5 @@ __all__ = [
"ChatHistory",
"ChatTurn",
"AgentResponse",
+ "expertise_based",
]
diff --git a/swarms/structs/spreadsheet_swarm.py b/swarms/structs/spreadsheet_swarm.py
index 8215bf2a..fded0820 100644
--- a/swarms/structs/spreadsheet_swarm.py
+++ b/swarms/structs/spreadsheet_swarm.py
@@ -16,8 +16,13 @@ from swarms.utils.loguru_logger import initialize_logger
logger = initialize_logger(log_folder="spreadsheet_swarm")
-# Replace timestamp-based time with a UUID for file naming
-run_id = uuid.uuid4().hex # Unique identifier for each run
+time = datetime.datetime.now().isoformat()
+uuid_hex = uuid.uuid4().hex
+
+# --------------- NEW CHANGE START ---------------
+# Format time variable to be compatible across operating systems
+formatted_time = datetime.datetime.now().strftime("%Y-%m-%dT%H-%M-%S")
+# --------------- NEW CHANGE END ---------------
class AgentOutput(BaseModel):
agent_name: str
@@ -279,4 +284,4 @@ class SpreadSheetSwarm(BaseSwarm):
# Write each output as a new row
for output in self.metadata.outputs:
row = f"{run_id},{output.agent_name},{output.task},{output.result},{output.timestamp}\n"
- await file.write(row)
\ No newline at end of file
+ await file.write(row)