Merge branch 'kyegomez:master' into new_master

deepseek_example.py

@@ -0,0 +1,70 @@
+import os
+
+from dotenv import load_dotenv
+from openai import OpenAI
+
+from swarms import Agent
+from swarms.prompts.finance_agent_sys_prompt import (
+    FINANCIAL_AGENT_SYS_PROMPT,
+)
+
+load_dotenv()
+
+
+class DeepSeekChat:
+    def __init__(
+        self,
+        api_key: str = os.getenv("DEEPSEEK_API_KEY"),
+        system_prompt: str = None,
+    ):
+        self.api_key = api_key
+
+        self.client = OpenAI(
+            api_key=api_key, base_url="https://api.deepseek.com"
+        )
+
+    def run(self, task: str):
+        response = self.client.chat.completions.create(
+            model="deepseek-chat",
+            messages=[
+                {
+                    "role": "system",
+                    "content": "You are a helpful assistant",
+                },
+                {"role": "user", "content": task},
+            ],
+            stream=False,
+        )
+
+        print(response)
+
+        out = response.choices[0].message.content
+        print(out)
+
+        return out
+
+
+model = DeepSeekChat()
+
+# Initialize the agent
+agent = Agent(
+    agent_name="Financial-Analysis-Agent",
+    agent_description="Personal finance advisor agent",
+    system_prompt=FINANCIAL_AGENT_SYS_PROMPT,
+    max_loops=1,
+    llm=model,
+    dynamic_temperature_enabled=True,
+    user_name="swarms_corp",
+    retry_attempts=3,
+    context_length=8192,
+    return_step_meta=False,
+    output_type="str",  # "json", "dict", "csv" OR "string" "yaml" and
+    auto_generate_prompt=False,  # Auto generate prompt for the agent based on name, description, and system prompt, task
+    max_tokens=4000,  # max output tokens
+)
+
+print(
+    agent.run(
+        "Create a table of super high growth opportunities for AI. I have $40k to invest in ETFs, index funds, and more. Please create a table in markdown.",
+    )
+)

docs/mkdocs.yml

@@ -199,6 +199,15 @@ nav:
     - Full API Reference: "swarms/framework/reference.md"
   - Examples:
     - Unique Swarms: "swarms/examples/unique_swarms.md"
+    - Various Model Providers:
+      - OpenAI: "swarms/examples/openai_example.md"
+      - Anthropic: "swarms/examples/claude.md"
+      - Groq: "swarms/examples/groq.md"
+      - Cohere: "swarms/examples/cohere.md"
+      - DeepSeek: "swarms/examples/deepseek.md"
+      - Ollama: "swarms/examples/ollama.md"
+      - OpenRouter: "swarms/examples/openrouter.md"
+      - XAI: "swarms/examples/xai.md"
   - Swarm Models:
     - Overview: "swarms/models/index.md"
     # - Models Available: "swarms/models/index.md"

docs/swarms/examples/claude.md

@@ -0,0 +1,25 @@
+# Agent with Anthropic/Claude
+
+- Get their api keys and put it in the `.env`
+
+- Select your model_name like `claude-3-sonnet-20240229` follows LiteLLM conventions
+
+
+```python
+from swarms import Agent
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Initialize the agent with ChromaDB memory
+agent = Agent(
+    agent_name="Financial-Analysis-Agent",
+    model_name="claude-3-sonnet-20240229",
+    system_prompt="Agent system prompt here",
+    agent_description="Agent performs financial analysis.",
+)
+
+# Run a query
+agent.run("What are the components of a startup's stock incentive equity plan?")
+```

docs/swarms/examples/cohere.md

@@ -0,0 +1,25 @@
+# Agent with Cohere
+
+- Add your `COHERE_API_KEY` in the `.env` file
+
+- Select your model_name like `command-r` follows LiteLLM conventions
+
+
+```python
+from swarms import Agent
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Initialize the agent with ChromaDB memory
+agent = Agent(
+    agent_name="Financial-Analysis-Agent",
+    model_name="command-r",
+    system_prompt="Agent system prompt here",
+    agent_description="Agent performs financial analysis.",
+)
+
+# Run a query
+agent.run("What are the components of a startup's stock incentive equity plan?")
+```

docs/swarms/examples/deepseek.md

@@ -0,0 +1,27 @@
+# Agent with DeepSeek
+
+- Add your `DEEPSEEK_API_KEY` in the `.env` file
+
+- Select your model_name like `deepseek/deepseek-chat` follows [LiteLLM conventions](https://docs.litellm.ai/docs/providers/deepseek)
+
+- Execute your agent!
+
+
+```python
+from swarms import Agent
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Initialize the agent with ChromaDB memory
+agent = Agent(
+    agent_name="Financial-Analysis-Agent",
+    model_name="deepseek/deepseek-chat",
+    system_prompt="Agent system prompt here",
+    agent_description="Agent performs financial analysis.",
+)
+
+# Run a query
+agent.run("What are the components of a startup's stock incentive equity plan?")
+```

docs/swarms/examples/groq.md

@@ -0,0 +1,48 @@
+# Agent with Groq
+
+- Add your `GROQ_API_KEY`
+
+```python
+import os
+
+from swarm_models import OpenAIChat
+
+from swarms import Agent
+
+company = "NVDA"
+
+# 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,
+)
+
+
+# Initialize the Managing Director agent
+managing_director = Agent(
+    agent_name="Managing-Director",
+    system_prompt=f"""
+    As the Managing Director at Blackstone, your role is to oversee the entire investment analysis process for potential acquisitions. 
+    Your responsibilities include:
+    1. Setting the overall strategy and direction for the analysis
+    2. Coordinating the efforts of the various team members and ensuring a comprehensive evaluation
+    3. Reviewing the findings and recommendations from each team member
+    4. Making the final decision on whether to proceed with the acquisition
+    
+    For the current potential acquisition of {company}, direct the tasks for the team to thoroughly analyze all aspects of the company, including its financials, industry position, technology, market potential, and regulatory compliance. Provide guidance and feedback as needed to ensure a rigorous and unbiased assessment.
+    """,
+    llm=model,
+    max_loops=1,
+    dashboard=False,
+    streaming_on=True,
+    verbose=True,
+    stopping_token="<DONE>",
+    state_save_file_type="json",
+    saved_state_path="managing-director.json",
+)
+```

docs/swarms/examples/ollama.md

@@ -0,0 +1,24 @@
+# Agent with Ollama
+
+- No API key needed
+- Select your model_name like `ollama/llama2` follows [LiteLLM conventions](https://docs.litellm.ai/docs/providers/ollama)
+
+
+```python
+from swarms import Agent
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Initialize the agent with ChromaDB memory
+agent = Agent(
+    agent_name="Financial-Analysis-Agent",
+    model_name="ollama/llama2",
+    system_prompt="Agent system prompt here",
+    agent_description="Agent performs financial analysis.",
+)
+
+# Run a query
+agent.run("What are the components of a startup's stock incentive equity plan?")
+```

docs/swarms/examples/openai_example.md

@@ -0,0 +1,16 @@
+# Agent with GPT-4o-Mini
+
+- Add `OPENAI_API_KEY="your_key"` to your `.env` file
+- Select your model like `gpt-4o-mini` or `gpt-4o`
+
+```python
+from swarms import Agent
+
+Agent(
+    agent_name="Stock-Analysis-Agent",
+    model_name="gpt-4o-mini",
+    max_loops="auto",
+    interactive=True,
+    streaming_on=True,
+).run("What are 5 hft algorithms")
+```

docs/swarms/examples/openrouter.md

@@ -0,0 +1,27 @@
+# Agent with OpenRouter
+
+- Add your `OPENROUTER_API_KEY` in the `.env` file
+
+- Select your model_name like `openrouter/google/palm-2-chat-bison` follows [LiteLLM conventions](https://docs.litellm.ai/docs/providers/openrouter)
+
+- Execute your agent!
+
+
+```python
+from swarms import Agent
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Initialize the agent with ChromaDB memory
+agent = Agent(
+    agent_name="Financial-Analysis-Agent",
+    model_name="openrouter/google/palm-2-chat-bison",
+    system_prompt="Agent system prompt here",
+    agent_description="Agent performs financial analysis.",
+)
+
+# Run a query
+agent.run("What are the components of a startup's stock incentive equity plan?")
+```

docs/swarms/examples/xai.md

@@ -0,0 +1,27 @@
+# Agent with XAI
+
+- Add your `XAI_API_KEY` in the `.env` file
+
+- Select your model_name like `xai/grok-beta` follows [LiteLLM conventions](https://docs.litellm.ai/docs/providers/xai)
+
+- Execute your agent!
+
+
+```python
+from swarms import Agent
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+# Initialize the agent with ChromaDB memory
+agent = Agent(
+    agent_name="Financial-Analysis-Agent",
+    model_name="xai/grok-beta",
+    system_prompt="Agent system prompt here",
+    agent_description="Agent performs financial analysis.",
+)
+
+# Run a query
+agent.run("What are the components of a startup's stock incentive equity plan?")
+```

new_features_examples/csvagent_example.py

@@ -1,6 +1,9 @@
 # Example usage
 from pathlib import Path
-from swarms.structs.csv_to_agent import AgentLoader, AgentValidationError
+from swarms.structs.csv_to_agent import (
+    AgentLoader,
+    AgentValidationError,
+)
 
 
 if __name__ == "__main__":

swarms/structs/csv_to_agent.py

@@ -136,6 +136,7 @@ class AgentValidator:
                 str(e), str(e.__class__.__name__), str(config)
             )
 
+
 class AgentLoader:
     """Class to manage agents through CSV with type safety"""
 
@@ -202,7 +203,9 @@ class AgentLoader:
         elif file_type == "json":
             return self._load_agents_from_json()
         else:
-            raise ValueError("Unsupported file type. Use 'csv' or 'json'.")
+            raise ValueError(
+                "Unsupported file type. Use 'csv' or 'json'."
+            )
 
     def _load_agents_from_csv(self) -> List[Agent]:
         """Load agents from a CSV file"""
@@ -229,13 +232,13 @@ class AgentLoader:
         """Load agents from a JSON file"""
         import json
 
-        if not self.csv_path.with_suffix('.json').exists():
+        if not self.csv_path.with_suffix(".json").exists():
             raise FileNotFoundError(
                 f"JSON file not found at {self.csv_path.with_suffix('.json')}"
             )
 
         agents: List[Agent] = []
-        with open(self.csv_path.with_suffix('.json'), "r") as f:
+        with open(self.csv_path.with_suffix(".json"), "r") as f:
             agents_data = json.load(f)
             for agent in agents_data:
                 try:
@@ -250,10 +253,14 @@ class AgentLoader:
                     )
                     continue
 
-        print(f"Loaded {len(agents)} agents from {self.csv_path.with_suffix('.json')}")
+        print(
+            f"Loaded {len(agents)} agents from {self.csv_path.with_suffix('.json')}"
+        )
         return agents
 
-    def _create_agent(self, validated_config: AgentConfigDict) -> Agent:
+    def _create_agent(
+        self, validated_config: AgentConfigDict
+    ) -> Agent:
         """Create an Agent instance from validated configuration"""
         return Agent(
             agent_name=validated_config["agent_name"],
@@ -263,7 +270,9 @@ class AgentLoader:
             autosave=validated_config["autosave"],
             dashboard=validated_config["dashboard"],
             verbose=validated_config["verbose"],
-            dynamic_temperature_enabled=validated_config["dynamic_temperature"],
+            dynamic_temperature_enabled=validated_config[
+                "dynamic_temperature"
+            ],
             saved_state_path=validated_config["saved_state_path"],
             user_name=validated_config["user_name"],
             retry_attempts=validated_config["retry_attempts"],

swarms/telemetry/bootup.py

@@ -54,7 +54,3 @@ def bootup():
     except Exception as e:
         logger.error(f"Error during bootup: {str(e)}")
         raise
-
-
-# Run bootup
-bootup()