[CLEANUP]

playground/creation_engine/omni_model_agent.py

@@ -0,0 +1,82 @@
+from swarms import Agent, Anthropic, tool
+
+# Model
+llm = Anthropic(
+    temperature=0.1,
+)
+
+
+# Tools
+@tool
+def text_to_video(task: str):
+    """
+    Converts a given text task into an animated video.
+
+    Args:
+        task (str): The text task to be converted into a video.
+
+    Returns:
+        str: The path to the exported GIF file.
+    """
+    import torch
+    from diffusers import (
+        AnimateDiffPipeline,
+        MotionAdapter,
+        EulerDiscreteScheduler,
+    )
+    from diffusers.utils import export_to_gif
+    from huggingface_hub import hf_hub_download
+    from safetensors.torch import load_file
+
+    device = "cuda"
+    dtype = torch.float16
+
+    step = 4  # Options: [1,2,4,8]
+    repo = "ByteDance/AnimateDiff-Lightning"
+    ckpt = f"animatediff_lightning_{step}step_diffusers.safetensors"
+    base = (  # Choose to your favorite base model.
+        "emilianJR/epiCRealism"
+    )
+
+    adapter = MotionAdapter().to(device, dtype)
+    adapter.load_state_dict(
+        load_file(hf_hub_download(repo, ckpt), device=device)
+    )
+    pipe = AnimateDiffPipeline.from_pretrained(
+        base, motion_adapter=adapter, torch_dtype=dtype
+    ).to(device)
+    pipe.scheduler = EulerDiscreteScheduler.from_config(
+        pipe.scheduler.config,
+        timestep_spacing="trailing",
+        beta_schedule="linear",
+    )
+
+    output = pipe(
+        prompt=task, guidance_scale=1.0, num_inference_steps=step
+    )
+    out = export_to_gif(output.frames[0], "animation.gif")
+    return out
+
+
+# Agent
+agent = Agent(
+    agent_name="Devin",
+    system_prompt=(
+        "Autonomous agent that can interact with humans and other"
+        " agents. Be Helpful and Kind. Use the tools provided to"
+        " assist the user. Return all code in markdown format."
+    ),
+    llm=llm,
+    max_loops="auto",
+    autosave=True,
+    dashboard=False,
+    streaming_on=True,
+    verbose=True,
+    stopping_token="<DONE>",
+    interactive=True,
+    tools=[text_to_video],
+)
+
+# Run the agent
+out = agent("Create a vide of a girl coding AI wearing hijab")
+print(out)

pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "swarms"
-version = "4.8.1"
+version = "4.8.2"
 description = "Swarms - Pytorch"
 license = "MIT"
 authors = ["Kye Gomez <kye@apac.ai>"]

scripts/log_cleanup.py

@@ -2,8 +2,8 @@ import os
 import shutil
 
 # Create a new directory for the log files if it doesn't exist
-if not os.path.exists("artifacts"):
+if not os.path.exists("artifacts_two"):
-    os.makedirs("artifacts")
+    os.makedirs("artifacts_two")
 
 # Walk through the current directory
 for dirpath, dirnames, filenames in os.walk("."):
@@ -12,10 +12,10 @@ for dirpath, dirnames, filenames in os.walk("."):
         if filename.endswith(".log"):
             # Construct the full file path
             file_path = os.path.join(dirpath, filename)
-            # Move the log file to the 'artifacts' directory
+            # Move the log file to the 'artifacts_two' directory
-            shutil.move(file_path, "artifacts")
+            shutil.move(file_path, "artifacts_two")
 
 print(
-    "Moved all log files into the 'artifacts' directory and deleted"
+    "Moved all log files into the 'artifacts_two' directory and"
-    " their original location."
+    " deleted their original location."
 )

scripts/log_cleanup.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+# Create the new directory if it doesn't exist
+sudo mkdir -p /artifacts_logs
+
+# Find all .log files in the root directory and its subdirectories
+find / -name "*.log" -print0 | while IFS= read -r -d '' file; do
+    # Use sudo to move the file to the new directory
+    sudo mv "$file" /artifacts_logs/
+done

swarms/models/open_router.py

@@ -0,0 +1,75 @@
+from swarms.models.base_llm import AbstractLLM
+from pydantic import BaseModel
+from typing import List, Dict
+import openai
+
+
+class OpenRouterRequest(BaseModel):
+    model: str
+    messages: List[Dict[str, str]] = []
+
+
+class OpenRouterChat(AbstractLLM):
+    """
+    A class representing an OpenRouter chat model.
+
+    Args:
+        model_name (str): The name of the OpenRouter model.
+        base_url (str, optional): The base URL for the OpenRouter API. Defaults to "https://openrouter.ai/api/v1/chat/completions".
+        openrouter_api_key (str, optional): The API key for accessing the OpenRouter API. Defaults to None.
+        system_prompt (str, optional): The system prompt for the chat model. Defaults to None.
+        *args: Variable length argument list.
+        **kwargs: Arbitrary keyword arguments.
+
+    Attributes:
+        model_name (str): The name of the OpenRouter model.
+        base_url (str): The base URL for the OpenRouter API.
+        openrouter_api_key (str): The API key for accessing the OpenRouter API.
+        system_prompt (str): The system prompt for the chat model.
+
+    Methods:
+        run(task, *args, **kwargs): Runs the chat model with the given task.
+
+    """
+
+    def __init__(
+        self,
+        model_name: str,
+        base_url: str = "https://openrouter.ai/api/v1/chat/completions",
+        openrouter_api_key: str = None,
+        system_prompt: str = None,
+        *args,
+        **kwargs,
+    ):
+        super().__init__(*args, **kwargs)
+        self.model_name = model_name
+        self.base_url = base_url
+        self.openrouter_api_key = openrouter_api_key
+        self.system_prompt = system_prompt
+
+        openai.api_base = "https://openrouter.ai/api/v1"
+        openai.api_key = openrouter_api_key
+
+    def run(self, task: str, *args, **kwargs) -> str:
+        """
+        Runs the chat model with the given task.
+
+        Args:
+            task (str): The user's task for the chat model.
+            *args: Variable length argument list.
+            **kwargs: Arbitrary keyword arguments.
+
+        Returns:
+            str: The response generated by the chat model.
+
+        """
+        response = openai.ChatCompletion.create(
+            model=self.model_name,
+            messages=[
+                {"role": "system", "content": self.system_prompt},
+                {"role": "user", "content": task},
+            ]
+            * args,
+            **kwargs,
+        )
+        return response.choices[0].message.text

swarms/structs/agent.py

@@ -614,7 +614,7 @@ class Agent:
                             else (task_prompt, img, *args)
                         )
                         response = self.llm(*response_args, **kwargs)
-                        print(response)
+                        # print(response)
                         self.short_memory.add(
                             role=self.agent_name, content=response
                         )
@@ -696,6 +696,11 @@ class Agent:
                                 content=sentiment,
                             )
 
+                        if self.streaming:
+                            self.streaming(response)
+                        else:
+                            print(response)
+
                         success = True  # Mark as successful to exit the retry loop
 
                     except Exception as e:

swarms/tools/exec_tool.py

@@ -9,6 +9,8 @@ from pydantic import ValidationError
 
 from swarms.tools.tool import BaseTool
 
+from swarms.utils.loguru_logger import logger
+
 
 class AgentAction(NamedTuple):
     """Action returned by AgentOutputParser."""
@@ -97,6 +99,9 @@ def execute_tool_by_name(
     # Get command name and arguments
     action = output_parser.parse(text)
     tools = {t.name: t for t in tools}
+
+    logger.info(f"Tools available: {tools}")
+
     if action.name == stop_token:
         return action.args["response"]
     if action.name in tools:
@@ -109,6 +114,7 @@ def execute_tool_by_name(
                 with concurrent.futures.ThreadPoolExecutor() as executor:
                     futures = []
                     for tool_name in tool_names:
+                        logger.info(f"Executing tool: {tool_name}")
                         futures.append(
                             executor.submit(
                                 tools[tool_name].run, action.args