[CLEANUP]

.env.example

@@ -2,4 +2,5 @@ OPENAI_API_KEY="your_openai_api_key"
 GROQ_API_KEY="your_groq_api_key"
 ANTHROPIC_API_KEY="your_anthropic_api_key"
 AZURE_OPENAI_API_KEY="your_azure_openai_api_key"
-# Additional keys
+# Additional keys
+WORKSPACE_DIR="agent_workspace"

.gitignore

@@ -12,6 +12,8 @@ __pycache__/
 .Python
 build/
 develop-eggs/
+agent_worpace
+agent_worpace
 dist/
 downloads/
 eggs/

README.md

@@ -139,6 +139,7 @@ Ready to streamline your API integrations and boost your application's performan
 | `LayoutLMDocumentQA`      | Model for document question answering.                |
 | `GPT4VisionAPI`           | Model for analyzing images with GPT-4 capabilities.  |
 | `LlamaForCausalLM`        | Causal language model from the Llama family.         |
+| `GroundedSAMTwo`          | Analyzes and track objects in images. GPU Only        |
 
 
 

examples/models/sam2_example.py

@@ -0,0 +1,16 @@
+from swarm_models.sam_two import GroundedSAMTwo
+from loguru import logger
+
+# Example usage:
+ontology = {"shipping container": "container"}
+runner = GroundedSAMTwo(ontology)
+
+# Run on a single image
+image_path = "path/to/your/image.jpg"
+json_output = runner.run(image_path, output_dir="annotated_images")
+logger.info("Annotation result: \n{}", json_output)
+
+# Run on a dataset (directory)
+image_dir = "path/to/your/dataset"
+json_output = runner.run(image_dir)
+logger.info("Dataset labeling result: \n{}", json_output)

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "swarm-models"
-version = "0.0.4"
+version = "0.0.7"
 description = "Swarm Models - Pytorch"
 license = "MIT"
 authors = ["Kye Gomez <[email protected]>"]

swarm_models/__init__.py

@@ -1,4 +1,3 @@
-from swarm_models.base_embedding_model import BaseEmbeddingModel
 from swarm_models.base_llm import BaseLLM  # noqa: E402
 from swarm_models.base_multimodal_model import BaseMultiModalModel
 from swarm_models.fuyu import Fuyu  # noqa: E402
@@ -29,7 +28,6 @@
 )
 from swarm_models.popular_llms import ReplicateChat as Replicate
 from swarm_models.qwen import QwenVLMultiModal  # noqa: E402
-from swarm_models.sampling_params import SamplingParams, SamplingType
 from swarm_models.together import TogetherLLM  # noqa: E402
 from swarm_models.model_types import (  # noqa: E402
     AudioModality,
@@ -42,9 +40,10 @@
 from swarm_models.popular_llms import FireWorksAI
 from swarm_models.openai_function_caller import OpenAIFunctionCaller
 from swarm_models.ollama_model import OllamaModel
+from swarm_models.sam_two import GroundedSAMTwo
+from swarm_models.utils import *  # NOQA
 
 __all__ = [
-    "BaseEmbeddingModel",
     "BaseLLM",
     "BaseMultiModalModel",
     "Fuyu",
@@ -65,8 +64,6 @@
     "OctoAIChat",
     "QwenVLMultiModal",
     "Replicate",
-    "SamplingParams",
-    "SamplingType",
     "TogetherLLM",
     "AudioModality",
     "ImageModality",
@@ -79,4 +76,5 @@
     "FireWorksAI",
     "OpenAIFunctionCaller",
     "OllamaModel",
+    "GroundedSAMTwo",
 ]

swarm_models/base_llm.py

@@ -4,10 +4,9 @@
 import time
 from abc import abstractmethod
 from typing import List, Optional
-from swarm_models.structs.base_structure import BaseStructure
 
 
-class BaseLLM(BaseStructure):
+class BaseLLM:
     """Abstract Language Model that defines the interface for all language models
 
     Args:

swarm_models/gpt4_vision_api.py

@@ -8,7 +8,7 @@
 import requests
 from dotenv import load_dotenv
 from termcolor import colored
-from swarm_models.utils.loguru_logger import logger
+from loguru import logger
 from swarm_models.base_multimodal_model import BaseMultiModalModel
 
 # Load environment variables

swarm_models/ollama_model.py

@@ -15,7 +15,7 @@
 class Message(BaseModel):
     role: str = Field(
         ...,
-        regex="^(user|system|assistant)$",
+        pattern="^(user|system|assistant)$",
         description="The role of the message sender.",
     )
     content: str = Field(

swarm_models/openai_function_caller.py

@@ -1,7 +1,7 @@
 import openai
 from pydantic import BaseModel
 import os
-from swarm_models.utils.loguru_logger import logger
+from loguru import logger
 from swarm_models.base_llm import BaseLLM
 from typing import List