[BUFG][CLEANUP]]

LICENSE

@@ -1,6 +1,5 @@
 
-
-# Creative Commons Attribution 4.0 International Public License
+Creative Commons Attribution 4.0 International Public License
 
 By exercising the Licensed Rights (defined below), You accept and agree
 to be bound by the terms and conditions of this Creative Commons

README.md

@@ -213,6 +213,52 @@ print(out)
 ```
 
 
+# `Agent` with Long Term Memory ++ Tools!
+An LLM equipped with long term memory and tools, a full stack agent capable of automating all and any digital tasks given a good prompt.
+
+```python
+from swarms import Agent, ChromaDB, OpenAIChat, tool
+
+# Making an instance of the ChromaDB class
+memory = ChromaDB(
+    metric="cosine",
+    n_results=3,
+    output_dir="results",
+    docs_folder="docs",
+)
+
+# Initialize a tool
+@tool
+def search_api(query: str):
+    # Add your logic here
+    return query
+
+# Initializing the agent with the Gemini instance and other parameters
+agent = Agent(
+    agent_name="Covid-19-Chat",
+    agent_description=(
+        "This agent provides information about COVID-19 symptoms."
+    ),
+    llm=OpenAIChat(),
+    max_loops="auto",
+    autosave=True,
+    verbose=True,
+    long_term_memory=memory,
+    stopping_condition="finish",
+    tools=[search_api],
+)
+
+# Defining the task and image path
+task = ("What are the symptoms of COVID-19?",)
+
+# Running the agent with the specified task and image
+out = agent.run(task)
+print(out)
+
+```
+
+
+
 
 
 
@@ -873,6 +919,10 @@ agent = Agent(
 # Run the workflow on a task
 agent.run(task=task, img=img)
 ```
+----
+
+
+## Build your own LLMs, Agents, and Swarms!
 
 ### Swarms Compliant Model Interface
 ```python
@@ -935,6 +985,16 @@ agent = MyCustomAgent()
 out = agent("Analyze and summarize these financial documents: ")
 print(out)
 
+```
+
+
+### Compliant Interface for Multi-Agent Collaboration
+
+```python
+from swarms import Agent, AbstractSwarm
+
+
+
 ```
 
 ---

pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "swarms"
-version = "4.6.1"
+version = "4.6.7"
 description = "Swarms - Pytorch"
 license = "MIT"
 authors = ["Kye Gomez <[email protected]>"]

swarms/__init__.py

@@ -11,12 +11,10 @@
 
 from swarms.agents import *  # noqa: E402, F403
 from swarms.artifacts import *  # noqa: E402, F403
-from swarms.chunkers import *  # noqa: E402, F403
 from swarms.memory import *  # noqa: E402, F403
 from swarms.models import *  # noqa: E402, F403
 from swarms.prompts import *  # noqa: E402, F403
 from swarms.structs import *  # noqa: E402, F403
 from swarms.telemetry import *  # noqa: E402, F403
 from swarms.tools import *  # noqa: E402, F403
-from swarms.utils import *  # noqa: E402, F403
-from swarms.schedulers import *  # noqa: E402, F403
+from swarms.utils import *  # noqa: E402, F403

swarms/artifacts/text_artifact.py

@@ -1,9 +1,8 @@
 from __future__ import annotations
 
 from dataclasses import dataclass, field
-
+from typing import Callable
 from swarms.artifacts.base_artifact import BaseArtifact
-from swarms.tokenizers.base_tokenizer import BaseTokenizer
 
 
 @dataclass
@@ -31,6 +30,7 @@ class TextArtifact(BaseArtifact):
     value: str
     encoding: str = "utf-8"
     encoding_error_handler: str = "strict"
+    tokenizer: Callable = None
     _embedding: list[float] = field(default_factory=list)
 
     @property
@@ -49,8 +49,8 @@ def generate_embedding(self, model) -> list[float] | None:
 
         return self.embedding
 
-    def token_count(self, tokenizer: BaseTokenizer) -> int:
-        return tokenizer.count_tokens(str(self.value))
+    def token_count(self) -> int:
+        return self.tokenizer.count_tokens(str(self.value))
 
     def to_bytes(self) -> bytes:
         return self.value.encode(

swarms/models/__init__.py

@@ -38,7 +38,7 @@
     ReplicateLLM as Replicate,
 )
 from swarms.models.qwen import QwenVLMultiModal  # noqa: E402
-from swarms.models.sam_supervision import SegmentAnythingMarkGenerator
+# from swarms.models.sam_supervision import SegmentAnythingMarkGenerator
 from swarms.models.sampling_params import SamplingParams, SamplingType
 from swarms.models.together import TogetherLLM  # noqa: E402
 from swarms.models.types import (  # noqa: E402
@@ -79,7 +79,6 @@
     "Replicate",
     "SamplingParams",
     "SamplingType",
-    "SegmentAnythingMarkGenerator",
     "TextModality",
     "TogetherLLM",
     "Vilt",

swarms/models/base_embedding_model.py

@@ -4,11 +4,8 @@
 from dataclasses import dataclass, field
 
 import numpy as np
-
+from typing import Callable
 from swarms.artifacts.text_artifact import TextArtifact
-from swarms.chunkers.base_chunker import BaseChunker
-from swarms.chunkers.text_chunker import TextChunker
-from swarms.tokenizers.base_tokenizer import BaseTokenizer
 from swarms.utils.exponential_backoff import ExponentialBackoffMixin
 
 
@@ -25,12 +22,8 @@ class BaseEmbeddingModel(
     """
 
     model: str = None
-    tokenizer: BaseTokenizer | None = None
-    chunker: BaseChunker = field(init=False)
-
-    def __post_init__(self) -> None:
-        if self.tokenizer:
-            self.chunker = TextChunker(tokenizer=self.tokenizer)
+    tokenizer: Callable = None
+    chunker: Callable = None
 
     def embed_text_artifact(
         self, artifact: TextArtifact

swarms/models/sam_supervision.py

@@ -1,5 +1,4 @@
-from typing import Optional
-
+from typing import Optional, Callable
 import cv2
 import numpy as np
 import supervision as sv
@@ -12,7 +11,6 @@
 )
 
 from swarms.models.base_multimodal_model import BaseMultiModalModel
-from swarms.utils.supervision_masking import masks_to_marks
 
 
 class SegmentAnythingMarkGenerator(BaseMultiModalModel):
@@ -30,13 +28,15 @@ def __init__(
         device: str = "cpu",
         model_name: str = "facebook/sam-vit-huge",
         visualize_marks: bool = False,
+        masks_to_marks: Callable = sv.masks_to_marks,
         *args,
         **kwargs,
     ):
         super(SegmentAnythingMarkGenerator).__init__(*args, **kwargs)
         self.device = device
         self.model_name = model_name
         self.visualize_marks = visualize_marks
+        self.masks_to_marks = masks_to_marks
 
         self.model = SamModel.from_pretrained(
             model_name, *args, **kwargs
@@ -74,7 +74,7 @@ def __call__(
         if mask is None:
             outputs = self.pipeline(image, points_per_batch=64)
             masks = np.array(outputs["masks"])
-            return masks_to_marks(masks=masks)
+            return self.masks_to_marks(masks=masks)
         else:
             inputs = self.processor(image, return_tensors="pt").to(
                 self.device
@@ -112,6 +112,6 @@ def __call__(
                 )
                 masks.append(mask)
             masks = np.array(masks)
-            return masks_to_marks(masks=masks)
+            return self.masks_to_marks(masks=masks)
 
     # def visualize_img(self):

swarms/structs/__init__.py

@@ -69,7 +69,6 @@
     TaskQueueBase,
     synchronized_queue,
 )
-from swarms.structs.tool_json_schema import JSON
 from swarms.structs.utils import (
     detect_markdown,
     distribute_tasks,
@@ -80,39 +79,47 @@
     parse_tasks,
 )
 
+
+
 __all__ = [
     "Agent",
-    "SequentialWorkflow",
+    "AgentJob",
+    "AgentProcess",
+    "AgentProcessQueue",
+    "AutoSwarm",
+    "AutoSwarmRouter",
     "AutoScaler",
-    "Conversation",
-    "TaskInput",
-    "Artifact",
-    "ArtifactUpload",
-    "StepInput",
-    "SwarmNetwork",
-    "ModelParallelizer",
-    "MultiAgentCollaboration",
+    "BaseStructure",
     "AbstractSwarm",
-    "GroupChat",
-    "GroupChatManager",
-    "parse_tasks",
-    "find_agent_by_id",
-    "distribute_tasks",
-    "find_token_in_text",
-    "extract_key_from_json",
-    "extract_tokens_from_text",
-    "ConcurrentWorkflow",
-    "RecursiveWorkflow",
-    "NonlinearWorkflow",
     "BaseWorkflow",
-    "BaseStructure",
-    "detect_markdown",
-    "Task",
     "block",
+    "ConcurrentWorkflow",
+    "Conversation",
     "GraphWorkflow",
-    "Step",
-    "Plan",
+    "GroupChat",
+    "GroupChatManager",
+    "MajorityVoting",
+    "majority_voting",
+    "most_frequent",
+    "parse_code_completion",
     "Message",
+    "ModelParallelizer",
+    "MultiAgentCollaboration",
+    "MultiProcessWorkflow",
+    "MultiThreadedWorkflow",
+    "NonlinearWorkflow",
+    "Plan",
+    "RecursiveWorkflow",
+    "Artifact",
+    "ArtifactUpload",
+    "StepInput",
+    "StepOutput",
+    "StepRequestBody",
+    "TaskInput",
+    "TaskRequestBody",
+    "SequentialWorkflow",
+    "Step",
+    "SwarmNetwork",
     "broadcast",
     "circular_swarm",
     "exponential_swarm",
@@ -131,21 +138,14 @@
     "sigmoid_swarm",
     "staircase_swarm",
     "star_swarm",
-    "StepOutput",
-    "StepRequestBody",
-    "TaskRequestBody",
-    "JSON",
-    "most_frequent",
-    "parse_code_completion",
-    "majority_voting",
-    "MajorityVoting",
-    "synchronized_queue",
+    "Task",
     "TaskQueueBase",
-    "MultiProcessWorkflow",
-    "MultiThreadedWorkflow",
-    "AgentJob",
-    "AutoSwarm",
-    "AutoSwarmRouter",
-    "AgentProcess",
-    "AgentProcessQueue",
-]
+    "synchronized_queue",
+    "detect_markdown",
+    "distribute_tasks",
+    "extract_key_from_json",
+    "extract_tokens_from_text",
+    "find_agent_by_id",
+    "find_token_in_text",
+    "parse_tasks",
+]

swarms/structs/agent.py

@@ -19,13 +19,11 @@
 )
 from swarms.prompts.worker_prompt import worker_tools_sop_promp
 from swarms.structs.conversation import Conversation
-from swarms.tokenizers.base_tokenizer import BaseTokenizer
 from swarms.tools.tool import BaseTool
 from swarms.utils.code_interpreter import SubprocessCodeInterpreter
 from swarms.utils.data_to_text import data_to_text
 from swarms.utils.parse_code import extract_code_from_markdown
 from swarms.utils.pdf_to_text import pdf_to_text
-from swarms.utils.token_count_tiktoken import limit_tokens_from_string
 
 
 # Utils
@@ -184,7 +182,7 @@ def __init__(
         multi_modal: Optional[bool] = None,
         pdf_path: Optional[str] = None,
         list_of_pdf: Optional[str] = None,
-        tokenizer: Optional[BaseTokenizer] = None,
+        tokenizer: Optional[Any] = None,
         long_term_memory: Optional[AbstractVectorDatabase] = None,
         preset_stopping_token: Optional[bool] = False,
         traceback: Any = None,
@@ -208,6 +206,7 @@ def __init__(
         sentiment_threshold: Optional[float] = None,
         custom_exit_command: Optional[str] = "exit",
         sentiment_analyzer: Optional[Callable] = None,
+        limit_tokens_from_string: Optional[Callable] = None,
         *args,
         **kwargs,
     ):
@@ -267,6 +266,7 @@ def __init__(
         self.sentiment_threshold = sentiment_threshold
         self.custom_exit_command = custom_exit_command
         self.sentiment_analyzer = sentiment_analyzer
+        self.limit_tokens_from_string = limit_tokens_from_string
 
         # The max_loops will be set dynamically if the dynamic_loop
         if self.dynamic_loops:
@@ -1262,7 +1262,7 @@ def pdf_chunker(self, text: str = None, num_limits: int = 1000):
             _type_: _description_
         """
         text = text or self.pdf_connector()
-        text = limit_tokens_from_string(text, num_limits)
+        text = self.limit_tokens_from_string(text, num_limits)
         return text
 
     def ingest_docs(self, docs: List[str], *args, **kwargs):