file paths

swarms/agents/boss/boss_agent.py

@@ -0,0 +1,22 @@
+
+
+# ---------- Boss Node ----------
+class BossNode:
+    def __init__(self, llm, vectorstore, task_execution_chain, verbose, max_iterations):
+        self.llm = llm
+        self.vectorstore = vectorstore
+        self.task_execution_chain = task_execution_chain
+        self.verbose = verbose
+        self.max_iterations = max_iterations
+
+        self.baby_agi = BabyAGI.from_llm(
+            llm=self.llm,
+            vectorstore=self.vectorstore,
+            task_execution_chain=self.task_execution_chain
+        )
+
+    def create_task(self, objective):
+        return {"objective": objective}
+
+    def execute_task(self, task):
+        self.baby_agi(task)

swarms/agents/workers/auto_agent.py

@@ -32,8 +32,8 @@ from langchain.embeddings import OpenAIEmbeddings
 
 from langchain.tools.human.tool import HumanInputRun
 # from swarms.agents.workers.auto_agent import 
-from swarms.agents.workers.multi_modal import MultiModalVisualAgent
-from swarms.tools.main import Terminal, CodeWriter, CodeEditor, process_csv, WebpageQATool
+from agents.workers.multi_modal import MultiModalVisualAgent
+from tools.main import Terminal, CodeWriter, CodeEditor, process_csv, WebpageQATool
 
 class MultiModalVisualAgentTool(BaseTool):
     name = "multi_visual_agent"

swarms/agents/workers/worker_agent.py

@@ -0,0 +1,33 @@
+
+
+# ---------- Worker Node ----------
+# Define the input schema for the WorkerNode
+class WorkerNodeInput(BaseModel):
+    llm: Any = Field(description="Language model")
+    tools: List[Tool] = Field(description="List of tools")
+    vectorstore: VectorStore = Field(description="Vector store")
+
+@tool("WorkerNode", args_schema=WorkerNodeInput)
+class WorkerNode:
+    """Useful for when you need to spawn an autonomous agent instance as a worker to accomplish complex tasks, it can search the internet or spawn child multi-modality models to process and generate images and text or audio and so on """
+    def __init__(self, llm, tools, vectorstore):
+        self.llm = llm
+        self.tools = tools
+        self.vectorstore = vectorstore
+
+    def create_agent(self, ai_name, ai_role, human_in_the_loop, search_kwargs):
+        self.agent = AutoGPT.from_llm_and_tools(
+            ai_name=ai_name,
+            ai_role=ai_role,
+            tools=tools,
+            llm=self.llm,
+            memory=self.vectorstore.as_retriever(search_kwargs=search_kwargs),
+            human_in_the_loop=human_in_the_loop,
+        )
+        self.agent.chain.verbose = True
+
+    def run_agent(self, prompt):
+        tree_of_thoughts_prompt = """
+        Imagine three different experts are answering this question. All experts will write down each chain of thought of each step of their thinking, then share it with the group. Then all experts will go on to the next step, etc. If any expert realises they're wrong at any point then they leave. The question is...
+        """
+        self.agent.run([f"{tree_of_thoughts_prompt} {prompt}"])

swarms/utils/ansi.py

@@ -1,112 +0,0 @@
-class Code:
-    def __init__(self, value: int):
-        self.value = value
-
-    def __str__(self):
-        return "%d" % self.value
-
-
-class Color(Code):
-    def bg(self) -> "Color":
-        self.value += 10
-        return self
-
-    def bright(self) -> "Color":
-        self.value += 60
-        return self
-
-    @staticmethod
-    def black() -> "Color":
-        return Color(30)
-
-    @staticmethod
-    def red() -> "Color":
-        return Color(31)
-
-    @staticmethod
-    def green() -> "Color":
-        return Color(32)
-
-    @staticmethod
-    def yellow() -> "Color":
-        return Color(33)
-
-    @staticmethod
-    def blue() -> "Color":
-        return Color(34)
-
-    @staticmethod
-    def magenta() -> "Color":
-        return Color(35)
-
-    @staticmethod
-    def cyan() -> "Color":
-        return Color(36)
-
-    @staticmethod
-    def white() -> "Color":
-        return Color(37)
-
-    @staticmethod
-    def default() -> "Color":
-        return Color(39)
-
-
-class Style(Code):
-    @staticmethod
-    def reset() -> "Style":
-        return Style(0)
-
-    @staticmethod
-    def bold() -> "Style":
-        return Style(1)
-
-    @staticmethod
-    def dim() -> "Style":
-        return Style(2)
-
-    @staticmethod
-    def italic() -> "Style":
-        return Style(3)
-
-    @staticmethod
-    def underline() -> "Style":
-        return Style(4)
-
-    @staticmethod
-    def blink() -> "Style":
-        return Style(5)
-
-    @staticmethod
-    def reverse() -> "Style":
-        return Style(7)
-
-    @staticmethod
-    def conceal() -> "Style":
-        return Style(8)
-
-
-class ANSI:
-    ESCAPE = "\x1b["
-    CLOSE = "m"
-
-    def __init__(self, text: str):
-        self.text = text
-        self.args = []
-
-    def join(self) -> str:
-        return ANSI.ESCAPE + ";".join([str(a) for a in self.args]) + ANSI.CLOSE
-
-    def wrap(self, text: str) -> str:
-        return self.join() + text + ANSI(Style.reset()).join()
-
-    def to(self, *args: str):
-        self.args = list(args)
-        return self.wrap(self.text)
-
-
-def dim_multiline(message: str) -> str:
-    lines = message.split("\n")
-    if len(lines) <= 1:
-        return lines[0]
-    return lines[0] + ANSI("\n... ".join([""] + lines[1:])).to(Color.black().bright())