code quality

Former-commit-id: 42ce6cf18c

apps/open-sourcerer/main.py

@@ -17,7 +17,7 @@ interpreter.api_key = os.getenv("OPENAI_API_KEY")
 
 def split_text(text, chunk_size=1500):
     #########################################################################
-    return [text[i:i + chunk_size] for i in range(0, len(text), chunk_size)]
+    return [text[i : i + chunk_size] for i in range(0, len(text), chunk_size)]
 
 
 # discord initial
@@ -32,7 +32,6 @@ model = whisper.load_model("base")
 
 
 def transcribe(audio):
-
     # load audio and pad/trim it to fit 30 seconds
     audio = whisper.load_audio(audio)
     audio = whisper.pad_or_trim(audio)
@@ -58,13 +57,16 @@ async def on_message(message):
     response = []
     for chunk in interpreter.chat(message.content, display=False, stream=False):
         # await message.channel.send(chunk)
-        if 'message' in chunk:
-            response.append(chunk['message'])
+        if "message" in chunk:
+            response.append(chunk["message"])
     last_response = response[-1]
 
     max_message_length = 2000  # Discord's max message length is 2000 characters
     # Splitting the message into chunks of 2000 characters
-    response_chunks = [last_response[i:i + max_message_length] for i in range(0, len(last_response), max_message_length)]
+    response_chunks = [
+        last_response[i : i + max_message_length]
+        for i in range(0, len(last_response), max_message_length)
+    ]
     # Sending each chunk as a separate message
     for chunk in response_chunks:
         await message.channel.send(chunk)
@@ -74,9 +76,9 @@ async def on_message(message):
 async def join(ctx):
     if ctx.author.voice:
         channel = ctx.message.author.voice.channel
-        print('joining..')
+        print("joining..")
         await channel.connect()
-        print('joined.')
+        print("joined.")
     else:
         print("not in a voice channel!")
 
@@ -92,32 +94,32 @@ async def leave(ctx):
 @client.command()
 async def listen(ctx):
     if ctx.voice_client:
-        print('trying to listen..')
+        print("trying to listen..")
         ctx.voice_client.start_recording(discord.sinks.WaveSink(), callback, ctx)
-        print('listening..')
+        print("listening..")
     else:
         print("not in a voice channel!")
 
 
 async def callback(sink: discord.sinks, ctx):
-    print('in callback..')
+    print("in callback..")
     for user_id, audio in sink.audio_data.items():
         if user_id == ctx.author.id:
-            print('saving audio..')
+            print("saving audio..")
             audio: discord.sinks.core.AudioData = audio
             print(user_id)
             filename = "audio.wav"
             with open(filename, "wb") as f:
                 f.write(audio.file.getvalue())
-            print('audio saved.')
+            print("audio saved.")
             transcription = transcribe(filename)
             print(transcription)
             response = []
             for chunk in interpreter.chat(transcription, display=False, stream=True):
                 # await message.channel.send(chunk)
-                if 'message' in chunk:
-                    response.append(chunk['message'])
-            await ctx.message.channel.send(' '.join(response))
+                if "message" in chunk:
+                    response.append(chunk["message"])
+            await ctx.message.channel.send(" ".join(response))
 
 
 @client.command()
@@ -129,4 +131,5 @@ async def stop(ctx):
 async def on_ready():
     print(f"We have logged in as {client.user}")
 
+
 client.run(bot_token)

apps/open-sourcerer/voice.py

@@ -34,15 +34,13 @@ def get_audio_length(audio_bytes):
 
 def speak(text):
     speaking = True
-    audio = generate(
-        text=text,
-        voice="Daniel"
-    )
+    audio = generate(text=text, voice="Daniel")
     play(audio, notebook=True)
 
     audio_length = get_audio_length(audio)
     time.sleep(audio_length)
 
+
 # @title Text-only JARVIS
 # @markdown Run this cell for a ChatGPT-like interface.
 
@@ -55,13 +53,11 @@ with gr.Blocks() as demo:
         return "", history + [[user_message, None]]
 
     def bot(history):
-
         user_message = history[-1][0]
         history[-1][1] = ""
         active_block_type = ""
 
         for chunk in interpreter.chat(user_message, stream=True, display=False):
-
             # Message
             if "message" in chunk:
                 if active_block_type != "message":
@@ -96,6 +92,6 @@ with gr.Blocks() as demo:
         bot, chatbot, chatbot
     )
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     demo.queue()
     demo.launch(debug=True)

swarms/agents/__init__.py

@@ -5,6 +5,7 @@ from swarms.agents.stream_response import stream
 from swarms.agents.base import AbstractAgent
 from swarms.agents.registry import Registry
 from swarms.agents.idea_to_image_agent import Idea2Image
+
 """Agent Infrastructure, models, memory, utils, tools"""
 """Agent Infrastructure, models, memory, utils, tools"""
 

swarms/agents/meta_prompter.py

@@ -108,7 +108,7 @@ class MetaPrompterAgent:
     def get_new_instructions(self, meta_output):
         """Get New Instructions from the meta_output"""
         delimiter = "Instructions: "
-        new_instructions = meta_output[meta_output.find(delimiter) + len(delimiter):]
+        new_instructions = meta_output[meta_output.find(delimiter) + len(delimiter) :]
         return new_instructions
 
     def run(self, task: str):

swarms/agents/multi_modal_visual_agent.py

@@ -207,12 +207,12 @@ def blend_gt2pt(old_image, new_image, sigma=0.15, steps=100):
     kernel[steps:-steps, :steps] = left
     kernel[steps:-steps, -steps:] = right
 
-    pt_gt_img = easy_img[pos_h: pos_h + old_size[1], pos_w: pos_w + old_size[0]]
+    pt_gt_img = easy_img[pos_h : pos_h + old_size[1], pos_w : pos_w + old_size[0]]
     gaussian_gt_img = (
         kernel * gt_img_array + (1 - kernel) * pt_gt_img
     )  # gt img with blur img
     gaussian_gt_img = gaussian_gt_img.astype(np.int64)
-    easy_img[pos_h: pos_h + old_size[1], pos_w: pos_w + old_size[0]] = gaussian_gt_img
+    easy_img[pos_h : pos_h + old_size[1], pos_w : pos_w + old_size[0]] = gaussian_gt_img
     gaussian_img = Image.fromarray(easy_img)
     return gaussian_img
 

swarms/chunkers/base.py

@@ -58,7 +58,7 @@ class BaseChunker(ABC):
             half_token_count = token_count // 2
 
             if current_separator:
-                separators = self.separators[self.separators.index(current_separator):]
+                separators = self.separators[self.separators.index(current_separator) :]
             else:
                 separators = self.separators
 
@@ -84,7 +84,7 @@ class BaseChunker(ABC):
                             subchanks[: balance_index + 1]
                         )
                         second_subchunk = separator.value + separator.value.join(
-                            subchanks[balance_index + 1:]
+                            subchanks[balance_index + 1 :]
                         )
                     else:
                         first_subchunk = (
@@ -92,7 +92,7 @@ class BaseChunker(ABC):
                             + separator.value
                         )
                         second_subchunk = separator.value.join(
-                            subchanks[balance_index + 1:]
+                            subchanks[balance_index + 1 :]
                         )
 
                     first_subchunk_rec = self._chunk_recursively(

swarms/embeddings/openai.py

@@ -347,7 +347,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
                 disallowed_special=self.disallowed_special,
             )
             for j in range(0, len(token), self.embedding_ctx_length):
-                tokens.append(token[j: j + self.embedding_ctx_length])
+                tokens.append(token[j : j + self.embedding_ctx_length])
                 indices.append(i)
 
         batched_embeddings: List[List[float]] = []
@@ -366,7 +366,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
         for i in _iter:
             response = embed_with_retry(
                 self,
-                input=tokens[i: i + _chunk_size],
+                input=tokens[i : i + _chunk_size],
                 **self._invocation_params,
             )
             batched_embeddings.extend(r["embedding"] for r in response["data"])
@@ -428,7 +428,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
                 disallowed_special=self.disallowed_special,
             )
             for j in range(0, len(token), self.embedding_ctx_length):
-                tokens.append(token[j: j + self.embedding_ctx_length])
+                tokens.append(token[j : j + self.embedding_ctx_length])
                 indices.append(i)
 
         batched_embeddings: List[List[float]] = []
@@ -436,7 +436,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
         for i in range(0, len(tokens), _chunk_size):
             response = await async_embed_with_retry(
                 self,
-                input=tokens[i: i + _chunk_size],
+                input=tokens[i : i + _chunk_size],
                 **self._invocation_params,
             )
             batched_embeddings.extend(r["embedding"] for r in response["data"])

swarms/models/bing_chat.py

@@ -28,14 +28,22 @@ class BingChat:
         self.cookies = json.loads(open(cookies_path, encoding="utf-8").read())
         self.bot = asyncio.run(Chatbot.create(cookies=self.cookies))
 
-    def __call__(self, prompt: str, style: ConversationStyle = ConversationStyle.creative) -> str:
+    def __call__(
+        self, prompt: str, style: ConversationStyle = ConversationStyle.creative
+    ) -> str:
         """
         Get a text response using the EdgeGPT model based on the provided prompt.
         """
-        response = asyncio.run(self.bot.ask(prompt=prompt, conversation_style=style, simplify_response=True))
-        return response['text']
+        response = asyncio.run(
+            self.bot.ask(
+                prompt=prompt, conversation_style=style, simplify_response=True
+            )
+        )
+        return response["text"]
 
-    def create_img(self, prompt: str, output_dir: str = "./output", auth_cookie: str = None) -> str:
+    def create_img(
+        self, prompt: str, output_dir: str = "./output", auth_cookie: str = None
+    ) -> str:
         """
         Generate an image based on the provided prompt and save it in the given output directory.
         Returns the path of the generated image.
@@ -47,7 +55,7 @@ class BingChat:
         images = image_generator.get_images(prompt)
         image_generator.save_images(images, output_dir=output_dir)
 
-        return Path(output_dir) / images[0]['path']
+        return Path(output_dir) / images[0]["path"]
 
     @staticmethod
     def set_cookie_dir_path(path: str):

swarms/models/chat_openai.py

@@ -458,7 +458,7 @@ class BaseOpenAI(BaseLLM):
                 )
             params["max_tokens"] = self.max_tokens_for_prompt(prompts[0])
         sub_prompts = [
-            prompts[i: i + self.batch_size]
+            prompts[i : i + self.batch_size]
             for i in range(0, len(prompts), self.batch_size)
         ]
         return sub_prompts
@@ -469,7 +469,7 @@ class BaseOpenAI(BaseLLM):
         """Create the LLMResult from the choices and prompts."""
         generations = []
         for i, _ in enumerate(prompts):
-            sub_choices = choices[i * self.n: (i + 1) * self.n]
+            sub_choices = choices[i * self.n : (i + 1) * self.n]
             generations.append(
                 [
                     Generation(

swarms/models/openai_models.py

@@ -462,7 +462,7 @@ class BaseOpenAI(BaseLLM):
                 )
             params["max_tokens"] = self.max_tokens_for_prompt(prompts[0])
         sub_prompts = [
-            prompts[i: i + self.batch_size]
+            prompts[i : i + self.batch_size]
             for i in range(0, len(prompts), self.batch_size)
         ]
         return sub_prompts
@@ -473,7 +473,7 @@ class BaseOpenAI(BaseLLM):
         """Create the LLMResult from the choices and prompts."""
         generations = []
         for i, _ in enumerate(prompts):
-            sub_choices = choices[i * self.n: (i + 1) * self.n]
+            sub_choices = choices[i * self.n : (i + 1) * self.n]
             generations.append(
                 [
                     Generation(

swarms/models/vilt.py

@@ -35,8 +35,6 @@ class Vilt:
 
 
         Args:
-        text: str
-
 
         """
         # Download the image

swarms/tools/autogpt.py

@@ -125,7 +125,7 @@ class WebpageQATool(BaseTool):
         results = []
         # TODO: Handle this with a MapReduceChain
         for i in range(0, len(web_docs), 4):
-            input_docs = web_docs[i: i + 4]
+            input_docs = web_docs[i : i + 4]
             window_result = self.qa_chain(
                 {"input_documents": input_docs, "question": question},
                 return_only_outputs=True,

swarms/tools/developer.py

@@ -306,7 +306,7 @@ class WriteCommand:
     @staticmethod
     def from_str(command: str) -> "WriteCommand":
         filepath = command.split(WriteCommand.separator)[0]
-        return WriteCommand(filepath, command[len(filepath) + 1:])
+        return WriteCommand(filepath, command[len(filepath) + 1 :])
 
 
 class CodeWriter:
@@ -433,7 +433,7 @@ class ReadCommand:
         if self.start == self.end:
             code = code[self.start - 1]
         else:
-            code = "".join(code[self.start - 1: self.end])
+            code = "".join(code[self.start - 1 : self.end])
         return code
 
     @staticmethod
@@ -590,9 +590,9 @@ class PatchCommand:
         lines[self.start.line] = (
             lines[self.start.line][: self.start.col]
             + self.content
-            + lines[self.end.line][self.end.col:]
+            + lines[self.end.line][self.end.col :]
         )
-        lines = lines[: self.start.line + 1] + lines[self.end.line + 1:]
+        lines = lines[: self.start.line + 1] + lines[self.end.line + 1 :]
 
         after = self.write_lines(lines)
 

swarms/tools/tool.py

@@ -851,5 +851,3 @@ def tool(
         return _partial
     else:
         raise ValueError("Too many arguments for tool decorator")
-
-

swarms/utils/main.py

@@ -365,7 +365,7 @@ class FileHandler:
         try:
             if url.startswith(os.environ.get("SERVER", "http://localhost:8000")):
                 local_filepath = url[
-                    len(os.environ.get("SERVER", "http://localhost:8000")) + 1:
+                    len(os.environ.get("SERVER", "http://localhost:8000")) + 1 :
                 ]
                 local_filename = Path("file") / local_filepath.split("/")[-1]
                 src = self.path / local_filepath

tests/orchestrate.py

@@ -1,68 +0,0 @@
-import pytest
-from unittest.mock import Mock
-from swarms.swarms.orchestrate import Orchestrator
-
-
-@pytest.fixture
-def mock_agent():
-    return Mock()
-
-
-@pytest.fixture
-def mock_task():
-    return {"task_id": 1, "task_data": "data"}
-
-
-@pytest.fixture
-def mock_vector_db():
-    return Mock()
-
-
-@pytest.fixture
-def orchestrator(mock_agent, mock_vector_db):
-    agent_list = [mock_agent for _ in range(5)]
-    task_queue = []
-    return Orchestrator(mock_agent, agent_list, task_queue, mock_vector_db)
-
-
-def test_assign_task(orchestrator, mock_agent, mock_task, mock_vector_db):
-    orchestrator.task_queue.append(mock_task)
-    orchestrator.assign_task(0, mock_task)
-
-    mock_agent.process_task.assert_called_once()
-    mock_vector_db.add_documents.assert_called_once()
-
-
-def test_retrieve_results(orchestrator, mock_vector_db):
-    mock_vector_db.query.return_value = "expected_result"
-    assert orchestrator.retrieve_results(0) == "expected_result"
-
-
-def test_update_vector_db(orchestrator, mock_vector_db):
-    data = {"vector": [0.1, 0.2, 0.3], "task_id": 1}
-    orchestrator.update_vector_db(data)
-    mock_vector_db.add_documents.assert_called_once_with(
-        [data["vector"]], [str(data["task_id"])]
-    )
-
-
-def test_get_vector_db(orchestrator, mock_vector_db):
-    assert orchestrator.get_vector_db() == mock_vector_db
-
-
-def test_append_to_db(orchestrator, mock_vector_db):
-    collection = "test_collection"
-    result = "test_result"
-    orchestrator.append_to_db(collection, result)
-    mock_vector_db.append_document.assert_called_once_with(
-        collection, result, id=str(id(result))
-    )
-
-
-def test_run(orchestrator, mock_agent, mock_vector_db):
-    objective = "test_objective"
-    collection = "test_collection"
-    orchestrator.run(objective, collection)
-
-    mock_agent.process_task.assert_called()
-    mock_vector_db.append_document.assert_called()

tests/swarms/orchestrate.py

@@ -1,71 +1,68 @@
-import numpy as np
-from swarms.swarms.orchestrate import Orchestrator, Worker
-import chromadb
+import pytest
+from unittest.mock import Mock
+from swarms.swarms.orchestrate import Orchestrator
 
 
-def test_orchestrator_initialization():
-    orchestrator = Orchestrator(agent=Worker, agent_list=[Worker] * 5, task_queue=[])
-    assert isinstance(orchestrator, Orchestrator)
-    assert orchestrator.agents.qsize() == 5
-    assert orchestrator.task_queue.qsize() == 0
+@pytest.fixture
+def mock_agent():
+    return Mock()
 
 
-def test_orchestrator_assign_task():
-    orchestrator = Orchestrator(agent=Worker, agent_list=[Worker] * 5, task_queue=[])
-    orchestrator.assign_task(1, {"content": "task1"})
-    assert orchestrator.task_queue.qsize() == 1
+@pytest.fixture
+def mock_task():
+    return {"task_id": 1, "task_data": "data"}
 
 
-def test_orchestrator_embed():
-    orchestrator = Orchestrator(agent=Worker, agent_list=[Worker] * 5, task_queue=[])
-    result = orchestrator.embed("Hello, world!", "api_key", "model_name")
-    assert isinstance(result, np.ndarray)
+@pytest.fixture
+def mock_vector_db():
+    return Mock()
 
 
-def test_orchestrator_retrieve_results():
-    orchestrator = Orchestrator(agent=Worker, agent_list=[Worker] * 5, task_queue=[])
-    result = orchestrator.retrieve_results(1)
-    assert isinstance(result, list)
+@pytest.fixture
+def orchestrator(mock_agent, mock_vector_db):
+    agent_list = [mock_agent for _ in range(5)]
+    task_queue = []
+    return Orchestrator(mock_agent, agent_list, task_queue, mock_vector_db)
 
 
-def test_orchestrator_update_vector_db():
-    orchestrator = Orchestrator(agent=Worker, agent_list=[Worker] * 5, task_queue=[])
-    data = {"vector": np.array([1, 2, 3]), "task_id": 1}
-    orchestrator.update_vector_db(data)
-    assert orchestrator.collection.count() == 1
+def test_assign_task(orchestrator, mock_agent, mock_task, mock_vector_db):
+    orchestrator.task_queue.append(mock_task)
+    orchestrator.assign_task(0, mock_task)
 
+    mock_agent.process_task.assert_called_once()
+    mock_vector_db.add_documents.assert_called_once()
 
-def test_orchestrator_get_vector_db():
-    orchestrator = Orchestrator(agent=Worker, agent_list=[Worker] * 5, task_queue=[])
-    result = orchestrator.get_vector_db()
-    assert isinstance(result, chromadb.Collection)
 
+def test_retrieve_results(orchestrator, mock_vector_db):
+    mock_vector_db.query.return_value = "expected_result"
+    assert orchestrator.retrieve_results(0) == "expected_result"
 
-def test_orchestrator_append_to_db():
-    orchestrator = Orchestrator(agent=Worker, agent_list=[Worker] * 5, task_queue=[])
-    orchestrator.append_to_db("Hello, world!")
-    assert orchestrator.collection.count() == 1
 
+def test_update_vector_db(orchestrator, mock_vector_db):
+    data = {"vector": [0.1, 0.2, 0.3], "task_id": 1}
+    orchestrator.update_vector_db(data)
+    mock_vector_db.add_documents.assert_called_once_with(
+        [data["vector"]], [str(data["task_id"])]
+    )
 
-def test_orchestrator_run():
-    orchestrator = Orchestrator(agent=Worker, agent_list=[Worker] * 5, task_queue=[])
-    result = orchestrator.run("Write a short story.")
-    assert isinstance(result, list)
 
+def test_get_vector_db(orchestrator, mock_vector_db):
+    assert orchestrator.get_vector_db() == mock_vector_db
 
-def test_orchestrator_chat():
-    orchestrator = Orchestrator(agent=Worker, agent_list=[Worker] * 5, task_queue=[])
-    orchestrator.chat(1, 2, "Hello, Agent 2!")
-    assert orchestrator.collection.count() == 1
 
+def test_append_to_db(orchestrator, mock_vector_db):
+    collection = "test_collection"
+    result = "test_result"
+    orchestrator.append_to_db(collection, result)
+    mock_vector_db.append_document.assert_called_once_with(
+        collection, result, id=str(id(result))
+    )
 
-def test_orchestrator_add_agents():
-    orchestrator = Orchestrator(agent=Worker, agent_list=[Worker] * 5, task_queue=[])
-    orchestrator.add_agents(5)
-    assert orchestrator.agents.qsize() == 10
 
+def test_run(orchestrator, mock_agent, mock_vector_db):
+    objective = "test_objective"
+    collection = "test_collection"
+    orchestrator.run(objective, collection)
 
-def test_orchestrator_remove_agents():
-    orchestrator = Orchestrator(agent=Worker, agent_list=[Worker] * 5, task_queue=[])
-    orchestrator.remove_agents(3)
-    assert orchestrator.agents.qsize() == 2
+    mock_agent.process_task.assert_called()
+    mock_vector_db.append_document.assert_called()