black and isort

tests/tools/test_tools.py

@@ -6,7 +6,7 @@
 from PIL import Image
 
 from vision_agent.tools import TOOLS, Tool, register_tool
-from vision_agent.tools.tools import BboxIoU, BoxDistance, SegArea, SegIoU, MaskDistance
+from vision_agent.tools.tools import BboxIoU, BoxDistance, MaskDistance, SegArea, SegIoU
 
 
 def test_bbox_iou():

vision_agent/agent/__init__.py

@@ -1,6 +1,6 @@
 from .agent import Agent
 from .agent_coder import AgentCoder
+from .automated_vision_agent import AutomatedVisionAgent
 from .easytool import EasyTool
 from .reflexion import Reflexion
 from .vision_agent import VisionAgent
-from .automated_vision_agent import AutomatedVisionAgent

vision_agent/agent/agent_coder.py

@@ -13,7 +13,6 @@
 
 from .agent_coder_prompts import DEBUG, FIX_BUG, PROGRAM, TEST, VISUAL_TEST
 
-
 IMPORT_HELPER = """
 import math
 import re

vision_agent/agent/automated_vision_agent.py

@@ -48,9 +48,13 @@ def write_plan(
  return plan["plan"]
 
 
-def write_code(user_req: str, subtask: str, tool_info: str, code: str, model: LLM) -> str:
+def write_code(
+ user_req: str, subtask: str, tool_info: str, code: str, model: LLM
+) -> str:
  prompt = CODE.format(
- context=USER_REQ_SUBTASK_CONTEXT.format(user_requirement=user_req, subtask=subtask),
+ context=USER_REQ_SUBTASK_CONTEXT.format(
+ user_requirement=user_req, subtask=subtask
+ ),
  tool_info=tool_info,
  code=code,
  )
@@ -62,9 +66,13 @@ def write_code(user_req: str, subtask: str, tool_info: str, code: str, model: LL
  return extract_code(code)
 
 
-def write_test(user_req: str, subtask: str, tool_info: str, code: str, model: LLM) -> str:
+def write_test(
+ user_req: str, subtask: str, tool_info: str, code: str, model: LLM
+) -> str:
  prompt = TEST.format(
- context=USER_REQ_SUBTASK_CONTEXT.format(user_requirement=user_req, subtask=subtask),
+ context=USER_REQ_SUBTASK_CONTEXT.format(
+ user_requirement=user_req, subtask=subtask
+ ),
  tool_info=tool_info,
  code=code,
  )
@@ -164,7 +172,9 @@ def run_plan(
  f"""
 {tabulate(tabular_data=[task], headers="keys", tablefmt="mixed_grid", maxcolwidths=_MAX_TABULATE_COL_WIDTH)}"""
  )
- tool_info = "\n".join([e["doc"] for e in tool_recommender.top_k(task["instruction"])])
+ tool_info = "\n".join(
+ [e["doc"] for e in tool_recommender.top_k(task["instruction"])]
+ )
  success, code, result, task_memory = write_and_exec_code(
  user_req,
  task["instruction"],

vision_agent/agent/vision_agent.py

@@ -8,15 +8,15 @@
 from PIL import Image
 from tabulate import tabulate
 
+from vision_agent.llm import LLM, OpenAILLM
+from vision_agent.lmm import LMM, OpenAILMM
+from vision_agent.tools import TOOLS
 from vision_agent.utils.image_utils import (
  convert_to_b64,
  overlay_bboxes,
  overlay_heat_map,
  overlay_masks,
 )
-from vision_agent.llm import LLM, OpenAILLM
-from vision_agent.lmm import LMM, OpenAILMM
-from vision_agent.tools import TOOLS
 
 from .agent import Agent
 from .easytool_prompts import (

vision_agent/tools/__init__.py

@@ -5,16 +5,16 @@
  TOOLS,
  BboxArea,
  BboxIoU,
- ObjectDistance,
  BoxDistance,
- MaskDistance,
  Crop,
  DINOv,
  ExtractFrames,
  GroundingDINO,
  GroundingSAM,
  ImageCaption,
  ImageQuestionAnswering,
+ MaskDistance,
+ ObjectDistance,
  SegArea,
  SegIoU,
  Tool,

vision_agent/tools/tools.py

@@ -11,6 +11,9 @@
 from PIL.Image import Image as ImageType
 from scipy.spatial import distance # type: ignore
 
+from vision_agent.lmm import OpenAILMM
+from vision_agent.tools.tool_utils import _send_inference_request
+from vision_agent.utils import extract_frames_from_video
 from vision_agent.utils.image_utils import (
  b64_to_pil,
  convert_to_b64,
@@ -19,9 +22,6 @@
  normalize_bbox,
  rle_decode,
 )
-from vision_agent.lmm import OpenAILMM
-from vision_agent.tools.tool_utils import _send_inference_request
-from vision_agent.utils import extract_frames_from_video
 
 _LOGGER = logging.getLogger(__name__)
 

vision_agent/tools/tools_v2.py

@@ -3,16 +3,16 @@
 import tempfile
 from importlib import resources
 from pathlib import Path
-from typing import Any, Callable, Dict, List, Union, Tuple
+from typing import Any, Callable, Dict, List, Tuple, Union
 
 import numpy as np
 import pandas as pd
 import requests
 from PIL import Image, ImageDraw, ImageFont
 
-from vision_agent.utils.image_utils import convert_to_b64, normalize_bbox, rle_decode
 from vision_agent.tools.tool_utils import _send_inference_request
 from vision_agent.utils import extract_frames_from_video
+from vision_agent.utils.image_utils import convert_to_b64, normalize_bbox, rle_decode
 
 COLORS = [
  (158, 218, 229),

vision_agent/utils/sim.py

@@ -1,5 +1,5 @@
 from pathlib import Path
-from typing import List, Optional, Sequence, Union, Dict
+from typing import Dict, List, Optional, Sequence, Union
 
 import pandas as pd
 from openai import Client