vision-agent 0.2.229__py3-none-any.whl → 0.2.230__py3-none-any.whl

vision_agent-0.2.230.dist-info/METADATA

@@ -0,0 +1,156 @@
+Metadata-Version: 2.1
+Name: vision-agent
+Version: 0.2.230
+Summary: Toolset for Vision Agent
+Author: Landing AI
+Author-email: dev@landing.ai
+Requires-Python: >=3.9,<4.0
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Requires-Dist: anthropic (>=0.31.0,<0.32.0)
+Requires-Dist: av (>=11.0.0,<12.0.0)
+Requires-Dist: e2b (>=0.17.2a50,<0.18.0)
+Requires-Dist: e2b-code-interpreter (==0.0.11a37)
+Requires-Dist: flake8 (>=7.0.0,<8.0.0)
+Requires-Dist: ipykernel (>=6.29.4,<7.0.0)
+Requires-Dist: langsmith (>=0.1.58,<0.2.0)
+Requires-Dist: libcst (>=1.5.0,<2.0.0)
+Requires-Dist: matplotlib (>=3.9.2,<4.0.0)
+Requires-Dist: nbclient (>=0.10.0,<0.11.0)
+Requires-Dist: nbformat (>=5.10.4,<6.0.0)
+Requires-Dist: numpy (>=1.21.0,<2.0.0)
+Requires-Dist: openai (>=1.0.0,<2.0.0)
+Requires-Dist: opencv-python (>=4.0.0,<5.0.0)
+Requires-Dist: opentelemetry-api (>=1.29.0,<2.0.0)
+Requires-Dist: pandas (>=2.0.0,<3.0.0)
+Requires-Dist: pillow (>=10.0.0,<11.0.0)
+Requires-Dist: pillow-heif (>=0.16.0,<0.17.0)
+Requires-Dist: pydantic (==2.7.4)
+Requires-Dist: pydantic-settings (>=2.2.1,<3.0.0)
+Requires-Dist: pytube (==15.0.0)
+Requires-Dist: requests (>=2.0.0,<3.0.0)
+Requires-Dist: rich (>=13.7.1,<14.0.0)
+Requires-Dist: scikit-learn (>=1.5.2,<2.0.0)
+Requires-Dist: scipy (>=1.13.0,<1.14.0)
+Requires-Dist: tabulate (>=0.9.0,<0.10.0)
+Requires-Dist: tenacity (>=8.3.0,<9.0.0)
+Requires-Dist: tqdm (>=4.64.0,<5.0.0)
+Requires-Dist: typing_extensions (>=4.0.0,<5.0.0)
+Project-URL: Homepage, https://landing.ai
+Project-URL: documentation, https://github.com/landing-ai/vision-agent
+Project-URL: repository, https://github.com/landing-ai/vision-agent
+Description-Content-Type: text/markdown
+
+<div align="center">
+    <picture>
+        <source media="(prefers-color-scheme: dark)" srcset="https://github.com/landing-ai/vision-agent/blob/main/assets/logo_light.svg?raw=true">
+        <source media="(prefers-color-scheme: light)" srcset="https://github.com/landing-ai/vision-agent/blob/main/assets/logo_dark.svg?raw=true">
+        <img alt="VisionAgent" height="200px" src="https://github.com/landing-ai/vision-agent/blob/main/assets/logo_light.svg?raw=true">
+    </picture>
+
+[![](https://dcbadge.vercel.app/api/server/wPdN8RCYew?compact=true&style=flat)](https://discord.gg/wPdN8RCYew)
+![ci_status](https://github.com/landing-ai/vision-agent/actions/workflows/ci_cd.yml/badge.svg)
+[![PyPI version](https://badge.fury.io/py/vision-agent.svg)](https://badge.fury.io/py/vision-agent)
+![version](https://img.shields.io/pypi/pyversions/vision-agent)
+</div>
+
+## VisionAgent
+VisionAgent is a library that helps you utilize agent frameworks to generate code to
+solve your vision task. Check out our discord for updates and roadmaps! The fastest
+way to test out VisionAgent is to use our web application which you can find [here](https://va.landing.ai/).
+
+## Installation
+```bash
+pip install vision-agent
+```
+
+```bash
+export ANTHROPIC_API_KEY="your-api-key"
+export OPENAI_API_KEY="your-api-key"
+```
+
+---
+**NOTE**
+We found using both Anthropic Claude-3.5 and OpenAI o1 to be provide the best performance
+for VisionAgent. If you want to use a different LLM provider or only one, see
+'Using Other LLM Providers' below.
+---
+
+## Documentation
+
+[VisionAgent Library Docs](https://landing-ai.github.io/vision-agent/)
+
+## Examples
+### Counting cans in an image
+You can run VisionAgent in a local Jupyter Notebook [Counting cans in an image](https://github.com/landing-ai/vision-agent/blob/main/examples/notebooks/counting_cans.ipynb)
+
+### Generating code
+You can use VisionAgent to generate code to count the number of people in an image:
+```python
+from vision_agent.agent import VisionAgentCoderV2
+from vision_agent.agent.types import AgentMessage
+
+agent = VisionAgentCoderV2(verbose=True)
+code_context = agent.generate_code(
+    [
+        AgentMessage(
+            role="user",
+            content="Count the number of people in this image",
+            media=["people.png"]
+        )
+    ]
+)
+
+with open("generated_code.py", "w") as f:
+    f.write(code_context.code + "\n" + code_context.test)
+```
+
+### Using the tools directly
+VisionAgent produces code that utilizes our tools. You can also use the tools directly.
+For example if you wanted to detect people in an image and visualize the results:
+```python
+import vision_agent.tools as T
+import matplotlib.pyplot as plt
+
+image = T.load_image("people.png")
+dets = T.countgd_object_detection("person", image)
+# visualize the countgd bounding boxes on the image
+viz = T.overlay_bounding_boxes(image, dets)
+
+# save the visualization to a file
+T.save_image(viz, "people_detected.png")
+
+# display the visualization
+plt.imshow(viz)
+plt.show()
+```
+
+You can also use the tools for running on video files:
+```python
+import vision_agent.tools as T
+
+frames_and_ts = T.extract_frames_and_timestamps("people.mp4")
+# extract the frames from the frames_and_ts list
+frames = [f["frame"] for f in frames_and_ts]
+
+# run the countgd tracking on the frames
+tracks = T.countgd_sam2_video_tracking("person", frames)
+# visualize the countgd tracking results on the frames and save the video
+viz = T.overlay_segmentation_masks(frames, tracks)
+T.save_video(viz, "people_detected.mp4")
+```
+
+## Using Other LLM Providers
+You can use other LLM providers by changing `config.py` in the `vision_agent/configs`
+directory. For example to change to Anthropic simply just run:
+```bash
+cp vision_agent/configs/anthropic_config.py vision_agent/configs/config.py
+```
+
+**NOTE**
+VisionAgent moves fast and we are constantly updating and changing the library. If you
+have any questions or need help, please reach out to us on our discord channel.
+---
+

{vision_agent-0.2.229.dist-info → vision_agent-0.2.230.dist-info}/RECORD

@@ -1,37 +1,42 @@
-vision_agent/.sim_tools/df.csv,sha256=Vamicw8MiSGildK1r3-HXY4cKiq17GZxsgBsHbk7jpM,42158
+vision_agent/.sim_tools/df.csv,sha256=XdcgkjC7CjF_CoJnXmFkYOPUBwHemiwsauh62b1eh1M,42472
 vision_agent/.sim_tools/embs.npy,sha256=YJe8EcKVNmeX_75CS2T1sbY-sUS_1HQAMT-34zc18a0,254080
 vision_agent/__init__.py,sha256=EAb4-f9iyuEYkBrX4ag1syM8Syx8118_t0R6_C34M9w,57
 vision_agent/agent/README.md,sha256=Q4w7FWw38qaWosQYAZ7NqWx8Q5XzuWrlv7nLhjUd1-8,5527
 vision_agent/agent/__init__.py,sha256=M8CffavdIh8Zh-skznLHIaQkYGCGK7vk4dq1FaVkbs4,617
 vision_agent/agent/agent.py,sha256=_1tHWAs7Jm5tqDzEcPfCRvJV3uRRveyh4n9_9pd6I1w,1565
-vision_agent/agent/agent_utils.py,sha256=pP4u5tiami7C3ChgjgYLqJITnmkTI1_GsUj6g5czSRk,13994
+vision_agent/agent/agent_utils.py,sha256=IXxN9XruaeNTreUrdztb3kWJhimpsdH6hjv6xT4jg1Q,14062
 vision_agent/agent/types.py,sha256=DkFm3VMMrKlhYyfxEmZx4keppD72Ov3wmLCbM2J2o10,2437
-vision_agent/agent/vision_agent.py,sha256=I75bEU-os9Lf9OSICKfvQ_H_ftg-zOwgTwWnu41oIdo,23555
+vision_agent/agent/vision_agent.py,sha256=fH9NOLk7twL1fPr9vLSqkaYhah-gfDWfTOVF2FfMyzI,23461
 vision_agent/agent/vision_agent_coder.py,sha256=flUxOibyGZK19BCSK5mhaD3HjCxHw6c6FtKom6N2q1E,27359
-vision_agent/agent/vision_agent_coder_prompts.py,sha256=gPLVXQMNSzYnQYpNm0wlH_5FPkOTaFDV24bqzK3jQ40,12221
+vision_agent/agent/vision_agent_coder_prompts.py,sha256=_kkPLezUVnBXieNPlxMQab_6J6P7F-aa6ItF5NhZZsM,12281
 vision_agent/agent/vision_agent_coder_prompts_v2.py,sha256=idmSMfxebPULqqvllz3gqRzGDchEvS5dkGngvBs4PGo,4872
-vision_agent/agent/vision_agent_coder_v2.py,sha256=i1qgXp5YsWVRoA_qO429Ef-aKZBakveCl1F_2ZbSzk8,16287
+vision_agent/agent/vision_agent_coder_v2.py,sha256=ZR2PQoMqNM6yK3vn_0rrCJf_EplRKye7t7bVjyl51ls,16476
 vision_agent/agent/vision_agent_planner.py,sha256=fFzjNkZBKkh8Y_oS06ATI4qz31xmIJvixb_tV1kX8KA,18590
-vision_agent/agent/vision_agent_planner_prompts.py,sha256=mn9NlZpRkW4XAvlNuMZwIs1ieHCFds5aYZJ55WXupZY,6733
-vision_agent/agent/vision_agent_planner_prompts_v2.py,sha256=YgemW2PRPYd8o8XpmwSJBUOJSxMUXMNr2DZNQnS4jEI,34988
-vision_agent/agent/vision_agent_planner_v2.py,sha256=vvxfmGydBIKB8CtNSAJyPvdEXkG7nIO5-Hs2SjNc48Y,20465
-vision_agent/agent/vision_agent_prompts.py,sha256=NtGdCfzzilCRtscKALC9FK55d1h4CBpMnbhLzg0PYlc,13772
-vision_agent/agent/vision_agent_prompts_v2.py,sha256=-vCWat-ARlCOOOeIDIFhg-kcwRRwjTXYEwsvvqPeaCs,1972
-vision_agent/agent/vision_agent_v2.py,sha256=1wu_vH_onic2kLYPKW2nAF2e6Zz5vmUt5Acv4Seq3sQ,10796
+vision_agent/agent/vision_agent_planner_prompts.py,sha256=rYRdJthc-sQN57VgCBKrF09Sd73BSxcBdjNe6C4WNZ8,6837
+vision_agent/agent/vision_agent_planner_prompts_v2.py,sha256=5xTx93lNpoyT4eAD9jicwDyDAkuW7eQqicr17zCjrQw,33337
+vision_agent/agent/vision_agent_planner_v2.py,sha256=Vbfe_QrhHVViFoTYk8UTkXiZ6cptAiMexQClmRucQeA,20482
+vision_agent/agent/vision_agent_prompts.py,sha256=KaJwYPUP7_GvQsCPPs6Fdawmi3AQWmWajBUuzj7gTG4,13812
+vision_agent/agent/vision_agent_prompts_v2.py,sha256=AW_bW1boGiCLyLFd3h4GQenfDACttQagDHwpBkSW4Xo,2518
+vision_agent/agent/vision_agent_v2.py,sha256=335VT0hk0jkB14y4W3cJo5ueEu1wY_jjN-R_m2xaQ30,10752
 vision_agent/clients/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 vision_agent/clients/http.py,sha256=k883i6M_4nl7zwwHSI-yP5sAgQZIDPM1nrKD6YFJ3Xs,2009
 vision_agent/clients/landing_public_api.py,sha256=lU2ev6E8NICmR8DMUljuGcVFy5VNJQ4WQkWC8WnnJEc,1503
+vision_agent/configs/__init__.py,sha256=Iu75-w9_nlPmnB_qKA7nYaaaHf7xtTrDmK8N4v2WV34,27
+vision_agent/configs/anthropic_config.py,sha256=qYpl03wcM6wYcI24rl-9Y8Cyt8STbtUYR0IR4e5YFsU,4298
+vision_agent/configs/anthropic_openai_config.py,sha256=YQjFxmlxppn5L55dJjK_v1myBJQ_V5J4q25pmUtwTOU,4310
+vision_agent/configs/config.py,sha256=YQjFxmlxppn5L55dJjK_v1myBJQ_V5J4q25pmUtwTOU,4310
+vision_agent/configs/openai_config.py,sha256=hCn-e8rRzg4I3OQV3zG0NTWVSULg-_9KAKx1D1IdKOU,4498
 vision_agent/fonts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 vision_agent/fonts/default_font_ch_en.ttf,sha256=1YM0Z3XqLDjSNbF7ihQFSAIUdjF9m1rtHiNC_6QosTE,1594400
-vision_agent/lmm/__init__.py,sha256=jyY1sJb_tYKg5-Wzs3p1lvwFkc-aUNZfMcLy3TOC4Zg,100
-vision_agent/lmm/lmm.py,sha256=x_nIyDNDZwq4-pfjnJTmcyyJZ2_B7TjkA5jZp88YVO8,17103
+vision_agent/lmm/__init__.py,sha256=xk2Rn8Zgpy2xwYaOGHzy4tXxnxo2aj6SkpNjeJ8yxcY,111
+vision_agent/lmm/lmm.py,sha256=arwfYPWme_RxCxSpEQ0ZkpHO22GFPCwVeoSvXqLPOAk,19288
 vision_agent/lmm/types.py,sha256=ZEXR_ptBL0ZwDMTDYkgxUCmSZFmBYPQd2jreNzr_8UY,221
 vision_agent/tools/__init__.py,sha256=8VpAC8zEk8OwcMLcTn7gEAfw6ihqlsEfzjEaW5yd5-4,2897
 vision_agent/tools/meta_tools.py,sha256=TPeS7QWnc_PmmU_ndiDT03dXbQ5yDSP33E7U8cSj7Ls,28660
-vision_agent/tools/planner_tools.py,sha256=qQvPuCif-KbFi7KsXKkTCfpgEQEJJ6oq6WB3gOuG2Xg,13686
+vision_agent/tools/planner_tools.py,sha256=VL9bv7i2FS0v3wMi9eoqgWczoG8vJ-MW5de6JXnbcdA,14354
 vision_agent/tools/prompts.py,sha256=V1z4YJLXZuUl_iZ5rY0M5hHc_2tmMEUKr0WocXKGt4E,1430
 vision_agent/tools/tool_utils.py,sha256=kXB0F-HwmiChpQgKk7tMo-Acsl3UXxjaJV9mYo_q6n4,10076
-vision_agent/tools/tools.py,sha256=M_kk17Yr5c6ODKet26GcxZAlGDwl0AwMMD4wCrBhR6Y,105157
+vision_agent/tools/tools.py,sha256=FgoWy2rHxo7z0Gj3gq7-seE7I5ss4i9qNiTuyCJZg-4,105471
 vision_agent/tools/tools_types.py,sha256=8hYf2OZhI58gvf65KGaeGkt4EQ56nwLFqIQDPHioOBc,2339
 vision_agent/utils/__init__.py,sha256=QKk4zVjMwGxQI0MQ-aZZA50N-qItxRY4EB9CwQkZ2HY,185
 vision_agent/utils/exceptions.py,sha256=booSPSuoULF7OXRr_YbC4dtKt6gM_HyiFQHBuaW86C4,2052
@@ -41,7 +46,7 @@ vision_agent/utils/sim.py,sha256=qr-6UWAxxGwtwIAKZjZCY_pu9VwBI_TTB8bfrGsaABg,928
 vision_agent/utils/type_defs.py,sha256=BE12s3JNQy36QvauXHjwyeffVh5enfcvd4vTzSwvEZI,1384
 vision_agent/utils/video.py,sha256=e1VwKhXzzlC5LcFMyrcQYrPnpnX4wxDpnQ-76sB4jgM,6001
 vision_agent/utils/video_tracking.py,sha256=wK5dOutqV2t2aeaxedstCBa7xy-NNQE0-QZqKu1QUds,9498
-vision_agent-0.2.229.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-vision_agent-0.2.229.dist-info/METADATA,sha256=ver5sB_NI_dkek1GxY9GsvktACS1Rl6-tgrr_B5p1Zc,20039
-vision_agent-0.2.229.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
-vision_agent-0.2.229.dist-info/RECORD,,
+vision_agent-0.2.230.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+vision_agent-0.2.230.dist-info/METADATA,sha256=RU0v0XPXdyFA43SLZjk4sKgXB_peosxwCodQ1F9p4wA,5762
+vision_agent-0.2.230.dist-info/WHEEL,sha256=7Z8_27uaHI_UZAc4Uox4PpBhQ9Y5_modZXWMxtUi4NU,88
+vision_agent-0.2.230.dist-info/RECORD,,