Rename lmm-tools to vision-agent

.github/workflows/ci_cd.yml

@@ -42,7 +42,7 @@ jobs:
  poetry run black --check --diff --color .
  - name: Type Checking
  run: |
- poetry run mypy lmm_tools
+ poetry run mypy vision_agent
  - name: Test with pytest
  run: |
  poetry run pytest -v tests

README.md

@@ -1,14 +1,14 @@
-# Large Multimodal Model Tools
-LMM-Tools (Large Multmodal Model Tools) is a minimal library that helps you utilize multimodal models to organize and structure your image data. One of the problems of dealing with image data is it can be difficult to organize and quickly search. For example, you might have a bunch of pictures of houses and want to count how many yellow houses you have, or how many houses with adobe roofs. This library utilizes LMMs to help create these tags or descriptions and allow you to search over them, or use them in a database to do other operations.
+# Vision Agent
+Vision Agent is a minimal library that helps you utilize multimodal models to organize and structure your image data. One of the problems of dealing with image data is it can be difficult to organize and quickly search. For example, you might have a bunch of pictures of houses and want to count how many yellow houses you have, or how many houses with adobe roofs. This library utilizes LMMs to help create these tags or descriptions and allow you to search over them, or use them in a database to do other operations.
 
 ## Getting Started
 ### LMMs
 To get started you can create an LMM and start generating text from images. The following code will grab the LLaVA-1.6 34B model and generate a description of the image you pass it.
 
 ```python
-import lmm_tools as lmt
+import vision_agent as va
 
-model = lmt.lmm.get_model("llava")
+model = va.lmm.get_model("llava")
 model.generate("Describe this image", "image.png")
 >>> "A yellow house with a green lawn."
 ```
@@ -19,13 +19,13 @@ model.generate("Describe this image", "image.png")
 You can use the `DataStore` class to store your images, add new metadata to them such as descriptions, and search over different columns.
 
 ```python
-import lmm_tools as lmt
+import vision_agent as va
 import pandas as pd
 
 df = pd.DataFrame({"image_paths": ["image1.png", "image2.png", "image3.png"]})
-ds = lmt.data.DataStore(df)
-ds = ds.add_lmm(lmt.lmm.get_model("llava"))
-ds = ds.add_embedder(lmt.emb.get_embedder("sentence-transformer"))
+ds = va.data.DataStore(df)
+ds = ds.add_lmm(va.lmm.get_model("llava"))
+ds = ds.add_embedder(va.emb.get_embedder("sentence-transformer"))
 
 ds = ds.add_column("descriptions", "Describe this image.")
 ```

docs/index.md

@@ -13,5 +13,5 @@ This library provides a set of tools to help you build applications with Large M
 First, install the library:
 
 ```bash
-pip install lmm-tools
+pip install vision-agent
 ```

pyproject.toml

@@ -3,17 +3,17 @@ requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
-name = "lmm-tools"
+name = "vision-agent"
 version = "0.0.8"
-description = "Toolset for Large Multi-Modal Models"
+description = "Toolset for Vision Agent"
 authors = ["Landing AI <[email protected]>"]
 readme = "README.md"
-packages = [{include = "lmm_tools"}]
+packages = [{include = "vision_agent"}]
 
 [tool.poetry.urls]
 "Homepage" = "https://landing.ai"
-"repository" = "https://github.com/landing-ai/lmm-tools"
-"documentation" = "https://github.com/landing-ai/lmm-tools"
+"repository" = "https://github.com/landing-ai/vision-agent"
+"documentation" = "https://github.com/landing-ai/vision-agent"
 
 [tool.poetry.dependencies] # main dependency group
 python = ">=3.10,<4.0"

tests/test_data.py

@@ -5,7 +5,7 @@
 import pandas as pd
 import pytest
 
-from lmm_tools.data import DataStore, build_data_store
+from vision_agent.data import DataStore, build_data_store
 
 
 @pytest.fixture(autouse=True)

lmm_tools/data/data.py → vision_agent/data/data.py

@@ -12,8 +12,8 @@
 from tqdm import tqdm
 from typing_extensions import Self
 
-from lmm_tools.emb import Embedder
-from lmm_tools.lmm import LMM
+from vision_agent.emb import Embedder
+from vision_agent.lmm import LMM
 
 tqdm.pandas()
 

lmm_tools/lmm/lmm.py → vision_agent/lmm/lmm.py

@@ -1,9 +1,11 @@
 import base64
-import requests
 from abc import ABC, abstractmethod
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union, cast
-from lmm_tools.config import BASETEN_API_KEY, BASETEN_URL
+
+import requests
+
+from vision_agent.config import BASETEN_API_KEY, BASETEN_URL
 
 
 def encode_image(image: Union[str, Path]) -> str: