fix: dependencies (#416)

docs/advanced/app_types.mdx

@@ -63,6 +63,7 @@ app = OpenSourceApp()
 - Here there is no need to setup any api keys. You just need to install embedchain package and these will get automatically installed. 📦
 - Once you have imported and instantiated the app, every functionality from here onwards is the same for either type of app. 📚
 - `OpenSourceApp` is opinionated. It uses the best open source embedding model and LLM on the market.
+- extra dependencies are required for this app type. Install them with `pip install embedchain[opensource]`.
 
 ### CustomApp
 

embedchain/apps/CustomApp.py

@@ -68,7 +68,7 @@ class CustomApp(EmbedChain):
                 return CustomApp._get_azure_openai_answer(prompt, config)
 
         except ImportError as e:
-            raise ImportError(e.msg) from None
+            raise ModuleNotFoundError(e.msg) from None
 
     @staticmethod
     def _get_openai_answer(prompt: str, config: ChatConfig) -> str:

embedchain/apps/OpenSourceApp.py

@@ -43,8 +43,8 @@ class OpenSourceApp(EmbedChain):
         try:
             from gpt4all import GPT4All
         except ModuleNotFoundError:
-            raise ValueError(
+            raise ModuleNotFoundError(
-                "The GPT4All python package is not installed. Please install it with `pip install GPT4All`"
+                "The GPT4All python package is not installed. Please install it with `pip install embedchain[opensource]`"  # noqa E501
             ) from None
 
         return GPT4All(model)

embedchain/config/apps/OpenSourceAppConfig.py

@@ -50,4 +50,10 @@ class OpenSourceAppConfig(BaseAppConfig):
 
         :returns: The default embedding function
         """
-        return embedding_functions.SentenceTransformerEmbeddingFunction(model_name="all-MiniLM-L6-v2")
+        try:
+            return embedding_functions.SentenceTransformerEmbeddingFunction(model_name="all-MiniLM-L6-v2")
+        except ValueError as e:
+            print(e)
+            raise ModuleNotFoundError(
+                "The open source app requires extra dependencies. Install with `pip install embedchain[opensource]`"
+            ) from None

pyproject.toml

@@ -91,6 +91,10 @@ beautifulsoup4 = "^4.12.2"
 pypdf = "^3.11.0"
 pytube = "^15.0.0"
 llama-index = { version = "^0.7.21", optional = true }
+sentence-transformers = { version = "^2.2.2", optional = true }
+torch = { version = ">=2.0.0, !=2.0.1", optional = true }
+# Torch 2.0.1 is not compatible with poetry (https://github.com/pytorch/pytorch/issues/100974)
+gpt4all = { version = "^1.0.8", optional = true }
 elasticsearch = { version = "^8.9.0", optional = true }
 flask = "^2.3.3"
 twilio = "^8.5.0"
@@ -110,6 +114,7 @@ isort = "^5.12.0"
 [tool.poetry.extras]
 streamlit = ["streamlit"]
 community = ["llama-index"]
+opensource = ["sentence-transformers", "torch", "gpt4all"]
 elasticsearch = ["elasticsearch"]
 
 [tool.poetry.group.docs.dependencies]

setup.py

@@ -1,46 +0,0 @@
-import setuptools
-
-with open("README.md", "r", encoding="utf-8") as fh:
-    long_description = fh.read()
-
-setuptools.setup(
-    name="embedchain",
-    version="0.0.41",
-    author="Taranjeet Singh",
-    author_email="reachtotj@gmail.com",
-    description="embedchain is a framework to easily create LLM powered bots over any dataset",  # noqa:E501
-    long_description=long_description,
-    long_description_content_type="text/markdown",
-    url="https://github.com/embedchain/embedchain",
-    packages=setuptools.find_packages(),
-    classifiers=[
-        "Programming Language :: Python :: 3",
-        "License :: OSI Approved :: Apache Software License",
-        "Operating System :: OS Independent",
-    ],
-    python_requires=">=3.8",
-    py_modules=["embedchain"],
-    install_requires=[
-        "langchain>=0.0.205",
-        "requests",
-        "openai",
-        "chromadb>=0.4.2",
-        "youtube-transcript-api",
-        "beautifulsoup4",
-        "pypdf",
-        "pytube",
-        "lxml",
-        "gpt4all",
-        "sentence_transformers",
-        "docx2txt",
-        "pydantic==1.10.8",
-        "replicate==0.9.0",
-        "duckduckgo-search==3.8.4",
-    ],
-    extras_require={
-        "dev": ["black", "ruff", "isort", "pytest"],
-        "community": ["llama-index==0.7.21"],
-        "elasticsearch": ["elasticsearch>=8.9.0"],
-        "whatsapp": ["twilio==8.5.0", "flask==1.1.2"],
-    },
-)