feat: attempt to make embedchain optional (#450)

* fix: attempt to make embedchain optional

* fix: drop pydantic_settings dependency

* fix: ensure the package is importable without any extra dependency

After making embedchain option many packages were unstalled which caused errors in some tools due to failing import directives

Author: lucasgomide

crewai_tools/adapters/embedchain_adapter.py

@@ -1,14 +1,23 @@
 from typing import Any
 
-from embedchain import App
-
 from crewai_tools.tools.rag.rag_tool import Adapter
 
+try:
+    from embedchain import App
+    EMBEDCHAIN_AVAILABLE = True
+except ImportError:
+    EMBEDCHAIN_AVAILABLE = False
+
 
 class EmbedchainAdapter(Adapter):
-    embedchain_app: App
+    embedchain_app: Any  # Will be App when embedchain is available
     summarize: bool = False
 
+    def __init__(self, **data):
+        if not EMBEDCHAIN_AVAILABLE:
+            raise ImportError("embedchain is not installed. Please install it with `pip install crewai-tools[embedchain]`")
+        super().__init__(**data)
+
     def query(self, question: str) -> str:
         result, sources = self.embedchain_app.query(
             question, citations=True, dry_run=(not self.summarize)

crewai_tools/adapters/pdf_embedchain_adapter.py

@@ -1,15 +1,24 @@
 from typing import Any, Optional
 
-from embedchain import App
-
 from crewai_tools.tools.rag.rag_tool import Adapter
 
+try:
+    from embedchain import App
+    EMBEDCHAIN_AVAILABLE = True
+except ImportError:
+    EMBEDCHAIN_AVAILABLE = False
+
 
 class PDFEmbedchainAdapter(Adapter):
-    embedchain_app: App
+    embedchain_app: Any  # Will be App when embedchain is available
     summarize: bool = False
     src: Optional[str] = None
 
+    def __init__(self, **data):
+        if not EMBEDCHAIN_AVAILABLE:
+            raise ImportError("embedchain is not installed. Please install it with `pip install crewai-tools[embedchain]`")
+        super().__init__(**data)
+
     def query(self, question: str) -> str:
         where = (
             {"app_id": self.embedchain_app.config.id, "source": self.src}

crewai_tools/tools/brightdata_tool/brightdata_dataset.py

@@ -5,15 +5,19 @@
 import aiohttp
 from crewai.tools import BaseTool
 from pydantic import BaseModel, Field
-from pydantic_settings import BaseSettings
 
-class BrightDataConfig(BaseSettings):
+class BrightDataConfig(BaseModel):
     API_URL: str = "https://api.brightdata.com"
     DEFAULT_TIMEOUT: int = 600
     DEFAULT_POLLING_INTERVAL: int = 1
-    
-    class Config:
-        env_prefix = "BRIGHTDATA_"
+
+    @classmethod
+    def from_env(cls):
+        return cls(
+            API_URL=os.environ.get("BRIGHTDATA_API_URL", "https://api.brightdata.com"),
+            DEFAULT_TIMEOUT=int(os.environ.get("BRIGHTDATA_DEFAULT_TIMEOUT", "600")),
+            DEFAULT_POLLING_INTERVAL=int(os.environ.get("BRIGHTDATA_DEFAULT_POLLING_INTERVAL", "1"))
+        )
 class BrightDataDatasetToolException(Exception):
     """Exception raised for custom error in the application."""
 
@@ -48,10 +52,10 @@ class BrightDataDatasetToolSchema(BaseModel):
         default=None, description="Additional params if any"
     )
 
-config = BrightDataConfig()
+config = BrightDataConfig.from_env()
 
-BRIGHTDATA_API_URL = config.API_URL  
-timeout = config.DEFAULT_TIMEOUT    
+BRIGHTDATA_API_URL = config.API_URL
+timeout = config.DEFAULT_TIMEOUT
 
 datasets = [
     {
@@ -532,7 +536,7 @@ def _run(self, url: str = None, dataset_type: str = None, format: str = None, zi
         url = url or self.url
         zipcode = zipcode or self.zipcode
         additional_params = additional_params or self.additional_params
-        
+
         if not dataset_type:
             raise ValueError("dataset_type is required either in constructor or method call")
         if not url:

crewai_tools/tools/brightdata_tool/brightdata_serp.py

@@ -5,12 +5,15 @@
 import requests
 from crewai.tools import BaseTool
 from pydantic import BaseModel, Field
-from pydantic_settings import BaseSettings
 
-class BrightDataConfig(BaseSettings):
-    API_URL: str = "https://api.brightdata.com/request"    
-    class Config:
-        env_prefix = "BRIGHTDATA_"
+class BrightDataConfig(BaseModel):
+    API_URL: str = "https://api.brightdata.com/request"
+
+    @classmethod
+    def from_env(cls):
+        return cls(
+            API_URL=os.environ.get("BRIGHTDATA_API_URL", "https://api.brightdata.com/request")
+        )
 
 class BrightDataSearchToolSchema(BaseModel):
     """
@@ -73,7 +76,7 @@ class BrightDataSearchTool(BaseTool):
     name: str = "Bright Data SERP Search"
     description: str = "Tool to perform web search using Bright Data SERP API."
     args_schema: Type[BaseModel] = BrightDataSearchToolSchema
-    _config = BrightDataConfig() 
+    _config = BrightDataConfig.from_env()
     base_url: str = ""
     api_key: str = ""
     zone: str = ""
@@ -95,7 +98,7 @@ def __init__(self, query: str = None, search_engine: str = "google", country: st
         self.search_type = search_type
         self.device_type = device_type
         self.parse_results = parse_results
-        
+
         self.api_key = os.getenv("BRIGHT_DATA_API_KEY")
         self.zone = os.getenv("BRIGHT_DATA_ZONE")
         if not self.api_key:
@@ -136,7 +139,7 @@ def _run(self, query: str = None, search_engine: str = None, country: str = None
         device_type = device_type or self.device_type
         parse_results = parse_results if parse_results is not None else self.parse_results
         results_count = kwargs.get("results_count", "10")
-    
+
         # Validate required parameters
         if not query:
             raise ValueError("query is required either in constructor or method call")

crewai_tools/tools/brightdata_tool/brightdata_unlocker.py

@@ -4,12 +4,15 @@
 import requests
 from crewai.tools import BaseTool
 from pydantic import BaseModel, Field
-from pydantic_settings import BaseSettings
 
-class BrightDataConfig(BaseSettings):
-    API_URL: str = "https://api.brightdata.com/request"    
-    class Config:
-        env_prefix = "BRIGHTDATA_"
+class BrightDataConfig(BaseModel):
+    API_URL: str = "https://api.brightdata.com/request"
+
+    @classmethod
+    def from_env(cls):
+        return cls(
+            API_URL=os.environ.get("BRIGHTDATA_API_URL", "https://api.brightdata.com/request")
+        )
 
 class BrightDataUnlockerToolSchema(BaseModel):
     """
@@ -57,7 +60,7 @@ class BrightDataWebUnlockerTool(BaseTool):
     name: str = "Bright Data Web Unlocker Scraping"
     description: str = "Tool to perform web scraping using Bright Data Web Unlocker"
     args_schema: Type[BaseModel] = BrightDataUnlockerToolSchema
-    _config = BrightDataConfig() 
+    _config = BrightDataConfig.from_env()
     base_url: str = ""
     api_key: str = ""
     zone: str = ""
@@ -71,7 +74,7 @@ def __init__(self, url: str = None, format: str = "raw", data_format: str = "mar
         self.url = url
         self.format = format
         self.data_format = data_format
-        
+
         self.api_key = os.getenv("BRIGHT_DATA_API_KEY")
         self.zone = os.getenv("BRIGHT_DATA_ZONE")
         if not self.api_key:
@@ -83,10 +86,10 @@ def _run(self, url: str = None, format: str = None, data_format: str = None, **k
         url = url or self.url
         format = format or self.format
         data_format = data_format or self.data_format
-        
+
         if not url:
             raise ValueError("url is required either in constructor or method call")
-        
+
         payload = {
             "url": url,
             "zone": self.zone,

crewai_tools/tools/code_docs_search_tool/code_docs_search_tool.py

@@ -1,6 +1,11 @@
 from typing import Any, Optional, Type
 
-from embedchain.models.data_type import DataType
+try:
+    from embedchain.models.data_type import DataType
+    EMBEDCHAIN_AVAILABLE = True
+except ImportError:
+    EMBEDCHAIN_AVAILABLE = False
+
 from pydantic import BaseModel, Field
 
 from ..rag.rag_tool import RagTool
@@ -37,6 +42,8 @@ def __init__(self, docs_url: Optional[str] = None, **kwargs):
             self._generate_description()
 
     def add(self, docs_url: str) -> None:
+        if not EMBEDCHAIN_AVAILABLE:
+            raise ImportError("embedchain is not installed. Please install it with `pip install crewai-tools[embedchain]`")
         super().add(docs_url, data_type=DataType.DOCS_SITE)
 
     def _run(

crewai_tools/tools/csv_search_tool/csv_search_tool.py

@@ -1,6 +1,11 @@
 from typing import Optional, Type
 
-from embedchain.models.data_type import DataType
+try:
+    from embedchain.models.data_type import DataType
+    EMBEDCHAIN_AVAILABLE = True
+except ImportError:
+    EMBEDCHAIN_AVAILABLE = False
+
 from pydantic import BaseModel, Field
 
 from ..rag.rag_tool import RagTool
@@ -37,6 +42,8 @@ def __init__(self, csv: Optional[str] = None, **kwargs):
             self._generate_description()
 
     def add(self, csv: str) -> None:
+        if not EMBEDCHAIN_AVAILABLE:
+            raise ImportError("embedchain is not installed. Please install it with `pip install crewai-tools[embedchain]`")
         super().add(csv, data_type=DataType.CSV)
 
     def _run(

crewai_tools/tools/directory_search_tool/directory_search_tool.py

@@ -1,6 +1,11 @@
 from typing import Optional, Type
 
-from embedchain.loaders.directory_loader import DirectoryLoader
+try:
+    from embedchain.loaders.directory_loader import DirectoryLoader
+    EMBEDCHAIN_AVAILABLE = True
+except ImportError:
+    EMBEDCHAIN_AVAILABLE = False
+
 from pydantic import BaseModel, Field
 
 from ..rag.rag_tool import RagTool
@@ -29,6 +34,8 @@ class DirectorySearchTool(RagTool):
     args_schema: Type[BaseModel] = DirectorySearchToolSchema
 
     def __init__(self, directory: Optional[str] = None, **kwargs):
+        if not EMBEDCHAIN_AVAILABLE:
+            raise ImportError("embedchain is not installed. Please install it with `pip install crewai-tools[embedchain]`")
         super().__init__(**kwargs)
         if directory is not None:
             self.add(directory)

crewai_tools/tools/docx_search_tool/docx_search_tool.py

@@ -1,6 +1,11 @@
 from typing import Any, Optional, Type
 
-from embedchain.models.data_type import DataType
+try:
+    from embedchain.models.data_type import DataType
+    EMBEDCHAIN_AVAILABLE = True
+except ImportError:
+    EMBEDCHAIN_AVAILABLE = False
+
 from pydantic import BaseModel, Field
 
 from ..rag.rag_tool import RagTool
@@ -43,6 +48,8 @@ def __init__(self, docx: Optional[str] = None, **kwargs):
             self._generate_description()
 
     def add(self, docx: str) -> None:
+        if not EMBEDCHAIN_AVAILABLE:
+            raise ImportError("embedchain is not installed. Please install it with `pip install crewai-tools[embedchain]`")
         super().add(docx, data_type=DataType.DOCX)
 
     def _run(

crewai_tools/tools/github_search_tool/github_search_tool.py

@@ -1,6 +1,11 @@
-from typing import List, Optional, Type
+from typing import List, Optional, Type, Any
+
+try:
+    from embedchain.loaders.github import GithubLoader
+    EMBEDCHAIN_AVAILABLE = True
+except ImportError:
+    EMBEDCHAIN_AVAILABLE = False
 
-from embedchain.loaders.github import GithubLoader
 from pydantic import BaseModel, Field, PrivateAttr
 
 from ..rag.rag_tool import RagTool
@@ -37,14 +42,16 @@ class GithubSearchTool(RagTool):
         default_factory=lambda: ["code", "repo", "pr", "issue"],
         description="Content types you want to be included search, options: [code, repo, pr, issue]",
     )
-    _loader: GithubLoader | None = PrivateAttr(default=None)
+    _loader: Any | None = PrivateAttr(default=None)
 
     def __init__(
         self,
         github_repo: Optional[str] = None,
         content_types: Optional[List[str]] = None,
         **kwargs,
     ):
+        if not EMBEDCHAIN_AVAILABLE:
+            raise ImportError("embedchain is not installed. Please install it with `pip install crewai-tools[embedchain]`")
         super().__init__(**kwargs)
         self._loader = GithubLoader(config={"token": self.gh_token})