Feat/docling-support (#1763)

* added tool for docling support

* docling support installation

* use file_paths instead of file_path

* fix import

* organized imports

* run_type docs

* needs to be list

* fixed logic

* logged but file_path is backwards compatible

* use file_paths instead of file_path 2

* added test for multiple sources for file_paths

* fix run-types

* enabling local files to work and type cleanup

* linted

* fix test and types

* fixed run types

* fix types

* renamed to CrewDoclingSource

* linted

* added docs

* resolve conflicts

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>
Co-authored-by: Brandon Hancock <brandon@brandonhancock.io>

src/crewai/knowledge/source/base_file_knowledge_source.py

@@ -1,8 +1,8 @@
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Dict, List, Union
+from typing import Dict, List, Optional, Union
 
-from pydantic import Field
+from pydantic import Field, field_validator
 
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
@@ -14,17 +14,28 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
     """Base class for knowledge sources that load content from files."""
 
     _logger: Logger = Logger(verbose=True)
-    file_path: Union[Path, List[Path], str, List[str]] = Field(
-        ..., description="The path to the file"
+    file_path: Optional[Union[Path, List[Path], str, List[str]]] = Field(
+        default=None,
+        description="[Deprecated] The path to the file. Use file_paths instead.",
+    )
+    file_paths: Optional[Union[Path, List[Path], str, List[str]]] = Field(
+        default_factory=list, description="The path to the file"
     )
     content: Dict[Path, str] = Field(init=False, default_factory=dict)
     storage: KnowledgeStorage = Field(default_factory=KnowledgeStorage)
     safe_file_paths: List[Path] = Field(default_factory=list)
 
+    @field_validator("file_path", "file_paths", mode="before")
+    def validate_file_path(cls, v, values):
+        """Validate that at least one of file_path or file_paths is provided."""
+        if v is None and ("file_path" not in values or values.get("file_path") is None):
+            raise ValueError("Either file_path or file_paths must be provided")
+        return v
+
     def model_post_init(self, _):
         """Post-initialization method to load content."""
         self.safe_file_paths = self._process_file_paths()
-        self.validate_paths()
+        self.validate_content()
         self.content = self.load_content()
 
     @abstractmethod
@@ -32,7 +43,7 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
         """Load and preprocess file content. Should be overridden by subclasses. Assume that the file path is relative to the project root in the knowledge directory."""
         pass
 
-    def validate_paths(self):
+    def validate_content(self):
         """Validate the paths."""
         for path in self.safe_file_paths:
             if not path.exists():
@@ -59,13 +70,29 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
 
     def _process_file_paths(self) -> List[Path]:
         """Convert file_path to a list of Path objects."""
-        paths = (
-            [self.file_path]
-            if isinstance(self.file_path, (str, Path))
-            else self.file_path
-        )
 
-        if not isinstance(paths, list):
-            raise ValueError("file_path must be a Path, str, or a list of these types")
+        # Check if old file_path is being used
+        if hasattr(self, "file_path") and self.file_path is not None:
+            self._logger.log(
+                "warning",
+                "The 'file_path' attribute is deprecated and will be removed in a future version. Please use 'file_paths' instead.",
+                color="yellow",
+            )
+            paths = (
+                [self.file_path]
+                if isinstance(self.file_path, (str, Path))
+                else self.file_path
+            )
+        else:
+            if self.file_paths is None:
+                raise ValueError("Your source must be provided with a file_paths: []")
+            elif isinstance(self.file_paths, list) and len(self.file_paths) == 0:
+                raise ValueError("Empty file_paths are not allowed")
+            else:
+                paths = (
+                    [self.file_paths]
+                    if isinstance(self.file_paths, (str, Path))
+                    else self.file_paths
+                )
 
         return [self.convert_to_path(path) for path in paths]