feat: merge latest changes from crewAI-tools main into packages/tools

- Merged upstream changes from crewAI-tools main branch
- Resolved conflicts due to monorepo structure (crewai_tools -> src/crewai_tools)
- Removed deprecated embedchain adapters
- Added new RAG loaders and crewai_rag_adapter
- Consolidated dependencies in pyproject.toml

Fixed critical linting issues:
- Added ClassVar annotations for mutable class attributes
- Added timeouts to requests calls (30s default)
- Fixed exception handling with proper 'from' clauses
- Added noqa comments for public API functions (backward compatibility)
- Updated ruff config to ignore expected patterns:
  - F401 in __init__ files (intentional re-exports)
  - S101 in test files (assertions are expected)
  - S607 for subprocess calls (uv/pip commands are safe)

Remaining issues are from upstream code and will be addressed in separate PRs.

packages/tools/src/crewai_tools/rag/chunkers/structured_chunker.py

@@ -1,49 +1,66 @@
 from crewai_tools.rag.chunkers.base_chunker import BaseChunker
-from typing import List, Optional
 
 
 class CsvChunker(BaseChunker):
-    def __init__(self, chunk_size: int = 1200, chunk_overlap: int = 100, separators: Optional[List[str]] = None, keep_separator: bool = True):
+    def __init__(
+        self,
+        chunk_size: int = 1200,
+        chunk_overlap: int = 100,
+        separators: list[str] | None = None,
+        keep_separator: bool = True,
+    ):
         if separators is None:
             separators = [
-                "\nRow ",   # Row boundaries (from CSVLoader format)
-                "\n",       # Line breaks
-                " | ",      # Column separators
-                ", ",       # Comma separators
-                " ",        # Word breaks
-                "",         # Character level
+                "\nRow ",  # Row boundaries (from CSVLoader format)
+                "\n",  # Line breaks
+                " | ",  # Column separators
+                ", ",  # Comma separators
+                " ",  # Word breaks
+                "",  # Character level
             ]
         super().__init__(chunk_size, chunk_overlap, separators, keep_separator)
 
 
 class JsonChunker(BaseChunker):
-    def __init__(self, chunk_size: int = 2000, chunk_overlap: int = 200, separators: Optional[List[str]] = None, keep_separator: bool = True):
+    def __init__(
+        self,
+        chunk_size: int = 2000,
+        chunk_overlap: int = 200,
+        separators: list[str] | None = None,
+        keep_separator: bool = True,
+    ):
         if separators is None:
             separators = [
-                "\n\n",     # Object/array boundaries
-                "\n",       # Line breaks
-                "},",       # Object endings
-                "],",       # Array endings
-                ", ",       # Property separators
-                ": ",       # Key-value separators
-                " ",        # Word breaks
-                "",         # Character level
+                "\n\n",  # Object/array boundaries
+                "\n",  # Line breaks
+                "},",  # Object endings
+                "],",  # Array endings
+                ", ",  # Property separators
+                ": ",  # Key-value separators
+                " ",  # Word breaks
+                "",  # Character level
             ]
         super().__init__(chunk_size, chunk_overlap, separators, keep_separator)
 
 
 class XmlChunker(BaseChunker):
-    def __init__(self, chunk_size: int = 2500, chunk_overlap: int = 250, separators: Optional[List[str]] = None, keep_separator: bool = True):
+    def __init__(
+        self,
+        chunk_size: int = 2500,
+        chunk_overlap: int = 250,
+        separators: list[str] | None = None,
+        keep_separator: bool = True,
+    ):
         if separators is None:
             separators = [
-                "\n\n",     # Element boundaries
-                "\n",       # Line breaks
-                ">",        # Tag endings
-                ". ",       # Sentence endings (for text content)
-                "! ",       # Exclamation endings
-                "? ",       # Question endings
-                ", ",       # Comma separators
-                " ",        # Word breaks
-                "",         # Character level
+                "\n\n",  # Element boundaries
+                "\n",  # Line breaks
+                ">",  # Tag endings
+                ". ",  # Sentence endings (for text content)
+                "! ",  # Exclamation endings
+                "? ",  # Question endings
+                ", ",  # Comma separators
+                " ",  # Word breaks
+                "",  # Character level
             ]
         super().__init__(chunk_size, chunk_overlap, separators, keep_separator)