Squashed 'packages/tools/' content from commit 78317b9c

git-subtree-dir: packages/tools
git-subtree-split: 78317b9c127f18bd040c1d77e3c0840cdc9a5b38

crewai_tools/tools/pdf_search_tool/pdf_search_tool.py

@@ -0,0 +1,55 @@
+from typing import Optional, Type
+
+from pydantic import BaseModel, Field
+
+try:
+    from embedchain.models.data_type import DataType
+    EMBEDCHAIN_AVAILABLE = True
+except ImportError:
+    EMBEDCHAIN_AVAILABLE = False
+
+from ..rag.rag_tool import RagTool
+
+
+class FixedPDFSearchToolSchema(BaseModel):
+    """Input for PDFSearchTool."""
+
+    query: str = Field(
+        ..., description="Mandatory query you want to use to search the PDF's content"
+    )
+
+
+class PDFSearchToolSchema(FixedPDFSearchToolSchema):
+    """Input for PDFSearchTool."""
+
+    pdf: str = Field(..., description="File path or URL of a PDF file to be searched")
+
+
+class PDFSearchTool(RagTool):
+    name: str = "Search a PDF's content"
+    description: str = (
+        "A tool that can be used to semantic search a query from a PDF's content."
+    )
+    args_schema: Type[BaseModel] = PDFSearchToolSchema
+
+    def __init__(self, pdf: Optional[str] = None, **kwargs):
+        super().__init__(**kwargs)
+        if pdf is not None:
+            self.add(pdf)
+            self.description = f"A tool that can be used to semantic search a query the {pdf} PDF's content."
+            self.args_schema = FixedPDFSearchToolSchema
+            self._generate_description()
+
+    def add(self, pdf: str) -> None:
+        if not EMBEDCHAIN_AVAILABLE:
+            raise ImportError("embedchain is not installed. Please install it with `pip install crewai-tools[embedchain]`")
+        super().add(pdf, data_type=DataType.PDF_FILE)
+
+    def _run(
+        self,
+        query: str,
+        pdf: Optional[str] = None,
+    ) -> str:
+        if pdf is not None:
+            self.add(pdf)
+        return super()._run(query=query)