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

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

crewai_tools/tools/csv_search_tool/README.md

@@ -0,0 +1,59 @@
+# CSVSearchTool
+
+## Description
+
+This tool is used to perform a RAG (Retrieval-Augmented Generation) search within a CSV file's content. It allows users to semantically search for queries in the content of a specified CSV file. This feature is particularly useful for extracting information from large CSV datasets where traditional search methods might be inefficient. All tools with "Search" in their name, including CSVSearchTool, are RAG tools designed for searching different sources of data.
+
+## Installation
+
+Install the crewai_tools package
+
+```shell
+pip install 'crewai[tools]'
+```
+
+## Example
+
+```python
+from crewai_tools import CSVSearchTool
+
+# Initialize the tool with a specific CSV file. This setup allows the agent to only search the given CSV file.
+tool = CSVSearchTool(csv='path/to/your/csvfile.csv')
+
+# OR
+
+# Initialize the tool without a specific CSV file. Agent  will need to provide the CSV path at runtime.
+tool = CSVSearchTool()
+```
+
+## Arguments
+
+- `csv` : The path to the CSV file you want to search. This is a mandatory argument if the tool was initialized without a specific CSV file; otherwise, it is optional.
+
+## Custom model and embeddings
+
+By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
+
+```python
+tool = CSVSearchTool(
+    config=dict(
+        llm=dict(
+            provider="ollama", # or google, openai, anthropic, llama2, ...
+            config=dict(
+                model="llama2",
+                # temperature=0.5,
+                # top_p=1,
+                # stream=true,
+            ),
+        ),
+        embedder=dict(
+            provider="google",
+            config=dict(
+                model="models/embedding-001",
+                task_type="retrieval_document",
+                # title="Embeddings",
+            ),
+        ),
+    )
+)
+```

crewai_tools/tools/csv_search_tool/csv_search_tool.py

@@ -0,0 +1,56 @@
+from typing import Optional, Type
+
+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
+
+
+class FixedCSVSearchToolSchema(BaseModel):
+    """Input for CSVSearchTool."""
+
+    search_query: str = Field(
+        ...,
+        description="Mandatory search query you want to use to search the CSV's content",
+    )
+
+
+class CSVSearchToolSchema(FixedCSVSearchToolSchema):
+    """Input for CSVSearchTool."""
+
+    csv: str = Field(..., description="File path or URL of a CSV file to be searched")
+
+
+class CSVSearchTool(RagTool):
+    name: str = "Search a CSV's content"
+    description: str = (
+        "A tool that can be used to semantic search a query from a CSV's content."
+    )
+    args_schema: Type[BaseModel] = CSVSearchToolSchema
+
+    def __init__(self, csv: Optional[str] = None, **kwargs):
+        super().__init__(**kwargs)
+        if csv is not None:
+            self.add(csv)
+            self.description = f"A tool that can be used to semantic search a query the {csv} CSV's content."
+            self.args_schema = FixedCSVSearchToolSchema
+            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(
+        self,
+        search_query: str,
+        csv: Optional[str] = None,
+    ) -> str:
+        if csv is not None:
+            self.add(csv)
+        return super()._run(query=search_query)