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

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

crewai_tools/tools/pg_search_tool/README.md

@@ -0,0 +1,56 @@
+# PGSearchTool
+
+## Description
+This tool is designed to facilitate semantic searches within PostgreSQL database tables. Leveraging the RAG (Retrieve and Generate) technology, the PGSearchTool provides users with an efficient means of querying database table content, specifically tailored for PostgreSQL databases. It simplifies the process of finding relevant data through semantic search queries, making it an invaluable resource for users needing to perform advanced queries on extensive datasets within a PostgreSQL database.
+
+## Installation
+To install the `crewai_tools` package and utilize the PGSearchTool, execute the following command in your terminal:
+
+```shell
+pip install 'crewai[tools]'
+```
+
+## Example
+Below is an example showcasing how to use the PGSearchTool to conduct a semantic search on a table within a PostgreSQL database:
+
+```python
+from crewai_tools import PGSearchTool
+
+# Initialize the tool with the database URI and the target table name
+tool = PGSearchTool(db_uri='postgresql://user:password@localhost:5432/mydatabase', table_name='employees')
+
+```
+
+## Arguments
+The PGSearchTool requires the following arguments for its operation:
+
+- `db_uri`: A string representing the URI of the PostgreSQL database to be queried. This argument is mandatory and must include the necessary authentication details and the location of the database.
+- `table_name`: A string specifying the name of the table within the database on which the semantic search will be performed. This argument is mandatory.
+
+## 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 = PGSearchTool(
+    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/pg_search_tool/pg_search_tool.py

@@ -0,0 +1,51 @@
+from typing import Any, Type
+
+try:
+    from embedchain.loaders.postgres import PostgresLoader
+    EMBEDCHAIN_AVAILABLE = True
+except ImportError:
+    EMBEDCHAIN_AVAILABLE = False
+
+from pydantic import BaseModel, Field
+
+from ..rag.rag_tool import RagTool
+
+
+class PGSearchToolSchema(BaseModel):
+    """Input for PGSearchTool."""
+
+    search_query: str = Field(
+        ...,
+        description="Mandatory semantic search query you want to use to search the database's content",
+    )
+
+
+class PGSearchTool(RagTool):
+    name: str = "Search a database's table content"
+    description: str = "A tool that can be used to semantic search a query from a database table's content."
+    args_schema: Type[BaseModel] = PGSearchToolSchema
+    db_uri: str = Field(..., description="Mandatory database URI")
+
+    def __init__(self, table_name: str, **kwargs):
+        if not EMBEDCHAIN_AVAILABLE:
+            raise ImportError("embedchain is not installed. Please install it with `pip install crewai-tools[embedchain]`")
+        super().__init__(**kwargs)
+        kwargs["data_type"] = "postgres"
+        kwargs["loader"] = PostgresLoader(config=dict(url=self.db_uri))
+        self.add(table_name)
+        self.description = f"A tool that can be used to semantic search a query the {table_name} database table's content."
+        self._generate_description()
+
+    def add(
+        self,
+        table_name: str,
+        **kwargs: Any,
+    ) -> None:
+        super().add(f"SELECT * FROM {table_name};", **kwargs)
+
+    def _run(
+        self,
+        search_query: str,
+        **kwargs: Any,
+    ) -> Any:
+        return super()._run(query=search_query, **kwargs)