19114177728

Committed 05 Nov 2025 07:41PM UTC coverage: 92.248%. Remained the same

Build # 19114177728

Build Type

Pull #9932

github

Committed by

web-flow

Commit Message

Merge 3db96ab24 into 510d06361

Pull Request Pull Request #9932: fix: prompt-builder - jinja2 template set vars still shows required

Run Details

13531 of 14668 relevant lines covered (92.25%)

0.92 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

84.71

haystack/tools/toolset.py

# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
#
# SPDX-License-Identifier: Apache-2.0

from dataclasses import dataclass, field
from typing import Any, Iterator, Union

from haystack.core.serialization import generate_qualified_class_name, import_class_by_name
from haystack.tools.tool import Tool, _check_duplicate_tool_names


@dataclass
class Toolset:
    """
    A collection of related Tools that can be used and managed as a cohesive unit.

    Toolset serves two main purposes:

    1. Group related tools together:
       Toolset allows you to organize related tools into a single collection, making it easier
       to manage and use them as a unit in Haystack pipelines.

       Example:
       ```python
       from haystack.tools import Tool, Toolset
       from haystack.components.tools import ToolInvoker

       # Define math functions
       def add_numbers(a: int, b: int) -> int:
           return a + b

       def subtract_numbers(a: int, b: int) -> int:
           return a - b

       # Create tools with proper schemas
       add_tool = Tool(
           name="add",
           description="Add two numbers",
           parameters={
               "type": "object",
               "properties": {
                   "a": {"type": "integer"},
                   "b": {"type": "integer"}
               },
               "required": ["a", "b"]
           },
           function=add_numbers
       )

       subtract_tool = Tool(
           name="subtract",
           description="Subtract b from a",
           parameters={
               "type": "object",
               "properties": {
                   "a": {"type": "integer"},
                   "b": {"type": "integer"}
               },
               "required": ["a", "b"]
           },
           function=subtract_numbers
       )

       # Create a toolset with the math tools
       math_toolset = Toolset([add_tool, subtract_tool])

       # Use the toolset with a ToolInvoker or ChatGenerator component
       invoker = ToolInvoker(tools=math_toolset)
       ```

    2. Base class for dynamic tool loading:
       By subclassing Toolset, you can create implementations that dynamically load tools
       from external sources like OpenAPI URLs, MCP servers, or other resources.

       Example:
       ```python
       from haystack.core.serialization import generate_qualified_class_name
       from haystack.tools import Tool, Toolset
       from haystack.components.tools import ToolInvoker

       class CalculatorToolset(Toolset):
           '''A toolset for calculator operations.'''

           def __init__(self):
               tools = self._create_tools()
               super().__init__(tools)

           def _create_tools(self):
               # These Tool instances are obviously defined statically and for illustration purposes only.
               # In a real-world scenario, you would dynamically load tools from an external source here.
               tools = []
               add_tool = Tool(
                   name="add",
                   description="Add two numbers",
                   parameters={
                       "type": "object",
                       "properties": {"a": {"type": "integer"}, "b": {"type": "integer"}},
                       "required": ["a", "b"],
                   },
                   function=lambda a, b: a + b,
               )

               multiply_tool = Tool(
                   name="multiply",
                   description="Multiply two numbers",
                   parameters={
                       "type": "object",
                       "properties": {"a": {"type": "integer"}, "b": {"type": "integer"}},
                       "required": ["a", "b"],
                   },
                   function=lambda a, b: a * b,
               )

               tools.append(add_tool)
               tools.append(multiply_tool)

               return tools

           def to_dict(self):
               return {
                   "type": generate_qualified_class_name(type(self)),
                   "data": {},  # no data to serialize as we define the tools dynamically
               }

           @classmethod
           def from_dict(cls, data):
               return cls()  # Recreate the tools dynamically during deserialization

       # Create the dynamic toolset and use it with ToolInvoker
       calculator_toolset = CalculatorToolset()
       invoker = ToolInvoker(tools=calculator_toolset)
       ```

    Toolset implements the collection interface (__iter__, __contains__, __len__, __getitem__),
    making it behave like a list of Tools. This makes it compatible with components that expect
    iterable tools, such as ToolInvoker or Haystack chat generators.

    When implementing a custom Toolset subclass for dynamic tool loading:
    - Perform the dynamic loading in the __init__ method
    - Override to_dict() and from_dict() methods if your tools are defined dynamically
    - Serialize endpoint descriptors rather than tool instances if your tools
      are loaded from external sources
    """

    # Use field() with default_factory to initialize the list
    tools: list[Tool] = field(default_factory=list)

    def __post_init__(self):
        """
        Validate and set up the toolset after initialization.

        This handles the case when tools are provided during initialization.
        """
        # If initialization was done a single Tool, raise an error
        if isinstance(self.tools, Tool):
            raise TypeError("A single Tool cannot be directly passed to Toolset. Please use a list: Toolset([tool])")

        # Check for duplicate tool names in the initial set
        _check_duplicate_tool_names(self.tools)

    def __iter__(self) -> Iterator[Tool]:
        """
        Return an iterator over the Tools in this Toolset.

        This allows the Toolset to be used wherever a list of Tools is expected.

        :returns: An iterator yielding Tool instances
        """
        return iter(self.tools)

    def __contains__(self, item: Any) -> bool:
        """
        Check if a tool is in this Toolset.

        Supports checking by:
        - Tool instance: tool in toolset
        - Tool name: "tool_name" in toolset

        :param item: Tool instance or tool name string
        :returns: True if contained, False otherwise
        """
        if isinstance(item, str):
            return any(tool.name == item for tool in self.tools)
        if isinstance(item, Tool):
            return item in self.tools
        return False

    def warm_up(self) -> None:
        """
        Prepare the Toolset for use.

        By default, this method iterates through and warms up all tools in the Toolset.
        Subclasses can override this method to customize initialization behavior, such as:

        - Setting up shared resources (database connections, HTTP sessions) instead of
          warming individual tools
        - Implementing custom initialization logic for dynamically loaded tools
        - Controlling when and how tools are initialized

        For example, a Toolset that manages tools from an external service (like MCPToolset)
        might override this to initialize a shared connection rather than warming up
        individual tools:

        ```python
        class MCPToolset(Toolset):
            def warm_up(self) -> None:
                # Only warm up the shared MCP connection, not individual tools
                self.mcp_connection = establish_connection(self.server_url)
        ```

        This method should be idempotent, as it may be called multiple times.
        """
        for tool in self.tools:
            if hasattr(tool, "warm_up"):
                tool.warm_up()

    def add(self, tool: Union[Tool, "Toolset"]) -> None:
        """
        Add a new Tool or merge another Toolset.

        :param tool: A Tool instance or another Toolset to add
        :raises ValueError: If adding the tool would result in duplicate tool names
        :raises TypeError: If the provided object is not a Tool or Toolset
        """
        new_tools = []

        if isinstance(tool, Tool):
            new_tools = [tool]
        elif isinstance(tool, Toolset):
            new_tools = list(tool)
        else:
            raise TypeError(f"Expected Tool or Toolset, got {type(tool).__name__}")

        # Check for duplicates before adding
        combined_tools = self.tools + new_tools
        _check_duplicate_tool_names(combined_tools)

        self.tools.extend(new_tools)

    def to_dict(self) -> dict[str, Any]:
        """
        Serialize the Toolset to a dictionary.

        :returns: A dictionary representation of the Toolset

        Note for subclass implementers:
        The default implementation is ideal for scenarios where Tool resolution is static. However, if your subclass
        of Toolset dynamically resolves Tool instances from external sources—such as an MCP server, OpenAPI URL, or
        a local OpenAPI specification—you should consider serializing the endpoint descriptor instead of the Tool
        instances themselves. This strategy preserves the dynamic nature of your Toolset and minimizes the overhead
        associated with serializing potentially large collections of Tool objects. Moreover, by serializing the
        descriptor, you ensure that the deserialization process can accurately reconstruct the Tool instances, even
        if they have been modified or removed since the last serialization. Failing to serialize the descriptor may
        lead to issues where outdated or incorrect Tool configurations are loaded, potentially causing errors or
        unexpected behavior.
        """
        return {
            "type": generate_qualified_class_name(type(self)),
            "data": {"tools": [tool.to_dict() for tool in self.tools]},
        }

    @classmethod
    def from_dict(cls, data: dict[str, Any]) -> "Toolset":
        """
        Deserialize a Toolset from a dictionary.

        :param data: Dictionary representation of the Toolset
        :returns: A new Toolset instance
        """
        inner_data = data["data"]
        tools_data = inner_data.get("tools", [])

        tools = []
        for tool_data in tools_data:
            tool_class = import_class_by_name(tool_data["type"])
            if not issubclass(tool_class, Tool):
                raise TypeError(f"Class '{tool_class}' is not a subclass of Tool")
            tools.append(tool_class.from_dict(tool_data))

        return cls(tools=tools)

    def __add__(self, other: Union[Tool, "Toolset", list[Tool]]) -> "Toolset":
        """
        Concatenate this Toolset with another Tool, Toolset, or list of Tools.

        :param other: Another Tool, Toolset, or list of Tools to concatenate
        :returns: A new Toolset containing all tools
        :raises TypeError: If the other parameter is not a Tool, Toolset, or list of Tools
        :raises ValueError: If the combination would result in duplicate tool names
        """
        if isinstance(other, Tool):
            return Toolset(tools=self.tools + [other])
        if isinstance(other, Toolset):
            return _ToolsetWrapper([self, other])
        if isinstance(other, list) and all(isinstance(item, Tool) for item in other):
            return Toolset(tools=self.tools + other)
        raise TypeError(f"Cannot add {type(other).__name__} to Toolset")

    def __len__(self) -> int:
        """
        Return the number of Tools in this Toolset.

        :returns: Number of Tools
        """
        return len(self.tools)

    def __getitem__(self, index):
        """
        Get a Tool by index.

        :param index: Index of the Tool to get
        :returns: The Tool at the specified index
        """
        return self.tools[index]


class _ToolsetWrapper(Toolset):
    """
    A wrapper that holds multiple toolsets and provides a unified interface.

    This is used internally when combining different types of toolsets to preserve
    their individual configurations while still being usable with ToolInvoker.
    """

    def __init__(self, toolsets: list[Toolset]):
        super().__init__([tool for toolset in toolsets for tool in toolset])
        self.toolsets = toolsets

    def __iter__(self):
        """Iterate over all tools from all toolsets."""
        for toolset in self.toolsets:
            yield from toolset

    def __contains__(self, item):
        """Check if a tool is in any of the toolsets."""
        return any(item in toolset for toolset in self.toolsets)

    def warm_up(self):
        """Warm up all toolsets."""
        for toolset in self.toolsets:
            toolset.warm_up()

    def __len__(self):
        """Return total number of tools across all toolsets."""
        return sum(len(toolset) for toolset in self.toolsets)

    def __getitem__(self, index):
        """Get a tool by index across all toolsets."""
        # Leverage iteration instead of manual index tracking
        for i, tool in enumerate(self):
            if i == index:
                return tool
        raise IndexError("ToolsetWrapper index out of range")

    def __add__(self, other):
        """Add another toolset or tool to this wrapper."""
        if isinstance(other, Toolset):
            return _ToolsetWrapper(self.toolsets + [other])
        if isinstance(other, Tool):
            return _ToolsetWrapper(self.toolsets + [Toolset([other])])
        if isinstance(other, list) and all(isinstance(item, Tool) for item in other):
            return _ToolsetWrapper(self.toolsets + [Toolset(other)])
        raise TypeError(f"Cannot add {type(other).__name__} to ToolsetWrapper")

1	# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
2	#
3	# SPDX-License-Identifier: Apache-2.0
4
5	from dataclasses import dataclass, field	1✔
6	from typing import Any, Iterator, Union	1✔
7
8	from haystack.core.serialization import generate_qualified_class_name, import_class_by_name	1✔
9	from haystack.tools.tool import Tool, _check_duplicate_tool_names	1✔
10
11
12	@dataclass	1✔
13	class Toolset:	1✔
14	"""
15	A collection of related Tools that can be used and managed as a cohesive unit.
16
17	Toolset serves two main purposes:
18
19	1. Group related tools together:
20	Toolset allows you to organize related tools into a single collection, making it easier
21	to manage and use them as a unit in Haystack pipelines.
22
23	Example:
24	```python
25	from haystack.tools import Tool, Toolset
26	from haystack.components.tools import ToolInvoker
27
28	# Define math functions
29	def add_numbers(a: int, b: int) -> int:
30	return a + b
31
32	def subtract_numbers(a: int, b: int) -> int:
33	return a - b
34
35	# Create tools with proper schemas
36	add_tool = Tool(
37	name="add",
38	description="Add two numbers",
39	parameters={
40	"type": "object",
41	"properties": {
42	"a": {"type": "integer"},
43	"b": {"type": "integer"}
44	},
45	"required": ["a", "b"]
46	},
47	function=add_numbers
48	)
49
50	subtract_tool = Tool(
51	name="subtract",
52	description="Subtract b from a",
53	parameters={
54	"type": "object",
55	"properties": {
56	"a": {"type": "integer"},
57	"b": {"type": "integer"}
58	},
59	"required": ["a", "b"]
60	},
61	function=subtract_numbers
62	)
63
64	# Create a toolset with the math tools
65	math_toolset = Toolset([add_tool, subtract_tool])
66
67	# Use the toolset with a ToolInvoker or ChatGenerator component
68	invoker = ToolInvoker(tools=math_toolset)
69	```
70
71	2. Base class for dynamic tool loading:
72	By subclassing Toolset, you can create implementations that dynamically load tools
73	from external sources like OpenAPI URLs, MCP servers, or other resources.
74
75	Example:
76	```python
77	from haystack.core.serialization import generate_qualified_class_name
78	from haystack.tools import Tool, Toolset
79	from haystack.components.tools import ToolInvoker
80
81	class CalculatorToolset(Toolset):
82	'''A toolset for calculator operations.'''
83
84	def __init__(self):
85	tools = self._create_tools()
86	super().__init__(tools)
87
88	def _create_tools(self):
89	# These Tool instances are obviously defined statically and for illustration purposes only.
90	# In a real-world scenario, you would dynamically load tools from an external source here.
91	tools = []
92	add_tool = Tool(
93	name="add",
94	description="Add two numbers",
95	parameters={
96	"type": "object",
97	"properties": {"a": {"type": "integer"}, "b": {"type": "integer"}},
98	"required": ["a", "b"],
99	},
100	function=lambda a, b: a + b,
101	)
102
103	multiply_tool = Tool(
104	name="multiply",
105	description="Multiply two numbers",
106	parameters={
107	"type": "object",
108	"properties": {"a": {"type": "integer"}, "b": {"type": "integer"}},
109	"required": ["a", "b"],
110	},
111	function=lambda a, b: a * b,
112	)
113
114	tools.append(add_tool)
115	tools.append(multiply_tool)
116
117	return tools
118
119	def to_dict(self):
120	return {
121	"type": generate_qualified_class_name(type(self)),
122	"data": {}, # no data to serialize as we define the tools dynamically
123	}
124
125	@classmethod
126	def from_dict(cls, data):
127	return cls() # Recreate the tools dynamically during deserialization
128
129	# Create the dynamic toolset and use it with ToolInvoker
130	calculator_toolset = CalculatorToolset()
131	invoker = ToolInvoker(tools=calculator_toolset)
132	```
133
134	Toolset implements the collection interface (__iter__, __contains__, __len__, __getitem__),
135	making it behave like a list of Tools. This makes it compatible with components that expect
136	iterable tools, such as ToolInvoker or Haystack chat generators.
137
138	When implementing a custom Toolset subclass for dynamic tool loading:
139	- Perform the dynamic loading in the __init__ method
140	- Override to_dict() and from_dict() methods if your tools are defined dynamically
141	- Serialize endpoint descriptors rather than tool instances if your tools
142	are loaded from external sources
143	"""
144
145	# Use field() with default_factory to initialize the list
146	tools: list[Tool] = field(default_factory=list)	1✔
147
148	def __post_init__(self):	1✔
149	"""
150	Validate and set up the toolset after initialization.
151
152	This handles the case when tools are provided during initialization.
153	"""
154	# If initialization was done a single Tool, raise an error
155	if isinstance(self.tools, Tool):	1✔
156	raise TypeError("A single Tool cannot be directly passed to Toolset. Please use a list: Toolset([tool])")	×
157
158	# Check for duplicate tool names in the initial set
159	_check_duplicate_tool_names(self.tools)	1✔
160
161	def __iter__(self) -> Iterator[Tool]:	1✔
162	"""
163	Return an iterator over the Tools in this Toolset.
164
165	This allows the Toolset to be used wherever a list of Tools is expected.
166
167	:returns: An iterator yielding Tool instances
168	"""
169	return iter(self.tools)	1✔
170
171	def __contains__(self, item: Any) -> bool:	1✔
172	"""
173	Check if a tool is in this Toolset.
174
175	Supports checking by:
176	- Tool instance: tool in toolset
177	- Tool name: "tool_name" in toolset
178
179	:param item: Tool instance or tool name string
180	:returns: True if contained, False otherwise
181	"""
182	if isinstance(item, str):	1✔
183	return any(tool.name == item for tool in self.tools)	1✔
184	if isinstance(item, Tool):	1✔
185	return item in self.tools	1✔
186	return False	×
187
188	def warm_up(self) -> None:	1✔
189	"""
190	Prepare the Toolset for use.
191
192	By default, this method iterates through and warms up all tools in the Toolset.
193	Subclasses can override this method to customize initialization behavior, such as:
194
195	- Setting up shared resources (database connections, HTTP sessions) instead of
196	warming individual tools
197	- Implementing custom initialization logic for dynamically loaded tools
198	- Controlling when and how tools are initialized
199
200	For example, a Toolset that manages tools from an external service (like MCPToolset)
201	might override this to initialize a shared connection rather than warming up
202	individual tools:
203
204	```python
205	class MCPToolset(Toolset):
206	def warm_up(self) -> None:
207	# Only warm up the shared MCP connection, not individual tools
208	self.mcp_connection = establish_connection(self.server_url)
209	```
210
211	This method should be idempotent, as it may be called multiple times.
212	"""
213	for tool in self.tools:	1✔
214	if hasattr(tool, "warm_up"):	1✔
215	tool.warm_up()	1✔
216
217	def add(self, tool: Union[Tool, "Toolset"]) -> None:	1✔
218	"""
219	Add a new Tool or merge another Toolset.
220
221	:param tool: A Tool instance or another Toolset to add
222	:raises ValueError: If adding the tool would result in duplicate tool names
223	:raises TypeError: If the provided object is not a Tool or Toolset
224	"""
225	new_tools = []	1✔
226
227	if isinstance(tool, Tool):	1✔
228	new_tools = [tool]	1✔
229	elif isinstance(tool, Toolset):	×
230	new_tools = list(tool)	×
231	else:
232	raise TypeError(f"Expected Tool or Toolset, got {type(tool).__name__}")	×
233
234	# Check for duplicates before adding
235	combined_tools = self.tools + new_tools	1✔
236	_check_duplicate_tool_names(combined_tools)	1✔
237
238	self.tools.extend(new_tools)	1✔
239
240	def to_dict(self) -> dict[str, Any]:	1✔
241	"""
242	Serialize the Toolset to a dictionary.
243
244	:returns: A dictionary representation of the Toolset
245
246	Note for subclass implementers:
247	The default implementation is ideal for scenarios where Tool resolution is static. However, if your subclass
248	of Toolset dynamically resolves Tool instances from external sources—such as an MCP server, OpenAPI URL, or
249	a local OpenAPI specification—you should consider serializing the endpoint descriptor instead of the Tool
250	instances themselves. This strategy preserves the dynamic nature of your Toolset and minimizes the overhead
251	associated with serializing potentially large collections of Tool objects. Moreover, by serializing the
252	descriptor, you ensure that the deserialization process can accurately reconstruct the Tool instances, even
253	if they have been modified or removed since the last serialization. Failing to serialize the descriptor may
254	lead to issues where outdated or incorrect Tool configurations are loaded, potentially causing errors or
255	unexpected behavior.
256	"""
257	return {	1✔
258	"type": generate_qualified_class_name(type(self)),
259	"data": {"tools": [tool.to_dict() for tool in self.tools]},
260	}
261
262	@classmethod	1✔
263	def from_dict(cls, data: dict[str, Any]) -> "Toolset":	1✔
264	"""
265	Deserialize a Toolset from a dictionary.
266
267	:param data: Dictionary representation of the Toolset
268	:returns: A new Toolset instance
269	"""
270	inner_data = data["data"]	1✔
271	tools_data = inner_data.get("tools", [])	1✔
272
273	tools = []	1✔
274	for tool_data in tools_data:	1✔
275	tool_class = import_class_by_name(tool_data["type"])	1✔
276	if not issubclass(tool_class, Tool):	1✔
277	raise TypeError(f"Class '{tool_class}' is not a subclass of Tool")	×
278	tools.append(tool_class.from_dict(tool_data))	1✔
279
280	return cls(tools=tools)	1✔
281
282	def __add__(self, other: Union[Tool, "Toolset", list[Tool]]) -> "Toolset":	1✔
283	"""
284	Concatenate this Toolset with another Tool, Toolset, or list of Tools.
285
286	:param other: Another Tool, Toolset, or list of Tools to concatenate
287	:returns: A new Toolset containing all tools
288	:raises TypeError: If the other parameter is not a Tool, Toolset, or list of Tools
289	:raises ValueError: If the combination would result in duplicate tool names
290	"""
291	if isinstance(other, Tool):	1✔
292	return Toolset(tools=self.tools + [other])	1✔
293	if isinstance(other, Toolset):	1✔
294	return _ToolsetWrapper([self, other])	1✔
295	if isinstance(other, list) and all(isinstance(item, Tool) for item in other):	1✔
296	return Toolset(tools=self.tools + other)	1✔
297	raise TypeError(f"Cannot add {type(other).__name__} to Toolset")	1✔
298
299	def __len__(self) -> int:	1✔
300	"""
301	Return the number of Tools in this Toolset.
302
303	:returns: Number of Tools
304	"""
305	return len(self.tools)	1✔
306
307	def __getitem__(self, index):	1✔
308	"""
309	Get a Tool by index.
310
311	:param index: Index of the Tool to get
312	:returns: The Tool at the specified index
313	"""
314	return self.tools[index]	1✔
315
316
317	class _ToolsetWrapper(Toolset):	1✔
318	"""
319	A wrapper that holds multiple toolsets and provides a unified interface.
320
321	This is used internally when combining different types of toolsets to preserve
322	their individual configurations while still being usable with ToolInvoker.
323	"""
324
325	def __init__(self, toolsets: list[Toolset]):	1✔
326	super().__init__([tool for toolset in toolsets for tool in toolset])	1✔
327	self.toolsets = toolsets	1✔
328
329	def __iter__(self):	1✔
330	"""Iterate over all tools from all toolsets."""
331	for toolset in self.toolsets:	1✔
332	yield from toolset	1✔
333
334	def __contains__(self, item):	1✔
335	"""Check if a tool is in any of the toolsets."""
336	return any(item in toolset for toolset in self.toolsets)	1✔
337
338	def warm_up(self):	1✔
339	"""Warm up all toolsets."""
340	for toolset in self.toolsets:	1✔
341	toolset.warm_up()	1✔
342
343	def __len__(self):	1✔
344	"""Return total number of tools across all toolsets."""
345	return sum(len(toolset) for toolset in self.toolsets)	1✔
346
347	def __getitem__(self, index):	1✔
348	"""Get a tool by index across all toolsets."""
349	# Leverage iteration instead of manual index tracking
350	for i, tool in enumerate(self):	×
351	if i == index:	×
352	return tool	×
353	raise IndexError("ToolsetWrapper index out of range")	×
354
355	def __add__(self, other):	1✔
356	"""Add another toolset or tool to this wrapper."""
357	if isinstance(other, Toolset):	1✔
358	return _ToolsetWrapper(self.toolsets + [other])	1✔
359	if isinstance(other, Tool):	1✔
360	return _ToolsetWrapper(self.toolsets + [Toolset([other])])	1✔
361	if isinstance(other, list) and all(isinstance(item, Tool) for item in other):	×
362	return _ToolsetWrapper(self.toolsets + [Toolset(other)])	×
363	raise TypeError(f"Cannot add {type(other).__name__} to ToolsetWrapper")	×

deepset-ai / haystack / 19114177728

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous