16143753132

Committed 08 Jul 2025 12:51PM UTC coverage: 90.433%. Remained the same

Build # 16143753132

Build Type

push

github

Committed by

web-flow

Commit Message

docs: fix curly brackets (#9599)

Run Details

11684 of 12920 relevant lines covered (90.43%)

0.9 hits per line

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

94.74

haystack/tools/component_tool.py

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

from typing import Any, Callable, Dict, Optional, Union, get_args, get_origin

from pydantic import Field, TypeAdapter, create_model

from haystack import logging
from haystack.core.component import Component
from haystack.core.serialization import (
    component_from_dict,
    component_to_dict,
    generate_qualified_class_name,
    import_class_by_name,
)
from haystack.tools import Tool
from haystack.tools.errors import SchemaGenerationError
from haystack.tools.from_function import _remove_title_from_schema
from haystack.tools.parameters_schema_utils import _get_component_param_descriptions, _resolve_type
from haystack.utils.callable_serialization import deserialize_callable, serialize_callable

logger = logging.getLogger(__name__)


class ComponentTool(Tool):
    """
    A Tool that wraps Haystack components, allowing them to be used as tools by LLMs.

    ComponentTool automatically generates LLM-compatible tool schemas from component input sockets,
    which are derived from the component's `run` method signature and type hints.


    Key features:
    - Automatic LLM tool calling schema generation from component input sockets
    - Type conversion and validation for component inputs
    - Support for types:
        - Dataclasses
        - Lists of dataclasses
        - Basic types (str, int, float, bool, dict)
        - Lists of basic types
    - Automatic name generation from component class name
    - Description extraction from component docstrings

    To use ComponentTool, you first need a Haystack component - either an existing one or a new one you create.
    You can create a ComponentTool from the component by passing the component to the ComponentTool constructor.
    Below is an example of creating a ComponentTool from an existing SerperDevWebSearch component.

    ```python
    from haystack import component, Pipeline
    from haystack.tools import ComponentTool
    from haystack.components.websearch import SerperDevWebSearch
    from haystack.utils import Secret
    from haystack.components.tools.tool_invoker import ToolInvoker
    from haystack.components.generators.chat import OpenAIChatGenerator
    from haystack.dataclasses import ChatMessage

    # Create a SerperDev search component
    search = SerperDevWebSearch(api_key=Secret.from_env_var("SERPERDEV_API_KEY"), top_k=3)

    # Create a tool from the component
    tool = ComponentTool(
        component=search,
        name="web_search",  # Optional: defaults to "serper_dev_web_search"
        description="Search the web for current information on any topic"  # Optional: defaults to component docstring
    )

    # Create pipeline with OpenAIChatGenerator and ToolInvoker
    pipeline = Pipeline()
    pipeline.add_component("llm", OpenAIChatGenerator(model="gpt-4o-mini", tools=[tool]))
    pipeline.add_component("tool_invoker", ToolInvoker(tools=[tool]))

    # Connect components
    pipeline.connect("llm.replies", "tool_invoker.messages")

    message = ChatMessage.from_user("Use the web search tool to find information about Nikola Tesla")

    # Run pipeline
    result = pipeline.run({"llm": {"messages": [message]}})

    print(result)
    ```

    """

    def __init__(
        self,
        component: Component,
        name: Optional[str] = None,
        description: Optional[str] = None,
        parameters: Optional[Dict[str, Any]] = None,
        *,
        outputs_to_string: Optional[Dict[str, Union[str, Callable[[Any], str]]]] = None,
        inputs_from_state: Optional[Dict[str, str]] = None,
        outputs_to_state: Optional[Dict[str, Dict[str, Union[str, Callable]]]] = None,
    ):
        """
        Create a Tool instance from a Haystack component.

        :param component: The Haystack component to wrap as a tool.
        :param name: Optional name for the tool (defaults to snake_case of component class name).
        :param description: Optional description (defaults to component's docstring).
        :param parameters:
            A JSON schema defining the parameters expected by the Tool.
            Will fall back to the parameters defined in the component's run method signature if not provided.
        :param outputs_to_string:
            Optional dictionary defining how a tool outputs should be converted into a string.
            If the source is provided only the specified output key is sent to the handler.
            If the source is omitted the whole tool result is sent to the handler.
            Example:
            ```python
            {
                "source": "docs", "handler": format_documents
            }
            ```
        :param inputs_from_state:
            Optional dictionary mapping state keys to tool parameter names.
            Example: `{"repository": "repo"}` maps state's "repository" to tool's "repo" parameter.
        :param outputs_to_state:
            Optional dictionary defining how tool outputs map to keys within state as well as optional handlers.
            If the source is provided only the specified output key is sent to the handler.
            Example:
            ```python
            {
                "documents": {"source": "docs", "handler": custom_handler}
            }
            ```
            If the source is omitted the whole tool result is sent to the handler.
            Example:
            ```python
            {
                "documents": {"handler": custom_handler}
            }
            ```
        :raises ValueError: If the component is invalid or schema generation fails.
        """
        if not isinstance(component, Component):
            message = (
                f"Object {component!r} is not a Haystack component. "
                "Use ComponentTool only with Haystack component instances."
            )
            raise ValueError(message)

        if getattr(component, "__haystack_added_to_pipeline__", None):
            msg = (
                "Component has been added to a pipeline and can't be used to create a ComponentTool. "
                "Create ComponentTool from a non-pipeline component instead."
            )
            raise ValueError(msg)

        self._unresolved_parameters = parameters
        # Create the tools schema from the component run method parameters
        tool_schema = parameters or self._create_tool_parameters_schema(component, inputs_from_state or {})

        def component_invoker(**kwargs):
            """
            Invokes the component using keyword arguments provided by the LLM function calling/tool-generated response.

            :param kwargs: The keyword arguments to invoke the component with.
            :returns: The result of the component invocation.
            """
            converted_kwargs = {}
            input_sockets = component.__haystack_input__._sockets_dict  # type: ignore[attr-defined]
            for param_name, param_value in kwargs.items():
                param_type = input_sockets[param_name].type

                # Check if the type (or list element type) has from_dict
                target_type = get_args(param_type)[0] if get_origin(param_type) is list else param_type
                if hasattr(target_type, "from_dict"):
                    if isinstance(param_value, list):
                        resolved_param_value = [
                            target_type.from_dict(item) if isinstance(item, dict) else item for item in param_value
                        ]
                    elif isinstance(param_value, dict):
                        resolved_param_value = target_type.from_dict(param_value)
                    else:
                        resolved_param_value = param_value
                else:
                    # Let TypeAdapter handle both single values and lists
                    type_adapter = TypeAdapter(param_type)
                    resolved_param_value = type_adapter.validate_python(param_value)

                converted_kwargs[param_name] = resolved_param_value
            logger.debug(f"Invoking component {type(component)} with kwargs: {converted_kwargs}")
            return component.run(**converted_kwargs)

        # Generate a name for the tool if not provided
        if not name:
            class_name = component.__class__.__name__
            # Convert camelCase/PascalCase to snake_case
            name = "".join(
                [
                    "_" + c.lower() if c.isupper() and i > 0 and not class_name[i - 1].isupper() else c.lower()
                    for i, c in enumerate(class_name)
                ]
            ).lstrip("_")

        description = description or component.__doc__ or name

        # Create the Tool instance with the component invoker as the function to be called and the schema
        super().__init__(
            name=name,
            description=description,
            parameters=tool_schema,
            function=component_invoker,
            inputs_from_state=inputs_from_state,
            outputs_to_state=outputs_to_state,
            outputs_to_string=outputs_to_string,
        )
        self._component = component

    def to_dict(self) -> Dict[str, Any]:
        """
        Serializes the ComponentTool to a dictionary.
        """
        serialized_component = component_to_dict(obj=self._component, name=self.name)

        serialized: Dict[str, Any] = {
            "component": serialized_component,
            "name": self.name,
            "description": self.description,
            "parameters": self._unresolved_parameters,
            "inputs_from_state": self.inputs_from_state,
            # This is soft-copied as to not modify the attributes in place
            "outputs_to_state": self.outputs_to_state.copy() if self.outputs_to_state else None,
        }

        if self.outputs_to_state is not None:
            serialized_outputs = {}
            for key, config in self.outputs_to_state.items():
                serialized_config = config.copy()
                if "handler" in config:
                    serialized_config["handler"] = serialize_callable(config["handler"])
                serialized_outputs[key] = serialized_config
            serialized["outputs_to_state"] = serialized_outputs

        if self.outputs_to_string is not None and self.outputs_to_string.get("handler") is not None:
            # This is soft-copied as to not modify the attributes in place
            serialized["outputs_to_string"] = self.outputs_to_string.copy()
            serialized["outputs_to_string"]["handler"] = serialize_callable(self.outputs_to_string["handler"])
        else:
            serialized["outputs_to_string"] = None

        return {"type": generate_qualified_class_name(type(self)), "data": serialized}

    @classmethod
    def from_dict(cls, data: Dict[str, Any]) -> "Tool":
        """
        Deserializes the ComponentTool from a dictionary.
        """
        inner_data = data["data"]
        component_class = import_class_by_name(inner_data["component"]["type"])
        component = component_from_dict(cls=component_class, data=inner_data["component"], name=inner_data["name"])

        if "outputs_to_state" in inner_data and inner_data["outputs_to_state"]:
            deserialized_outputs = {}
            for key, config in inner_data["outputs_to_state"].items():
                deserialized_config = config.copy()
                if "handler" in config:
                    deserialized_config["handler"] = deserialize_callable(config["handler"])
                deserialized_outputs[key] = deserialized_config
            inner_data["outputs_to_state"] = deserialized_outputs

        if (
            inner_data.get("outputs_to_string") is not None
            and inner_data["outputs_to_string"].get("handler") is not None
        ):
            inner_data["outputs_to_string"]["handler"] = deserialize_callable(
                inner_data["outputs_to_string"]["handler"]
            )

        return cls(
            component=component,
            name=inner_data["name"],
            description=inner_data["description"],
            parameters=inner_data.get("parameters", None),
            outputs_to_string=inner_data.get("outputs_to_string", None),
            inputs_from_state=inner_data.get("inputs_from_state", None),
            outputs_to_state=inner_data.get("outputs_to_state", None),
        )

    def _create_tool_parameters_schema(self, component: Component, inputs_from_state: Dict[str, Any]) -> Dict[str, Any]:
        """
        Creates an OpenAI tools schema from a component's run method parameters.

        :param component: The component to create the schema from.
        :raises SchemaGenerationError: If schema generation fails
        :returns: OpenAI tools schema for the component's run method parameters.
        """
        component_run_description, param_descriptions = _get_component_param_descriptions(component)

        # collect fields (types and defaults) and descriptions from function parameters
        fields: Dict[str, Any] = {}

        for input_name, socket in component.__haystack_input__._sockets_dict.items():  # type: ignore[attr-defined]
            if inputs_from_state is not None and input_name in inputs_from_state:
                continue
            input_type = socket.type
            description = param_descriptions.get(input_name, f"Input '{input_name}' for the component.")

            # if the parameter has not a default value, Pydantic requires an Ellipsis (...)
            # to explicitly indicate that the parameter is required
            default = ... if socket.is_mandatory else socket.default_value
            resolved_type = _resolve_type(input_type)
            fields[input_name] = (resolved_type, Field(default=default, description=description))

        parameters_schema: Dict[str, Any] = {}
        try:
            model = create_model(component.run.__name__, __doc__=component_run_description, **fields)
            parameters_schema = model.model_json_schema()
        except Exception as e:
            raise SchemaGenerationError(
                f"Failed to create JSON schema for the run method of Component '{component.__class__.__name__}'"
            ) from e

        # we don't want to include title keywords in the schema, as they contain redundant information
        # there is no programmatic way to prevent Pydantic from adding them, so we remove them later
        # see https://github.com/pydantic/pydantic/discussions/8504
        _remove_title_from_schema(parameters_schema)

        return parameters_schema

1	# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
2	#
3	# SPDX-License-Identifier: Apache-2.0
4
5	from typing import Any, Callable, Dict, Optional, Union, get_args, get_origin	1✔
6
7	from pydantic import Field, TypeAdapter, create_model	1✔
8
9	from haystack import logging	1✔
10	from haystack.core.component import Component	1✔
11	from haystack.core.serialization import (	1✔
12	component_from_dict,
13	component_to_dict,
14	generate_qualified_class_name,
15	import_class_by_name,
16	)
17	from haystack.tools import Tool	1✔
18	from haystack.tools.errors import SchemaGenerationError	1✔
19	from haystack.tools.from_function import _remove_title_from_schema	1✔
20	from haystack.tools.parameters_schema_utils import _get_component_param_descriptions, _resolve_type	1✔
21	from haystack.utils.callable_serialization import deserialize_callable, serialize_callable	1✔
22
23	logger = logging.getLogger(__name__)	1✔
24
25
26	class ComponentTool(Tool):	1✔
27	"""
28	A Tool that wraps Haystack components, allowing them to be used as tools by LLMs.
29
30	ComponentTool automatically generates LLM-compatible tool schemas from component input sockets,
31	which are derived from the component's `run` method signature and type hints.
32
33
34	Key features:
35	- Automatic LLM tool calling schema generation from component input sockets
36	- Type conversion and validation for component inputs
37	- Support for types:
38	- Dataclasses
39	- Lists of dataclasses
40	- Basic types (str, int, float, bool, dict)
41	- Lists of basic types
42	- Automatic name generation from component class name
43	- Description extraction from component docstrings
44
45	To use ComponentTool, you first need a Haystack component - either an existing one or a new one you create.
46	You can create a ComponentTool from the component by passing the component to the ComponentTool constructor.
47	Below is an example of creating a ComponentTool from an existing SerperDevWebSearch component.
48
49	```python
50	from haystack import component, Pipeline
51	from haystack.tools import ComponentTool
52	from haystack.components.websearch import SerperDevWebSearch
53	from haystack.utils import Secret
54	from haystack.components.tools.tool_invoker import ToolInvoker
55	from haystack.components.generators.chat import OpenAIChatGenerator
56	from haystack.dataclasses import ChatMessage
57
58	# Create a SerperDev search component
59	search = SerperDevWebSearch(api_key=Secret.from_env_var("SERPERDEV_API_KEY"), top_k=3)
60
61	# Create a tool from the component
62	tool = ComponentTool(
63	component=search,
64	name="web_search", # Optional: defaults to "serper_dev_web_search"
65	description="Search the web for current information on any topic" # Optional: defaults to component docstring
66	)
67
68	# Create pipeline with OpenAIChatGenerator and ToolInvoker
69	pipeline = Pipeline()
70	pipeline.add_component("llm", OpenAIChatGenerator(model="gpt-4o-mini", tools=[tool]))
71	pipeline.add_component("tool_invoker", ToolInvoker(tools=[tool]))
72
73	# Connect components
74	pipeline.connect("llm.replies", "tool_invoker.messages")
75
76	message = ChatMessage.from_user("Use the web search tool to find information about Nikola Tesla")
77
78	# Run pipeline
79	result = pipeline.run({"llm": {"messages": [message]}})
80
81	print(result)
82	```
83
84	"""
85
86	def __init__(	1✔
87	self,
88	component: Component,
89	name: Optional[str] = None,
90	description: Optional[str] = None,
91	parameters: Optional[Dict[str, Any]] = None,
92	*,
93	outputs_to_string: Optional[Dict[str, Union[str, Callable[[Any], str]]]] = None,
94	inputs_from_state: Optional[Dict[str, str]] = None,
95	outputs_to_state: Optional[Dict[str, Dict[str, Union[str, Callable]]]] = None,
96	):
97	"""
98	Create a Tool instance from a Haystack component.
99
100	:param component: The Haystack component to wrap as a tool.
101	:param name: Optional name for the tool (defaults to snake_case of component class name).
102	:param description: Optional description (defaults to component's docstring).
103	:param parameters:
104	A JSON schema defining the parameters expected by the Tool.
105	Will fall back to the parameters defined in the component's run method signature if not provided.
106	:param outputs_to_string:
107	Optional dictionary defining how a tool outputs should be converted into a string.
108	If the source is provided only the specified output key is sent to the handler.
109	If the source is omitted the whole tool result is sent to the handler.
110	Example:
111	```python
112	{
113	"source": "docs", "handler": format_documents
114	}
115	```
116	:param inputs_from_state:
117	Optional dictionary mapping state keys to tool parameter names.
118	Example: `{"repository": "repo"}` maps state's "repository" to tool's "repo" parameter.
119	:param outputs_to_state:
120	Optional dictionary defining how tool outputs map to keys within state as well as optional handlers.
121	If the source is provided only the specified output key is sent to the handler.
122	Example:
123	```python
124	{
125	"documents": {"source": "docs", "handler": custom_handler}
126	}
127	```
128	If the source is omitted the whole tool result is sent to the handler.
129	Example:
130	```python
131	{
132	"documents": {"handler": custom_handler}
133	}
134	```
135	:raises ValueError: If the component is invalid or schema generation fails.
136	"""
137	if not isinstance(component, Component):	1✔
138	message = (	1✔
139	f"Object {component!r} is not a Haystack component. "
140	"Use ComponentTool only with Haystack component instances."
141	)
142	raise ValueError(message)	1✔
143
144	if getattr(component, "__haystack_added_to_pipeline__", None):	1✔
145	msg = (	1✔
146	"Component has been added to a pipeline and can't be used to create a ComponentTool. "
147	"Create ComponentTool from a non-pipeline component instead."
148	)
149	raise ValueError(msg)	1✔
150
151	self._unresolved_parameters = parameters	1✔
152	# Create the tools schema from the component run method parameters
153	tool_schema = parameters or self._create_tool_parameters_schema(component, inputs_from_state or {})	1✔
154
155	def component_invoker(**kwargs):	1✔
156	"""
157	Invokes the component using keyword arguments provided by the LLM function calling/tool-generated response.
158
159	:param kwargs: The keyword arguments to invoke the component with.
160	:returns: The result of the component invocation.
161	"""
162	converted_kwargs = {}	1✔
163	input_sockets = component.__haystack_input__._sockets_dict # type: ignore[attr-defined]	1✔
164	for param_name, param_value in kwargs.items():	1✔
165	param_type = input_sockets[param_name].type	1✔
166
167	# Check if the type (or list element type) has from_dict
168	target_type = get_args(param_type)[0] if get_origin(param_type) is list else param_type	1✔
169	if hasattr(target_type, "from_dict"):	1✔
170	if isinstance(param_value, list):	1✔
171	resolved_param_value = [	1✔
172	target_type.from_dict(item) if isinstance(item, dict) else item for item in param_value
173	]
174	elif isinstance(param_value, dict):	×
175	resolved_param_value = target_type.from_dict(param_value)	×
176	else:
177	resolved_param_value = param_value	×
178	else:
179	# Let TypeAdapter handle both single values and lists
180	type_adapter = TypeAdapter(param_type)	1✔
181	resolved_param_value = type_adapter.validate_python(param_value)	1✔
182
183	converted_kwargs[param_name] = resolved_param_value	1✔
184	logger.debug(f"Invoking component {type(component)} with kwargs: {converted_kwargs}")	1✔
185	return component.run(**converted_kwargs)	1✔
186
187	# Generate a name for the tool if not provided
188	if not name:	1✔
189	class_name = component.__class__.__name__	1✔
190	# Convert camelCase/PascalCase to snake_case
191	name = "".join(	1✔
192	[
193	"_" + c.lower() if c.isupper() and i > 0 and not class_name[i - 1].isupper() else c.lower()
194	for i, c in enumerate(class_name)
195	]
196	).lstrip("_")
197
198	description = description or component.__doc__ or name	1✔
199
200	# Create the Tool instance with the component invoker as the function to be called and the schema
201	super().__init__(	1✔
202	name=name,
203	description=description,
204	parameters=tool_schema,
205	function=component_invoker,
206	inputs_from_state=inputs_from_state,
207	outputs_to_state=outputs_to_state,
208	outputs_to_string=outputs_to_string,
209	)
210	self._component = component	1✔
211
212	def to_dict(self) -> Dict[str, Any]:	1✔
213	"""
214	Serializes the ComponentTool to a dictionary.
215	"""
216	serialized_component = component_to_dict(obj=self._component, name=self.name)	1✔
217
218	serialized: Dict[str, Any] = {	1✔
219	"component": serialized_component,
220	"name": self.name,
221	"description": self.description,
222	"parameters": self._unresolved_parameters,
223	"inputs_from_state": self.inputs_from_state,
224	# This is soft-copied as to not modify the attributes in place
225	"outputs_to_state": self.outputs_to_state.copy() if self.outputs_to_state else None,
226	}
227
228	if self.outputs_to_state is not None:	1✔
229	serialized_outputs = {}	1✔
230	for key, config in self.outputs_to_state.items():	1✔
231	serialized_config = config.copy()	1✔
232	if "handler" in config:	1✔
233	serialized_config["handler"] = serialize_callable(config["handler"])	1✔
234	serialized_outputs[key] = serialized_config	1✔
235	serialized["outputs_to_state"] = serialized_outputs	1✔
236
237	if self.outputs_to_string is not None and self.outputs_to_string.get("handler") is not None:	1✔
238	# This is soft-copied as to not modify the attributes in place
239	serialized["outputs_to_string"] = self.outputs_to_string.copy()	1✔
240	serialized["outputs_to_string"]["handler"] = serialize_callable(self.outputs_to_string["handler"])	1✔
241	else:
242	serialized["outputs_to_string"] = None	1✔
243
244	return {"type": generate_qualified_class_name(type(self)), "data": serialized}	1✔
245
246	@classmethod	1✔
247	def from_dict(cls, data: Dict[str, Any]) -> "Tool":	1✔
248	"""
249	Deserializes the ComponentTool from a dictionary.
250	"""
251	inner_data = data["data"]	1✔
252	component_class = import_class_by_name(inner_data["component"]["type"])	1✔
253	component = component_from_dict(cls=component_class, data=inner_data["component"], name=inner_data["name"])	1✔
254
255	if "outputs_to_state" in inner_data and inner_data["outputs_to_state"]:	1✔
256	deserialized_outputs = {}	1✔
257	for key, config in inner_data["outputs_to_state"].items():	1✔
258	deserialized_config = config.copy()	1✔
259	if "handler" in config:	1✔
260	deserialized_config["handler"] = deserialize_callable(config["handler"])	1✔
261	deserialized_outputs[key] = deserialized_config	1✔
262	inner_data["outputs_to_state"] = deserialized_outputs	1✔
263
264	if (	1✔
265	inner_data.get("outputs_to_string") is not None
266	and inner_data["outputs_to_string"].get("handler") is not None
267	):
268	inner_data["outputs_to_string"]["handler"] = deserialize_callable(	1✔
269	inner_data["outputs_to_string"]["handler"]
270	)
271
272	return cls(	1✔
273	component=component,
274	name=inner_data["name"],
275	description=inner_data["description"],
276	parameters=inner_data.get("parameters", None),
277	outputs_to_string=inner_data.get("outputs_to_string", None),
278	inputs_from_state=inner_data.get("inputs_from_state", None),
279	outputs_to_state=inner_data.get("outputs_to_state", None),
280	)
281
282	def _create_tool_parameters_schema(self, component: Component, inputs_from_state: Dict[str, Any]) -> Dict[str, Any]:	1✔
283	"""
284	Creates an OpenAI tools schema from a component's run method parameters.
285
286	:param component: The component to create the schema from.
287	:raises SchemaGenerationError: If schema generation fails
288	:returns: OpenAI tools schema for the component's run method parameters.
289	"""
290	component_run_description, param_descriptions = _get_component_param_descriptions(component)	1✔
291
292	# collect fields (types and defaults) and descriptions from function parameters
293	fields: Dict[str, Any] = {}	1✔
294
295	for input_name, socket in component.__haystack_input__._sockets_dict.items(): # type: ignore[attr-defined]	1✔
296	if inputs_from_state is not None and input_name in inputs_from_state:	1✔
297	continue	1✔
298	input_type = socket.type	1✔
299	description = param_descriptions.get(input_name, f"Input '{input_name}' for the component.")	1✔
300
301	# if the parameter has not a default value, Pydantic requires an Ellipsis (...)
302	# to explicitly indicate that the parameter is required
303	default = ... if socket.is_mandatory else socket.default_value	1✔
304	resolved_type = _resolve_type(input_type)	1✔
305	fields[input_name] = (resolved_type, Field(default=default, description=description))	1✔
306
307	parameters_schema: Dict[str, Any] = {}	1✔
308	try:	1✔
309	model = create_model(component.run.__name__, __doc__=component_run_description, **fields)	1✔
310	parameters_schema = model.model_json_schema()	1✔
311	except Exception as e:	×
312	raise SchemaGenerationError(	×
313	f"Failed to create JSON schema for the run method of Component '{component.__class__.__name__}'"
314	) from e
315
316	# we don't want to include title keywords in the schema, as they contain redundant information
317	# there is no programmatic way to prevent Pydantic from adding them, so we remove them later
318	# see https://github.com/pydantic/pydantic/discussions/8504
319	_remove_title_from_schema(parameters_schema)	1✔
320
321	return parameters_schema	1✔

deepset-ai / haystack / 16143753132

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