Skip to content

Class swarmauri_standard.tool_llms.AnthropicToolModel.AnthropicToolModel

swarmauri_standard.tool_llms.AnthropicToolModel.AnthropicToolModel

AnthropicToolModel(**data)

Bases: ToolLLMBase

A model class for integrating with the Anthropic API to enable tool-assisted AI interactions.

This class supports various functionalities, including synchronous and asynchronous message prediction, streaming responses, and batch processing of conversations. It utilizes Anthropic's schema and tool-conversion techniques to facilitate enhanced interactions involving tool usage within conversations.

ATTRIBUTE DESCRIPTION
api_key

The API key used for authenticating requests to the Anthropic API.

TYPE: str

allowed_models

A list of allowed model versions that can be used.

TYPE: List[str]

name

The default model name used for predictions.

TYPE: str

type

The type of the model, which is set to "AnthropicToolModel".

TYPE: Literal

Linked to Allowed Models: https://docs.anthropic.com/en/docs/build-with-claude/tool-use Link to API KEY: https://console.anthropic.com/settings/keys

Source code in swarmauri_standard/tool_llms/AnthropicToolModel.py
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
def __init__(self, **data: dict[str, Any]):
    super().__init__(**data)
    self._headers = {
        "Content-Type": "application/json",
        "x-api-key": self.api_key.get_secret_value(),
        "anthropic-version": "2023-06-01",
    }
    self._client = httpx.Client(
        headers=self._headers, base_url=self.BASE_URL, timeout=self.timeout
    )
    self._async_client = httpx.AsyncClient(
        headers=self._headers, base_url=self.BASE_URL, timeout=self.timeout
    )

    self.allowed_models = self.allowed_models or self.get_allowed_models()
    self.name = self.name or self.allowed_models[0]

BASE_URL class-attribute instance-attribute

BASE_URL = 'https://api.anthropic.com/v1'

api_key instance-attribute

api_key

type class-attribute instance-attribute

type = 'AnthropicToolModel'

allowed_models class-attribute instance-attribute

allowed_models = allowed_models or get_allowed_models()

name class-attribute instance-attribute

name = name or allowed_models[0]

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="forbid", arbitrary_types_allowed=True
)

id class-attribute instance-attribute

id = Field(default_factory=generate_id)

members class-attribute instance-attribute

members = None

owners class-attribute instance-attribute

owners = None

host class-attribute instance-attribute

host = None

default_logger class-attribute

default_logger = None

logger class-attribute instance-attribute

logger = None

resource class-attribute instance-attribute

resource = Field(default=TOOL_LLM.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

timeout class-attribute instance-attribute

timeout = 600.0

get_schema_converter

get_schema_converter()

Returns the schema converter class for Anthropic API.

RETURNS DESCRIPTION
Type[SchemaConverterBase]

Type[SchemaConverterBase]: The AnthropicSchemaConverter class.

Source code in swarmauri_standard/tool_llms/AnthropicToolModel.py
82
83
84
85
86
87
88
89
def get_schema_converter(self) -> Type[SchemaConverterBase]:
    """
    Returns the schema converter class for Anthropic API.

    Returns:
        Type[SchemaConverterBase]: The AnthropicSchemaConverter class.
    """
    return AnthropicSchemaConverter

predict

predict(
    conversation,
    toolkit,
    tool_choice,
    multiturn=True,
    temperature=0.7,
    max_tokens=1024,
)

Predicts the response based on the given conversation and optional toolkit.

PARAMETER DESCRIPTION
conversation

The current conversation object.

TYPE: IConversation

toolkit

Optional toolkit object containing tools for tool-based responses.

TYPE: Toolkit

tool_choice

Optional parameter to choose specific tools or set to 'auto' for automatic tool usage.

TYPE: dict[str, Any]

multiturn

Whether to process multiple turns in a single call.

TYPE: bool DEFAULT: True

temperature

The temperature for the model's output randomness.

TYPE: float DEFAULT: 0.7

max_tokens

The maximum number of tokens in the response.

TYPE: int DEFAULT: 1024

RETURNS DESCRIPTION
IConversation

The updated conversation with the assistant's response.

TYPE: Conversation

Source code in swarmauri_standard/tool_llms/AnthropicToolModel.py
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
def predict(
    self,
    conversation: Conversation,
    toolkit: Toolkit,
    tool_choice: dict[str, Any],
    multiturn: bool = True,
    temperature: float = 0.7,
    max_tokens: int = 1024,
) -> Conversation:
    """
    Predicts the response based on the given conversation and optional toolkit.

    Args:
        conversation (IConversation): The current conversation object.
        toolkit: Optional toolkit object containing tools for tool-based responses.
        tool_choice: Optional parameter to choose specific tools or set to 'auto' for automatic tool usage.
        multiturn (bool): Whether to process multiple turns in a single call.
        temperature (float): The temperature for the model's output randomness.
        max_tokens (int): The maximum number of tokens in the response.

    Returns:
        IConversation: The updated conversation with the assistant's response.
    """
    formatted_messages = self._format_messages(conversation.history)

    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "temperature": temperature,
        "max_tokens": max_tokens,
        "tools": self._schema_convert_tools(toolkit.tools) if toolkit else None,
        "tool_choice": tool_choice if toolkit and tool_choice else {"type": "auto"},
    }

    response = self._client.post("/messages", json=payload)
    response.raise_for_status()
    response_data = response.json()

    # Extract text content if available
    tool_text_response = None
    if response_data["content"] and response_data["content"][0]["type"] == "text":
        tool_text_response = response_data["content"][0]["text"]
        logging.info(f"tool_text_response: {tool_text_response}")

    # Process tool calls
    tool_calls = [c for c in response_data["content"] if c["type"] == "tool_use"]
    messages = formatted_messages.copy()

    messages.append(
        {
            "role": "assistant",
            "content": response_data["content"],
        }
    )

    messages, tool_messages = self._process_tool_calls(
        tool_calls, toolkit, messages
    )

    conversation.add_messages(tool_messages)

    # For multiturn, we need to make a follow-up request with the tool results
    if multiturn and tool_calls:
        # Create a new payload without tools
        followup_payload = {
            "model": self.name,
            "messages": messages,
            "temperature": temperature,
            "max_tokens": max_tokens,
        }

        logging.info(f"messages: {messages}")

        followup_response = self._client.post("/messages", json=followup_payload)
        logging.info(f"response: {followup_response.json()}")

        followup_response.raise_for_status()
        followup_data = followup_response.json()

        if (
            followup_data["content"]
            and followup_data["content"][0]["type"] == "text"
        ):
            tool_text_response = followup_data["content"][0]["text"]

    # Create and add the agent message
    if tool_text_response:
        agent_message = AgentMessage(content=tool_text_response)
        conversation.add_message(agent_message)

    return conversation

apredict async

apredict(
    conversation,
    toolkit,
    tool_choice,
    multiturn=True,
    temperature=0.7,
    max_tokens=1024,
)

Asynchronous version of the predict method to handle concurrent processing of requests.

PARAMETER DESCRIPTION
conversation

The current conversation object.

TYPE: IConversation

toolkit

Optional toolkit object containing tools for tool-based responses.

TYPE: Toolkit

tool_choice

Optional parameter to choose specific tools or set to 'auto' for automatic tool usage.

TYPE: dict[str, Any]

multiturn

Whether to process multiple turns in a single call.

TYPE: bool DEFAULT: True

temperature

The temperature for the model's output randomness.

TYPE: float DEFAULT: 0.7

max_tokens

The maximum number of tokens in the response.

TYPE: int DEFAULT: 1024

RETURNS DESCRIPTION
IConversation

The updated conversation with the assistant's response.

TYPE: IConversation

Source code in swarmauri_standard/tool_llms/AnthropicToolModel.py
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
@retry_on_status_codes((429, 529), max_retries=1)
async def apredict(
    self,
    conversation: Conversation,
    toolkit: Toolkit,
    tool_choice: dict[str, Any],
    multiturn: bool = True,
    temperature: float = 0.7,
    max_tokens: int = 1024,
) -> IConversation:
    """
    Asynchronous version of the `predict` method to handle concurrent processing of requests.

    Args:
        conversation (IConversation): The current conversation object.
        toolkit: Optional toolkit object containing tools for tool-based responses.
        tool_choice: Optional parameter to choose specific tools or set to 'auto' for automatic tool usage.
        multiturn (bool): Whether to process multiple turns in a single call.
        temperature (float): The temperature for the model's output randomness.
        max_tokens (int): The maximum number of tokens in the response.

    Returns:
        IConversation: The updated conversation with the assistant's response.
    """
    formatted_messages = self._format_messages(conversation.history)
    logging.info(f"formatted_messages: {formatted_messages}")

    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "temperature": temperature,
        "max_tokens": max_tokens,
        "tools": self._schema_convert_tools(toolkit.tools) if toolkit else None,
        "tool_choice": tool_choice if toolkit and tool_choice else {"type": "auto"},
    }

    response = await self._async_client.post("/messages", json=payload)
    response.raise_for_status()
    response_data = response.json()

    logging.info(f"tool_response: {response_data}")

    # Extract text content if available
    tool_text_response = None
    if response_data["content"] and response_data["content"][0]["type"] == "text":
        tool_text_response = response_data["content"][0]["text"]
        logging.info(f"tool_text_response: {tool_text_response}")

    # Process tool calls
    tool_calls = [c for c in response_data["content"] if c["type"] == "tool_use"]
    messages = formatted_messages.copy()
    messages.append(
        {
            "role": "assistant",
            "content": response_data["content"],
        }
    )

    messages, tool_messages = self._process_tool_calls(
        tool_calls, toolkit, messages
    )

    conversation.add_messages(tool_messages)

    # For multiturn, we need to make a follow-up request with the tool results
    if multiturn and tool_calls:
        # Create a new payload without tools
        followup_payload = {
            "model": self.name,
            "messages": messages,
            "temperature": temperature,
            "max_tokens": max_tokens,
        }

        followup_response = await self._async_client.post(
            "/messages", json=followup_payload
        )
        followup_response.raise_for_status()
        followup_data = followup_response.json()

        if (
            followup_data["content"]
            and followup_data["content"][0]["type"] == "text"
        ):
            tool_text_response = followup_data["content"][0]["text"]

    # Create and add the agent message
    if tool_text_response:
        agent_message = AgentMessage(content=tool_text_response)
        conversation.add_message(agent_message)

    return conversation

stream

stream(
    conversation,
    toolkit,
    tool_choice,
    temperature=0.7,
    max_tokens=1024,
)

Streams the response for a conversation in real-time, yielding text as it is received.

PARAMETER DESCRIPTION
conversation

The current conversation object.

TYPE: IConversation

toolkit

Optional toolkit object for tool-based responses.

TYPE: Toolkit

tool_choice

Optional parameter to choose specific tools or set to 'auto'.

TYPE: dict[str, Any]

temperature

Controls randomness in the output.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum tokens in the response.

TYPE: int DEFAULT: 1024

YIELDS DESCRIPTION
str

Iterator[str]: Chunks of text received from the streaming response.

Source code in swarmauri_standard/tool_llms/AnthropicToolModel.py
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
def stream(
    self,
    conversation: Conversation,
    toolkit: Toolkit,
    tool_choice: dict[str, Any],
    temperature: float = 0.7,
    max_tokens: int = 1024,
) -> Iterator[str]:
    """
    Streams the response for a conversation in real-time, yielding text as it is received.

    Args:
        conversation (IConversation): The current conversation object.
        toolkit: Optional toolkit object for tool-based responses.
        tool_choice: Optional parameter to choose specific tools or set to 'auto'.
        temperature (float): Controls randomness in the output.
        max_tokens (int): Maximum tokens in the response.

    Yields:
        Iterator[str]: Chunks of text received from the streaming response.
    """
    formatted_messages = self._format_messages(conversation.history)

    # First, handle any tool calls that might be needed
    tool_payload = {
        "model": self.name,
        "messages": formatted_messages,
        "temperature": temperature,
        "max_tokens": max_tokens,
        "tools": self._schema_convert_tools(toolkit.tools) if toolkit else None,
        "tool_choice": tool_choice if toolkit and tool_choice else {"type": "auto"},
    }

    response = self._client.post("/messages", json=tool_payload)
    response.raise_for_status()
    tool_response_data = response.json()

    tool_calls = [
        c for c in tool_response_data["content"] if c["type"] == "tool_use"
    ]
    messages = formatted_messages.copy()

    if tool_calls:
        messages.append(
            {
                "role": "assistant",
                "content": tool_response_data["content"],
            }
        )

        messages, tool_messages = self._process_tool_calls(
            tool_calls, toolkit, messages
        )
        conversation.add_messages(tool_messages)

    stream_payload = {
        "model": self.name,
        "messages": messages,
        "temperature": temperature,
        "max_tokens": max_tokens,
        "stream": True,
    }

    message_content = ""

    with self._client.stream("POST", "/messages", json=stream_payload) as response:
        response.raise_for_status()

        for line in response.iter_lines():
            if not line:
                continue

            line_text = line.decode("utf-8") if isinstance(line, bytes) else line

            if not line_text.startswith("data: "):
                continue

            json_str = line_text.removeprefix("data: ").strip()
            if not json_str or json_str == "[DONE]":
                continue

            try:
                event = json.loads(json_str)

                if event["type"] == "content_block_delta":
                    if "delta" in event and "text" in event["delta"].get(
                        "type", ""
                    ):
                        delta_text = event["delta"].get("text", "")
                        if delta_text:
                            message_content += delta_text
                            yield delta_text

                elif event["type"] == "tool_use":
                    logging.info(f"Tool use event in stream: {event}")

            except json.JSONDecodeError as e:
                logging.warning(
                    f"Error parsing stream event: {e}\nLine: {line_text}"
                )

    if message_content:
        conversation.add_message(AgentMessage(content=message_content))

    return conversation

astream async

astream(
    conversation,
    toolkit,
    tool_choice,
    temperature=0.7,
    max_tokens=1024,
)

Asynchronously streams the response for a conversation, yielding text in real-time.

PARAMETER DESCRIPTION
conversation

The current conversation object.

TYPE: IConversation

toolkit

Optional toolkit object for tool-based responses.

TYPE: Toolkit

tool_choice

Optional parameter to choose specific tools or set to 'auto'.

TYPE: dict[str, Any]

temperature

Controls randomness in the output.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum tokens in the response.

TYPE: int DEFAULT: 1024

YIELDS DESCRIPTION
AsyncIterator[str]

AsyncIterator[str]: Chunks of text received from the streaming response.

Source code in swarmauri_standard/tool_llms/AnthropicToolModel.py
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
async def astream(
    self,
    conversation: Conversation,
    toolkit: Toolkit,
    tool_choice: dict[str, Any],
    temperature: float = 0.7,
    max_tokens: int = 1024,
) -> AsyncIterator[str]:
    """
    Asynchronously streams the response for a conversation, yielding text in real-time.

    Args:
        conversation (IConversation): The current conversation object.
        toolkit: Optional toolkit object for tool-based responses.
        tool_choice: Optional parameter to choose specific tools or set to 'auto'.
        temperature (float): Controls randomness in the output.
        max_tokens (int): Maximum tokens in the response.

    Yields:
        AsyncIterator[str]: Chunks of text received from the streaming response.
    """
    formatted_messages = self._format_messages(conversation.history)

    tool_payload = {
        "model": self.name,
        "messages": formatted_messages,
        "temperature": temperature,
        "max_tokens": max_tokens,
        "tools": self._schema_convert_tools(toolkit.tools) if toolkit else None,
        "tool_choice": tool_choice if toolkit and tool_choice else {"type": "auto"},
    }

    response = await self._async_client.post("/messages", json=tool_payload)
    response.raise_for_status()
    tool_response_data = response.json()

    tool_calls = [
        c for c in tool_response_data["content"] if c["type"] == "tool_use"
    ]
    messages = formatted_messages.copy()

    if tool_calls:
        messages.append(
            {
                "role": "assistant",
                "content": tool_response_data["content"],
            }
        )

        messages, tool_messages = self._process_tool_calls(
            tool_calls, toolkit, messages
        )
        conversation.add_messages(tool_messages)

    stream_payload = {
        "model": self.name,
        "messages": messages,
        "temperature": temperature,
        "max_tokens": max_tokens,
        "stream": True,
    }

    message_content = ""

    async with self._async_client.stream(
        "POST", "/messages", json=stream_payload
    ) as response:
        response.raise_for_status()

        async for line in response.aiter_lines():
            if not line:
                continue

            if not line.startswith("data: "):
                continue

            json_str = line.removeprefix("data: ").strip()
            if not json_str or json_str == "[DONE]":
                continue

            try:
                event = json.loads(json_str)

                if event["type"] == "content_block_delta":
                    if (
                        "delta" in event
                        and event["delta"].get("type") == "text_delta"
                    ):
                        delta_text = event["delta"].get("text", "")
                        if delta_text:
                            message_content += delta_text
                            yield delta_text

            except json.JSONDecodeError as e:
                logging.warning(f"Error parsing stream event: {e}\nLine: {line}")

    if message_content:
        conversation.add_message(AgentMessage(content=message_content))

batch

batch(
    conversations,
    toolkit,
    tool_choice,
    temperature=0.7,
    max_tokens=1024,
)

Processes a batch of conversations in a synchronous manner.

PARAMETER DESCRIPTION
conversations

A list of conversation objects to process.

TYPE: List[IConversation]

toolkit

Optional toolkit object for tool-based responses.

TYPE: Toolkit

tool_choice

Optional parameter to choose specific tools or set to 'auto' for automatic tool usage.

TYPE: dict[str, Any]

temperature

The temperature for the model's output randomness.

TYPE: float DEFAULT: 0.7

max_tokens

The maximum number of tokens in the response.

TYPE: int DEFAULT: 1024

RETURNS DESCRIPTION
List[IConversation]

List[IConversation]: A list of conversation objects updated with the assistant's responses.

Source code in swarmauri_standard/tool_llms/AnthropicToolModel.py
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
def batch(
    self,
    conversations: List[Conversation],
    toolkit: Toolkit,
    tool_choice: dict[str, Any],
    temperature: float = 0.7,
    max_tokens: int = 1024,
) -> List[IConversation]:
    """
    Processes a batch of conversations in a synchronous manner.

    Args:
        conversations (List[IConversation]): A list of conversation objects to process.
        toolkit: Optional toolkit object for tool-based responses.
        tool_choice: Optional parameter to choose specific tools or set to 'auto' for automatic tool usage.
        temperature (float): The temperature for the model's output randomness.
        max_tokens (int): The maximum number of tokens in the response.

    Returns:
        List[IConversation]: A list of conversation objects updated with the assistant's responses.
    """
    results = []
    for conv in conversations:
        result = self.predict(
            conversation=conv,
            toolkit=toolkit,
            tool_choice=tool_choice,
            temperature=temperature,
            max_tokens=max_tokens,
        )
        results.append(result)
    return results

abatch async

abatch(
    conversations,
    toolkit,
    tool_choice,
    temperature=0.7,
    max_tokens=1024,
    max_concurrent=5,
)

Processes a batch of conversations asynchronously with limited concurrency.

PARAMETER DESCRIPTION
conversations

A list of conversation objects to process.

TYPE: List[IConversation]

toolkit

Optional toolkit object for tool-based responses.

TYPE: Toolkit

tool_choice

Optional parameter to choose specific tools or set to 'auto' for automatic tool usage.

TYPE: dict[str, Any]

temperature

The temperature for the model's output randomness.

TYPE: float DEFAULT: 0.7

max_tokens

The maximum number of tokens in the response.

TYPE: int DEFAULT: 1024

max_concurrent

The maximum number of concurrent processes allowed.

TYPE: int DEFAULT: 5

RETURNS DESCRIPTION
List[IConversation]

List[IConversation]: A list of conversation objects updated with the assistant's responses.

Source code in swarmauri_standard/tool_llms/AnthropicToolModel.py
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
async def abatch(
    self,
    conversations: List[Conversation],
    toolkit: Toolkit,
    tool_choice: dict[str, Any],
    temperature: float = 0.7,
    max_tokens: int = 1024,
    max_concurrent=5,
) -> List[IConversation]:
    """
    Processes a batch of conversations asynchronously with limited concurrency.

    Args:
        conversations (List[IConversation]): A list of conversation objects to process.
        toolkit: Optional toolkit object for tool-based responses.
        tool_choice: Optional parameter to choose specific tools or set to 'auto' for automatic tool usage.
        temperature (float): The temperature for the model's output randomness.
        max_tokens (int): The maximum number of tokens in the response.
        max_concurrent (int): The maximum number of concurrent processes allowed.

    Returns:
        List[IConversation]: A list of conversation objects updated with the assistant's responses.
    """
    semaphore = asyncio.Semaphore(max_concurrent)

    async def process_conversation(conv):
        async with semaphore:
            return await self.apredict(
                conv,
                toolkit=toolkit,
                tool_choice=tool_choice,
                temperature=temperature,
                max_tokens=max_tokens,
            )

    tasks = [process_conversation(conv) for conv in conversations]
    return await asyncio.gather(*tasks)

get_allowed_models

get_allowed_models()

Returns the list of allowed models for Anthropic API.

RETURNS DESCRIPTION
List[str]

List[str]: A list of allowed model names.

Source code in swarmauri_standard/tool_llms/AnthropicToolModel.py
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
def get_allowed_models(self) -> List[str]:
    """
    Returns the list of allowed models for Anthropic API.

    Returns:
        List[str]: A list of allowed model names.
    """
    allowed_models = [
        "claude-3-7-sonnet-latest",
        "claude-3-5-haiku-latest",
        "claude-3-5-sonnet-latest",
        "claude-3-opus-latest",
        "claude-3-5-sonnet-20241022",
        "claude-3-5-haiku-20241022",
        "claude-3-7-sonnet-20250219",
        "claude-3-5-sonnet-20240620",
        "claude-3-opus-20240229",
        "claude-3-sonnet-20240229",
        "claude-3-haiku-20240307",
    ]
    return allowed_models

register_model classmethod

register_model()

Decorator to register a base model in the unified registry.

RETURNS DESCRIPTION
Callable

A decorator function that registers the model class.

TYPE: Callable[[Type[BaseModel]], Type[BaseModel]]

Source code in swarmauri_base/DynamicBase.py
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
@classmethod
def register_model(cls) -> Callable[[Type[BaseModel]], Type[BaseModel]]:
    """
    Decorator to register a base model in the unified registry.

    Returns:
        Callable: A decorator function that registers the model class.
    """

    def decorator(model_cls: Type[BaseModel]):
        """Register ``model_cls`` as a base model."""
        model_name = model_cls.__name__
        if model_name in cls._registry:
            glogger.warning(
                "Model '%s' is already registered; skipping duplicate.", model_name
            )
            return model_cls

        cls._registry[model_name] = {"model_cls": model_cls, "subtypes": {}}
        glogger.debug("Registered base model '%s'.", model_name)
        DynamicBase._recreate_models()
        return model_cls

    return decorator

register_type classmethod

register_type(resource_type=None, type_name=None)

Decorator to register a subtype under one or more base models in the unified registry.

PARAMETER DESCRIPTION
resource_type

The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase) are used.

TYPE: Optional[Union[Type[T], List[Type[T]]]] DEFAULT: None

type_name

An optional custom type name for the subtype.

TYPE: Optional[str] DEFAULT: None

RETURNS DESCRIPTION
Callable

A decorator function that registers the subtype.

TYPE: Callable[[Type[DynamicBase]], Type[DynamicBase]]

Source code in swarmauri_base/DynamicBase.py
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
@classmethod
def register_type(
    cls,
    resource_type: Optional[Union[Type[T], List[Type[T]]]] = None,
    type_name: Optional[str] = None,
) -> Callable[[Type["DynamicBase"]], Type["DynamicBase"]]:
    """
    Decorator to register a subtype under one or more base models in the unified registry.

    Parameters:
        resource_type (Optional[Union[Type[T], List[Type[T]]]]):
            The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase)
            are used.
        type_name (Optional[str]): An optional custom type name for the subtype.

    Returns:
        Callable: A decorator function that registers the subtype.
    """

    def decorator(subclass: Type["DynamicBase"]):
        """Register ``subclass`` as a subtype."""
        if resource_type is None:
            resource_types = [
                base for base in subclass.__bases__ if base is not cls
            ]
        elif not isinstance(resource_type, list):
            resource_types = [resource_type]
        else:
            resource_types = resource_type

        for rt in resource_types:
            if not issubclass(subclass, rt):
                raise TypeError(
                    f"'{subclass.__name__}' must be a subclass of '{rt.__name__}'."
                )
            final_type_name = type_name or getattr(
                subclass, "_type", subclass.__name__
            )
            base_model_name = rt.__name__

            if base_model_name not in cls._registry:
                cls._registry[base_model_name] = {"model_cls": rt, "subtypes": {}}
                glogger.debug(
                    "Created new registry entry for base model '%s'.",
                    base_model_name,
                )

            subtypes_dict = cls._registry[base_model_name]["subtypes"]
            if final_type_name in subtypes_dict:
                glogger.warning(
                    "Type '%s' already exists under '%s'; skipping duplicate.",
                    final_type_name,
                    base_model_name,
                )
                continue

            subtypes_dict[final_type_name] = subclass
            glogger.debug(
                "Registered '%s' as '%s' under '%s'.",
                subclass.__name__,
                final_type_name,
                base_model_name,
            )

        DynamicBase._recreate_models()
        return subclass

    return decorator

model_validate_toml classmethod

model_validate_toml(toml_data)

Validate a model from a TOML string.

Source code in swarmauri_base/TomlMixin.py
12
13
14
15
16
17
18
19
20
21
22
23
24
@classmethod
def model_validate_toml(cls, toml_data: str):
    """Validate a model from a TOML string."""
    try:
        # Parse TOML into a Python dictionary
        toml_content = tomllib.loads(toml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(toml_content))
    except tomllib.TOMLDecodeError as e:
        raise ValueError(f"Invalid TOML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_toml

model_dump_toml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a TOML representation of the model.

Source code in swarmauri_base/TomlMixin.py
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
def model_dump_toml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a TOML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into TOML
    return toml.dumps(filtered_data)

model_validate_yaml classmethod

model_validate_yaml(yaml_data)

Validate a model from a YAML string.

Source code in swarmauri_base/YamlMixin.py
11
12
13
14
15
16
17
18
19
20
21
22
23
@classmethod
def model_validate_yaml(cls, yaml_data: str):
    """Validate a model from a YAML string."""
    try:
        # Parse YAML into a Python dictionary
        yaml_content = yaml.safe_load(yaml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(yaml_content))
    except yaml.YAMLError as e:
        raise ValueError(f"Invalid YAML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_yaml

model_dump_yaml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a YAML representation of the model.

Source code in swarmauri_base/YamlMixin.py
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
def model_dump_yaml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a YAML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into YAML using safe mode
    return yaml.safe_dump(filtered_data, default_flow_style=False)

model_post_init

model_post_init(logger=None)

Assign a logger instance after model initialization.

Source code in swarmauri_base/LoggerMixin.py
23
24
25
26
27
28
def model_post_init(self, logger: Optional[FullUnion[LoggerBase]] = None) -> None:
    """Assign a logger instance after model initialization."""

    # Directly assign the provided FullUnion[LoggerBase] or fallback to the
    # class-level default.
    self.logger = self.logger or logger or self.default_logger

add_allowed_model

add_allowed_model(model)

Add a new model to the list of allowed models.

RAISES DESCRIPTION
ValueError

If the model is already in the allowed models list.

Source code in swarmauri_base/tool_llms/ToolLLMBase.py
35
36
37
38
39
40
41
42
43
44
def add_allowed_model(self, model: str) -> None:
    """
    Add a new model to the list of allowed models.

    Raises:
        ValueError: If the model is already in the allowed models list.
    """
    if model in self.allowed_models:
        raise ValueError(f"Model '{model}' is already allowed.")
    self.allowed_models.append(model)

remove_allowed_model

remove_allowed_model(model)

Remove a model from the list of allowed models.

RAISES DESCRIPTION
ValueError

If the model is not in the allowed models list.

Source code in swarmauri_base/tool_llms/ToolLLMBase.py
46
47
48
49
50
51
52
53
54
55
def remove_allowed_model(self, model: str) -> None:
    """
    Remove a model from the list of allowed models.

    Raises:
        ValueError: If the model is not in the allowed models list.
    """
    if model not in self.allowed_models:
        raise ValueError(f"Model '{model}' is not in the allowed models list.")
    self.allowed_models.remove(model)