Skip to content

Class swarmauri_standard.llms.LLM.LLM

swarmauri_standard.llms.LLM.LLM

LLM(**data)

Bases: LLMBase

Generic LLM class for interacting with various language model APIs. This class provides synchronous and asynchronous methods to send conversation data to the model, receive predictions, and stream responses.

ATTRIBUTE DESCRIPTION
api_key

API key for authenticating requests to the API.

TYPE: SecretStr

allowed_models

List of allowed model names that can be used.

TYPE: List[str]

name

The default model name to use for predictions.

TYPE: str

type

The type identifier for this class.

TYPE: Literal[LLM]

BASE_URL

The base URL for API requests.

TYPE: str

timeout

Timeout for API requests in seconds.

TYPE: float

Initialize the LLM class with the provided data.

PARAMETER DESCRIPTION
**data

Arbitrary keyword arguments containing initialization data. Should include api_key, and optionally name, BASE_URL, timeout.

DEFAULT: {}

Source code in swarmauri_standard/llms/LLM.py
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
def __init__(self, **data) -> None:
    """
    Initialize the LLM class with the provided data.

    Args:
        **data: Arbitrary keyword arguments containing initialization data.
               Should include api_key, and optionally name, BASE_URL, timeout.
    """
    super().__init__(**data)

    # Set up headers for API requests
    self._headers = {
        "Authorization": f"Bearer {self.api_key.get_secret_value()}",
        "Content-Type": "application/json",
    }

    # Load allowed models and set default if needed
    if not self.allowed_models:
        self.allowed_models = self.get_allowed_models()

    if not self.name and self.allowed_models:
        self.name = self.allowed_models[0]

allowed_models instance-attribute

allowed_models = get_allowed_models()

name instance-attribute

name = allowed_models[0]

type class-attribute instance-attribute

type = 'LLMBase'

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="allow", 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=LLM.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

api_key class-attribute instance-attribute

api_key = None

timeout class-attribute instance-attribute

timeout = 600.0

include_usage class-attribute instance-attribute

include_usage = True

BASE_URL class-attribute instance-attribute

BASE_URL = None

predict

predict(
    conversation,
    temperature=0.7,
    max_tokens=256,
    top_p=1.0,
    enable_json=False,
    stop=None,
)

Generates a response from the model based on the given conversation.

PARAMETER DESCRIPTION
conversation

Conversation object with message history.

TYPE: Conversation

temperature

Sampling temperature for response diversity.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum tokens for the model's response.

TYPE: int DEFAULT: 256

top_p

Cumulative probability for nucleus sampling.

TYPE: float DEFAULT: 1.0

enable_json

Whether to format the response as JSON.

TYPE: bool DEFAULT: False

stop

List of stop sequences for response termination.

TYPE: Optional[List[str]] DEFAULT: None

RETURNS DESCRIPTION
Conversation

Updated conversation with the model's response.

TYPE: Conversation

Source code in swarmauri_standard/llms/LLM.py
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
@retry_on_status_codes((429, 529), max_retries=3)
def predict(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
    top_p: float = 1.0,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> Conversation:
    """
    Generates a response from the model based on the given conversation.

    Args:
        conversation (Conversation): Conversation object with message history.
        temperature (float): Sampling temperature for response diversity.
        max_tokens (int): Maximum tokens for the model's response.
        top_p (float): Cumulative probability for nucleus sampling.
        enable_json (bool): Whether to format the response as JSON.
        stop (Optional[List[str]]): List of stop sequences for response termination.

    Returns:
        Conversation: Updated conversation with the model's response.
    """
    formatted_messages = self._format_messages(conversation.history)

    # Prepare the payload
    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "temperature": temperature,
        "max_tokens": max_tokens,
        "top_p": top_p,
        "stop": stop or [],
    }

    # Add JSON response format if requested
    if enable_json:
        payload["response_format"] = {"type": "json_object"}

    # Make the API request and measure time
    with DurationManager() as prompt_timer:
        with httpx.Client(timeout=self.timeout) as client:
            response = client.post(
                self.BASE_URL, headers=self._headers, json=payload
            )
            response.raise_for_status()

    # Parse the response
    response_data = response.json()
    message_content = response_data["choices"][0]["message"]["content"]
    usage_data = response_data.get("usage", {})

    # Prepare usage data if tracking is enabled
    if self.include_usage:
        usage = self._prepare_usage_data(usage_data, prompt_timer.duration)
        conversation.add_message(AgentMessage(content=message_content, usage=usage))
    else:
        conversation.add_message(AgentMessage(content=message_content))
    return conversation

apredict async

apredict(
    conversation,
    temperature=0.7,
    max_tokens=256,
    top_p=1.0,
    enable_json=False,
    stop=None,
)

Async method to generate a response from the model based on the given conversation.

PARAMETER DESCRIPTION
conversation

Conversation object with message history.

TYPE: Conversation

temperature

Sampling temperature for response diversity.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum tokens for the model's response.

TYPE: int DEFAULT: 256

top_p

Cumulative probability for nucleus sampling.

TYPE: float DEFAULT: 1.0

enable_json

Whether to format the response as JSON.

TYPE: bool DEFAULT: False

stop

List of stop sequences for response termination.

TYPE: Optional[List[str]] DEFAULT: None

RETURNS DESCRIPTION
Conversation

Updated conversation with the model's response.

TYPE: Conversation

Source code in swarmauri_standard/llms/LLM.py
177
178
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
@retry_on_status_codes((429, 529), max_retries=3)
async def apredict(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
    top_p: float = 1.0,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> Conversation:
    """
    Async method to generate a response from the model based on the given conversation.

    Args:
        conversation (Conversation): Conversation object with message history.
        temperature (float): Sampling temperature for response diversity.
        max_tokens (int): Maximum tokens for the model's response.
        top_p (float): Cumulative probability for nucleus sampling.
        enable_json (bool): Whether to format the response as JSON.
        stop (Optional[List[str]]): List of stop sequences for response termination.

    Returns:
        Conversation: Updated conversation with the model's response.
    """
    formatted_messages = self._format_messages(conversation.history)

    # Prepare the payload
    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "temperature": temperature,
        "max_tokens": max_tokens,
        "top_p": top_p,
        "stop": stop or [],
    }

    # Add JSON response format if requested
    if enable_json:
        payload["response_format"] = {"type": "json_object"}

    # Make the async API request and measure time
    with DurationManager() as prompt_timer:
        async with httpx.AsyncClient(timeout=self.timeout) as client:
            response = await client.post(
                self.BASE_URL, headers=self._headers, json=payload
            )
            response.raise_for_status()

    # Parse the response
    response_data = response.json()
    message_content = response_data["choices"][0]["message"]["content"]
    usage_data = response_data.get("usage", {})

    # Prepare usage data if tracking is enabled
    if self.include_usage:
        usage = self._prepare_usage_data(usage_data, prompt_timer.duration)
        conversation.add_message(AgentMessage(content=message_content, usage=usage))
    else:
        conversation.add_message(AgentMessage(content=message_content))

    return conversation

stream

stream(
    conversation,
    temperature=0.7,
    max_tokens=256,
    top_p=1.0,
    enable_json=False,
    stop=None,
)

Streams response text from the model in real-time.

PARAMETER DESCRIPTION
conversation

Conversation object with message history.

TYPE: Conversation

temperature

Sampling temperature for response diversity.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum tokens for the model's response.

TYPE: int DEFAULT: 256

top_p

Cumulative probability for nucleus sampling.

TYPE: float DEFAULT: 1.0

enable_json

Whether to format the response as JSON.

TYPE: bool DEFAULT: False

stop

List of stop sequences for response termination.

TYPE: Optional[List[str]] DEFAULT: None

YIELDS DESCRIPTION
str

Partial response content from the model.

TYPE:: str

Source code in swarmauri_standard/llms/LLM.py
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
270
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
@retry_on_status_codes((429, 529), max_retries=3)
def stream(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
    top_p: float = 1.0,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> Generator[str, None, None]:
    """
    Streams response text from the model in real-time.

    Args:
        conversation (Conversation): Conversation object with message history.
        temperature (float): Sampling temperature for response diversity.
        max_tokens (int): Maximum tokens for the model's response.
        top_p (float): Cumulative probability for nucleus sampling.
        enable_json (bool): Whether to format the response as JSON.
        stop (Optional[List[str]]): List of stop sequences for response termination.

    Yields:
        str: Partial response content from the model.
    """
    formatted_messages = self._format_messages(conversation.history)

    # Prepare the payload with stream flag
    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "temperature": temperature,
        "max_tokens": max_tokens,
        "top_p": top_p,
        "stream": True,
        "stop": stop or [],
    }

    if enable_json:
        payload["response_format"] = {"type": "json_object"}

    if self.include_usage:
        payload["stream_options"] = {"include_usage": True}

    # Start timing for prompt processing
    with DurationManager() as prompt_timer:
        with httpx.Client(timeout=self.timeout) as client:
            response = client.post(
                self.BASE_URL, headers=self._headers, json=payload
            )
            response.raise_for_status()

    # Process the streaming response
    message_content = ""
    usage_data = {}

    with DurationManager() as completion_timer:
        for line in response.iter_lines():
            if line.startswith("data: "):
                json_str = line.replace("data: ", "")  # Remove 'data: ' prefix

                if json_str.strip() == "[DONE]":
                    break

                try:
                    if json_str:
                        chunk = json.loads(json_str)
                        if (
                            "choices" in chunk
                            and chunk["choices"]
                            and "delta" in chunk["choices"][0]
                        ):
                            delta = chunk["choices"][0]["delta"]
                            if "content" in delta:
                                content = delta["content"]
                                message_content += content
                                yield content

                        # Collect usage data if available
                        if (
                            self.include_usage
                            and "usage" in chunk
                            and chunk["usage"] is not None
                        ):
                            usage_data = chunk["usage"]

                except json.JSONDecodeError:
                    pass

    # Add the complete message to the conversation
    if self.include_usage:
        usage = self._prepare_usage_data(
            usage_data, prompt_timer.duration, completion_timer.duration
        )
        conversation.add_message(AgentMessage(content=message_content, usage=usage))
    else:
        conversation.add_message(AgentMessage(content=message_content))

astream async

astream(
    conversation,
    temperature=0.7,
    max_tokens=256,
    top_p=1.0,
    enable_json=False,
    stop=None,
)

Async generator that streams response text from the model in real-time.

PARAMETER DESCRIPTION
conversation

Conversation object with message history.

TYPE: Conversation

temperature

Sampling temperature for response diversity.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum tokens for the model's response.

TYPE: int DEFAULT: 256

top_p

Cumulative probability for nucleus sampling.

TYPE: float DEFAULT: 1.0

enable_json

Whether to format the response as JSON.

TYPE: bool DEFAULT: False

stop

List of stop sequences for response termination.

TYPE: Optional[List[str]] DEFAULT: None

YIELDS DESCRIPTION
str

Partial response content from the model.

TYPE:: AsyncGenerator[str, None]

Source code in swarmauri_standard/llms/LLM.py
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
363
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
@retry_on_status_codes((429, 529), max_retries=3)
async def astream(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
    top_p: float = 1.0,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> AsyncGenerator[str, None]:
    """
    Async generator that streams response text from the model in real-time.

    Args:
        conversation (Conversation): Conversation object with message history.
        temperature (float): Sampling temperature for response diversity.
        max_tokens (int): Maximum tokens for the model's response.
        top_p (float): Cumulative probability for nucleus sampling.
        enable_json (bool): Whether to format the response as JSON.
        stop (Optional[List[str]]): List of stop sequences for response termination.

    Yields:
        str: Partial response content from the model.
    """
    formatted_messages = self._format_messages(conversation.history)

    # Prepare the payload with stream flag
    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "temperature": temperature,
        "max_tokens": max_tokens,
        "top_p": top_p,
        "stream": True,
        "stop": stop or [],
    }

    if enable_json:
        payload["response_format"] = {"type": "json_object"}

    if self.include_usage:
        payload["stream_options"] = {"include_usage": True}

    # Start timing for prompt processing
    with DurationManager() as prompt_timer:
        async with httpx.AsyncClient(timeout=self.timeout) as client:
            response = await client.post(
                self.BASE_URL, headers=self._headers, json=payload
            )
            response.raise_for_status()

    # Process the streaming response asynchronously
    message_content = ""
    usage_data = {}

    with DurationManager() as completion_timer:
        async for line in response.aiter_lines():
            if line.startswith("data: "):
                json_str = line[6:]  # Remove 'data: ' prefix

                if json_str.strip() == "[DONE]":
                    break

                try:
                    if json_str:
                        chunk = json.loads(json_str)
                        if (
                            "choices" in chunk
                            and chunk["choices"]
                            and "delta" in chunk["choices"][0]
                        ):
                            delta = chunk["choices"][0]["delta"]
                            if "content" in delta:
                                content = delta["content"]
                                message_content += content
                                yield content

                        # Collect usage data if available
                        if (
                            self.include_usage
                            and "usage" in chunk
                            and chunk["usage"] is not None
                        ):
                            usage_data = chunk["usage"]

                except json.JSONDecodeError:
                    pass

    # Add the complete message to the conversation
    if self.include_usage:
        usage = self._prepare_usage_data(
            usage_data, prompt_timer.duration, completion_timer.duration
        )
        conversation.add_message(AgentMessage(content=message_content, usage=usage))
    else:
        conversation.add_message(AgentMessage(content=message_content))

batch

batch(
    conversations,
    temperature=0.7,
    max_tokens=256,
    top_p=1.0,
    enable_json=False,
    stop=None,
)

Processes a batch of conversations and generates responses for each sequentially.

PARAMETER DESCRIPTION
conversations

List of conversations to process.

TYPE: List[Conversation]

temperature

Sampling temperature for response diversity.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum tokens for each response.

TYPE: int DEFAULT: 256

top_p

Cumulative probability for nucleus sampling.

TYPE: float DEFAULT: 1.0

enable_json

Whether to format the response as JSON.

TYPE: bool DEFAULT: False

stop

List of stop sequences for response termination.

TYPE: Optional[List[str]] DEFAULT: None

RETURNS DESCRIPTION
List[Conversation]

List[Conversation]: List of updated conversations with model responses.

Source code in swarmauri_standard/llms/LLM.py
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
def batch(
    self,
    conversations: List[Conversation],
    temperature: float = 0.7,
    max_tokens: int = 256,
    top_p: float = 1.0,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> List[Conversation]:
    """
    Processes a batch of conversations and generates responses for each sequentially.

    Args:
        conversations (List[Conversation]): List of conversations to process.
        temperature (float): Sampling temperature for response diversity.
        max_tokens (int): Maximum tokens for each response.
        top_p (float): Cumulative probability for nucleus sampling.
        enable_json (bool): Whether to format the response as JSON.
        stop (Optional[List[str]]): List of stop sequences for response termination.

    Returns:
        List[Conversation]: List of updated conversations with model responses.
    """
    results = []
    for conversation in conversations:
        result_conversation = self.predict(
            conversation,
            temperature=temperature,
            max_tokens=max_tokens,
            top_p=top_p,
            enable_json=enable_json,
            stop=stop,
        )
        results.append(result_conversation)
    return results

abatch async

abatch(
    conversations,
    temperature=0.7,
    max_tokens=256,
    top_p=1.0,
    enable_json=False,
    stop=None,
    max_concurrent=5,
)

Async method for processing a batch of conversations concurrently.

PARAMETER DESCRIPTION
conversations

List of conversations to process.

TYPE: List[Conversation]

temperature

Sampling temperature for response diversity.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum tokens for each response.

TYPE: int DEFAULT: 256

top_p

Cumulative probability for nucleus sampling.

TYPE: float DEFAULT: 1.0

enable_json

Whether to format the response as JSON.

TYPE: bool DEFAULT: False

stop

List of stop sequences for response termination.

TYPE: Optional[List[str]] DEFAULT: None

max_concurrent

Maximum number of concurrent requests.

TYPE: int DEFAULT: 5

RETURNS DESCRIPTION
List[Conversation]

List[Conversation]: List of updated conversations with model responses.

Source code in swarmauri_standard/llms/LLM.py
469
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
async def abatch(
    self,
    conversations: List[Conversation],
    temperature: float = 0.7,
    max_tokens: int = 256,
    top_p: float = 1.0,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
    max_concurrent: int = 5,
) -> List[Conversation]:
    """
    Async method for processing a batch of conversations concurrently.

    Args:
        conversations (List[Conversation]): List of conversations to process.
        temperature (float): Sampling temperature for response diversity.
        max_tokens (int): Maximum tokens for each response.
        top_p (float): Cumulative probability for nucleus sampling.
        enable_json (bool): Whether to format the response as JSON.
        stop (Optional[List[str]]): List of stop sequences for response termination.
        max_concurrent (int): Maximum number of concurrent requests.

    Returns:
        List[Conversation]: List of updated conversations with model responses.
    """
    semaphore = asyncio.Semaphore(max_concurrent)

    async def process_conversation(conv: Conversation) -> Conversation:
        async with semaphore:
            return await self.apredict(
                conv,
                temperature=temperature,
                max_tokens=max_tokens,
                top_p=top_p,
                enable_json=enable_json,
                stop=stop,
            )

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

get_allowed_models

get_allowed_models()

Returns a list of allowed models for this LLM provider.

This default implementation returns a static list. Provider-specific subclasses should override this to query their respective APIs.

RETURNS DESCRIPTION
List[str]

List[str]: List of allowed model names.

Source code in swarmauri_standard/llms/LLM.py
510
511
512
513
514
515
516
517
518
519
520
def get_allowed_models(self) -> List[str]:
    """
    Returns a list of allowed models for this LLM provider.

    This default implementation returns a static list. Provider-specific
    subclasses should override this to query their respective APIs.

    Returns:
        List[str]: List of allowed model names.
    """
    return ["gpt-4", "gpt-3.5-turbo", "claude-3-5-sonnet-20240229"]

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/llms/LLMBase.py
36
37
38
39
40
41
42
43
44
45
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/llms/LLMBase.py
47
48
49
50
51
52
53
54
55
56
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)