Skip to content

Class swarmauri_standard.llms.PerplexityModel.PerplexityModel

swarmauri_standard.llms.PerplexityModel.PerplexityModel

PerplexityModel(**data)

Bases: LLMBase

Represents a language model interface for Perplexity API.

Provides methods for synchronous and asynchronous predictions, streaming, and batch processing of conversations using the Perplexity language models.

ATTRIBUTE DESCRIPTION
api_key

API key for authenticating requests to the Perplexity 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['PerplexityModel']

timeout

Timeout for API requests in seconds.

TYPE: float

Provider resources: https://docs.perplexity.ai/guides/model-cards Link to deprecated models: https://docs.perplexity.ai/changelog/changelog#model-deprecation-notice

Initialize the GroqAIAudio class with the provided data.

PARAMETER DESCRIPTION
**data

Arbitrary keyword arguments containing initialization data.

TYPE: Dict[str, Any] DEFAULT: {}

Source code in swarmauri_standard/llms/PerplexityModel.py
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
def __init__(self, **data: Dict[str, Any]) -> None:
    """
    Initialize the GroqAIAudio class with the provided data.

    Args:
        **data (Dict[str, Any]): Arbitrary keyword arguments containing initialization data.
    """
    super().__init__(**data)
    self._client = httpx.Client(
        headers={"Authorization": f"Bearer {self.api_key.get_secret_value()}"},
        base_url=self._BASE_URL,
        timeout=self.timeout,
    )
    self._async_client = httpx.AsyncClient(
        headers={"Authorization": f"Bearer {self.api_key.get_secret_value()}"},
        base_url=self._BASE_URL,
        timeout=self.timeout,
    )

api_key instance-attribute

api_key

allowed_models class-attribute instance-attribute

allowed_models = [
    "sonar-reasoning-pro",
    "sonar-reasoning",
    "sonar-pro",
    "sonar",
]

name class-attribute instance-attribute

name = 'sonar'

type class-attribute instance-attribute

type = 'PerplexityModel'

timeout class-attribute instance-attribute

timeout = 600.0

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'

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=None,
    top_k=None,
    return_citations=False,
    presence_penalty=None,
    frequency_penalty=None,
)

Makes a synchronous prediction request.

PARAMETER DESCRIPTION
conversation

The conversation object containing the history.

TYPE: Conversation

temperature

Sampling temperature for response generation. Defaults to 0.7.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum number of tokens for the response. Defaults to 256.

TYPE: int DEFAULT: 256

top_p

Nucleus sampling parameter. If specified, top_k should not be set.

TYPE: Optional[float] DEFAULT: None

top_k

Top-k sampling parameter. If specified, top_p should not be set.

TYPE: Optional[int] DEFAULT: None

return_citations

Whether to return citations in the response. Defaults to False.

TYPE: bool DEFAULT: False

presence_penalty

Penalty for new tokens based on presence.

TYPE: Optional[float] DEFAULT: None

frequency_penalty

Penalty for new tokens based on frequency.

TYPE: Optional[float] DEFAULT: None

RETURNS DESCRIPTION
Conversation

An updated Conversation object with the model's response.

TYPE: Conversation

Source code in swarmauri_standard/llms/PerplexityModel.py
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
176
177
178
179
180
181
182
183
184
185
@retry_on_status_codes((429, 529), max_retries=1)
def predict(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
    top_p: Optional[float] = None,
    top_k: Optional[int] = None,
    return_citations: bool = False,
    presence_penalty: Optional[float] = None,
    frequency_penalty: Optional[float] = None,
) -> Conversation:
    """
    Makes a synchronous prediction request.

    Args:
        conversation (Conversation): The conversation object containing the history.
        temperature (float): Sampling temperature for response generation. Defaults to 0.7.
        max_tokens (int): Maximum number of tokens for the response. Defaults to 256.
        top_p (Optional[float]): Nucleus sampling parameter. If specified, `top_k` should not be set.
        top_k (Optional[int]): Top-k sampling parameter. If specified, `top_p` should not be set.
        return_citations (bool): Whether to return citations in the response. Defaults to False.
        presence_penalty (Optional[float]): Penalty for new tokens based on presence.
        frequency_penalty (Optional[float]): Penalty for new tokens based on frequency.

    Returns:
        Conversation: An updated Conversation object with the model's response.
    """

    if top_p and top_k:
        raise ValueError("Do not set top_p and top_k")

    formatted_messages = self._format_messages(conversation.history)

    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "max_tokens": max_tokens,
        "temperature": temperature,
        "top_p": top_p,
        "return_citations": return_citations,
        "top_k": top_k,
        "presence_penalty": presence_penalty,
        "frequency_penalty": frequency_penalty,
    }
    headers = {
        "accept": "application/json",
        "content-type": "application/json",
        "authorization": f"Bearer {self.api_key.get_secret_value()}",
    }

    with DurationManager() as prompt_timer:
        response = self._client.post(self._BASE_URL, json=payload, headers=headers)
        response.raise_for_status()

    result = response.json()
    message_content = result["choices"][0]["message"]["content"]

    usage_data = result.get("usage", {})

    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=None,
    top_k=None,
    return_citations=False,
    presence_penalty=None,
    frequency_penalty=None,
)

Makes an asynchronous prediction request.

PARAMETER DESCRIPTION
conversation

The conversation object containing the history.

TYPE: Conversation

temperature

Sampling temperature for response generation. Defaults to 0.7.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum number of tokens for the response. Defaults to 256.

TYPE: int DEFAULT: 256

top_p

Nucleus sampling parameter. If specified, top_k should not be set.

TYPE: Optional[float] DEFAULT: None

top_k

Top-k sampling parameter. If specified, top_p should not be set.

TYPE: Optional[int] DEFAULT: None

return_citations

Whether to return citations in the response. Defaults to False.

TYPE: bool DEFAULT: False

presence_penalty

Penalty for new tokens based on presence.

TYPE: Optional[float] DEFAULT: None

frequency_penalty

Penalty for new tokens based on frequency.

TYPE: Optional[float] DEFAULT: None

RETURNS DESCRIPTION
Conversation

An updated Conversation object with the model's response.

TYPE: Conversation

Source code in swarmauri_standard/llms/PerplexityModel.py
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
@retry_on_status_codes((429, 529), max_retries=1)
async def apredict(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
    top_p: Optional[float] = None,
    top_k: Optional[int] = None,
    return_citations: bool = False,
    presence_penalty: Optional[float] = None,
    frequency_penalty: Optional[float] = None,
) -> Conversation:
    """
    Makes an asynchronous prediction request.

    Args:
        conversation (Conversation): The conversation object containing the history.
        temperature (float): Sampling temperature for response generation. Defaults to 0.7.
        max_tokens (int): Maximum number of tokens for the response. Defaults to 256.
        top_p (Optional[float]): Nucleus sampling parameter. If specified, `top_k` should not be set.
        top_k (Optional[int]): Top-k sampling parameter. If specified, `top_p` should not be set.
        return_citations (bool): Whether to return citations in the response. Defaults to False.
        presence_penalty (Optional[float]): Penalty for new tokens based on presence.
        frequency_penalty (Optional[float]): Penalty for new tokens based on frequency.

    Returns:
        Conversation: An updated Conversation object with the model's response.
    """

    if top_p and top_k:
        raise ValueError("Do not set top_p and top_k")

    formatted_messages = self._format_messages(conversation.history)

    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "max_tokens": max_tokens,
        "temperature": temperature,
        "top_p": top_p,
        "return_citations": return_citations,
        "top_k": top_k,
        "presence_penalty": presence_penalty,
        "frequency_penalty": frequency_penalty,
    }
    headers = {
        "accept": "application/json",
        "content-type": "application/json",
        "authorization": f"Bearer {self.api_key.get_secret_value()}",
    }

    with DurationManager() as prompt_timer:
        response = await self._async_client.post(
            self._BASE_URL, json=payload, headers=headers
        )
        response.raise_for_status()

    result = response.json()

    message_content = result["choices"][0]["message"]["content"]

    usage_data = result.get("usage", {})

    if self.include_usage and usage_data:
        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=None,
    top_k=None,
    return_citations=False,
    presence_penalty=None,
    frequency_penalty=None,
)

Synchronously streams the response for a given conversation.

PARAMETER DESCRIPTION
conversation

The conversation object containing message history.

TYPE: Conversation

temperature

Sampling temperature for response generation. Defaults to 0.7.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum number of tokens in the generated response. Defaults to 256.

TYPE: int DEFAULT: 256

top_p

Nucleus sampling parameter. If specified, top_k should not be set.

TYPE: Optional[float] DEFAULT: None

top_k

Top-k sampling parameter. If specified, top_p should not be set.

TYPE: Optional[int] DEFAULT: None

return_citations

Whether to return citations in the response. Defaults to False.

TYPE: bool DEFAULT: False

presence_penalty

Penalty for introducing new topics. Defaults to None.

TYPE: Optional[float] DEFAULT: None

frequency_penalty

Penalty for repeating existing tokens. Defaults to None.

TYPE: Optional[float] DEFAULT: None

YIELDS DESCRIPTION
str

Chunks of response content as the data is streamed.

TYPE:: str

Source code in swarmauri_standard/llms/PerplexityModel.py
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
335
336
337
338
339
@retry_on_status_codes((429, 529), max_retries=1)
def stream(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
    top_p: Optional[float] = None,
    top_k: Optional[int] = None,
    return_citations: bool = False,
    presence_penalty: Optional[float] = None,
    frequency_penalty: Optional[float] = None,
) -> Iterator[str]:
    """
    Synchronously streams the response for a given conversation.

    Args:
        conversation (Conversation): The conversation object containing message history.
        temperature (float): Sampling temperature for response generation. Defaults to 0.7.
        max_tokens (int): Maximum number of tokens in the generated response. Defaults to 256.
        top_p (Optional[float]): Nucleus sampling parameter. If specified, `top_k` should not be set.
        top_k (Optional[int]): Top-k sampling parameter. If specified, `top_p` should not be set.
        return_citations (bool): Whether to return citations in the response. Defaults to False.
        presence_penalty (Optional[float]): Penalty for introducing new topics. Defaults to None.
        frequency_penalty (Optional[float]): Penalty for repeating existing tokens. Defaults to None.

    Yields:
        str: Chunks of response content as the data is streamed.
    """
    if top_p and top_k:
        raise ValueError("Do not set top_p and top_k")

    formatted_messages = self._format_messages(conversation.history)

    url = "https://api.perplexity.ai/chat/completions"

    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "max_tokens": max_tokens,
        "temperature": temperature,
        "top_p": top_p,
        "return_citations": return_citations,
        "top_k": top_k,
        "presence_penalty": presence_penalty,
        "frequency_penalty": frequency_penalty,
        "stream": True,
    }
    headers = {
        "accept": "application/json",
        "content-type": "application/json",
        "authorization": f"Bearer {self.api_key.get_secret_value()}",
    }

    with DurationManager() as prompt_timer:
        response = self._client.post(url, json=payload, headers=headers)
        response.raise_for_status()

    message_content = ""
    usage_data = {}

    with DurationManager() as completion_timer:
        for chunk in response.iter_lines():
            json_string = chunk.replace("data: ", "", 1)
            if json_string:
                chunk_data = json.loads(json_string)
                delta_content = (
                    chunk_data.get("choices", [{}])[0]
                    .get("delta", {})
                    .get("content", "")
                )
                message_content += delta_content
                yield delta_content
                if chunk_data.get("usage"):
                    usage_data = chunk_data["usage"]

    if self.include_usage and usage_data:
        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=None,
    top_k=None,
    return_citations=False,
    presence_penalty=None,
    frequency_penalty=None,
)

Asynchronously streams the response for a given conversation.

PARAMETER DESCRIPTION
conversation

The conversation object containing message history.

TYPE: Conversation

temperature

Sampling temperature for response generation. Defaults to 0.7.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum number of tokens in the generated response. Defaults to 256.

TYPE: int DEFAULT: 256

top_p

Nucleus sampling parameter. If specified, top_k should not be set.

TYPE: Optional[float] DEFAULT: None

top_k

Top-k sampling parameter. If specified, top_p should not be set.

TYPE: Optional[int] DEFAULT: None

return_citations

Whether to return citations in the response. Defaults to False.

TYPE: bool DEFAULT: False

presence_penalty

Penalty for introducing new topics. Defaults to None.

TYPE: Optional[float] DEFAULT: None

frequency_penalty

Penalty for repeating existing tokens. Defaults to None.

TYPE: Optional[float] DEFAULT: None

YIELDS DESCRIPTION
str

Chunks of response content as the data is streamed asynchronously.

TYPE:: AsyncIterator[str]

Source code in swarmauri_standard/llms/PerplexityModel.py
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
@retry_on_status_codes((429, 529), max_retries=1)
async def astream(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
    top_p: Optional[float] = None,
    top_k: Optional[int] = None,
    return_citations: bool = False,
    presence_penalty: Optional[float] = None,
    frequency_penalty: Optional[float] = None,
) -> AsyncIterator[str]:
    """
    Asynchronously streams the response for a given conversation.

    Args:
        conversation (Conversation): The conversation object containing message history.
        temperature (float): Sampling temperature for response generation. Defaults to 0.7.
        max_tokens (int): Maximum number of tokens in the generated response. Defaults to 256.
        top_p (Optional[float]): Nucleus sampling parameter. If specified, `top_k` should not be set.
        top_k (Optional[int]): Top-k sampling parameter. If specified, `top_p` should not be set.
        return_citations (bool): Whether to return citations in the response. Defaults to False.
        presence_penalty (Optional[float]): Penalty for introducing new topics. Defaults to None.
        frequency_penalty (Optional[float]): Penalty for repeating existing tokens. Defaults to None.

    Yields:
        str: Chunks of response content as the data is streamed asynchronously.
    """
    if top_p and top_k:
        raise ValueError("Do not set top_p and top_k")

    formatted_messages = self._format_messages(conversation.history)

    payload = {
        "model": self.name,
        "messages": formatted_messages,
        "max_tokens": max_tokens,
        "temperature": temperature,
        "top_p": top_p,
        "return_citations": return_citations,
        "top_k": top_k,
        "presence_penalty": presence_penalty,
        "frequency_penalty": frequency_penalty,
        "stream": True,
    }

    with DurationManager() as prompt_timer:
        response = await self._async_client.post(self._BASE_URL, json=payload)
        response.raise_for_status()

    message_content = ""
    usage_data = {}

    with DurationManager() as completion_timer:
        async for line in response.aiter_lines():
            json_string = line.replace("data: ", "", 1)
            if json_string:  # Ensure it's not empty
                chunk_data = json.loads(json_string)
                delta_content = (
                    chunk_data.get("choices", [{}])[0]
                    .get("delta", {})
                    .get("content", "")
                )
                message_content += delta_content
                yield delta_content
                usage_data = chunk_data.get("usage", usage_data)

    if self.include_usage and usage_data:
        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=None,
    top_k=None,
    return_citations=False,
    presence_penalty=None,
    frequency_penalty=None,
)

Processes a batch of conversations synchronously.

PARAMETER DESCRIPTION
conversations

List of conversation objects.

TYPE: List[Conversation]

temperature

Sampling temperature for response generation. Defaults to 0.7.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum number of tokens in the generated response. Defaults to 256.

TYPE: int DEFAULT: 256

top_p

Nucleus sampling parameter. If specified, top_k should not be set.

TYPE: Optional[float] DEFAULT: None

top_k

Top-k sampling parameter. If specified, top_p should not be set.

TYPE: Optional[int] DEFAULT: None

return_citations

Whether to return citations in the response. Defaults to False.

TYPE: bool DEFAULT: False

presence_penalty

Penalty for introducing new topics. Defaults to None.

TYPE: Optional[float] DEFAULT: None

frequency_penalty

Penalty for repeating existing tokens. Defaults to None.

TYPE: Optional[float] DEFAULT: None

RETURNS DESCRIPTION
List[Conversation]

List[Conversation]: List of updated conversation objects after processing.

Source code in swarmauri_standard/llms/PerplexityModel.py
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
def batch(
    self,
    conversations: List[Conversation],
    temperature: float = 0.7,
    max_tokens: int = 256,
    top_p: Optional[float] = None,
    top_k: Optional[int] = None,
    return_citations: bool = False,
    presence_penalty: Optional[float] = None,
    frequency_penalty: Optional[float] = None,
) -> List[Conversation]:
    """
    Processes a batch of conversations synchronously.

    Args:
        conversations (List[Conversation]): List of conversation objects.
        temperature (float): Sampling temperature for response generation. Defaults to 0.7.
        max_tokens (int): Maximum number of tokens in the generated response. Defaults to 256.
        top_p (Optional[float]): Nucleus sampling parameter. If specified, `top_k` should not be set.
        top_k (Optional[int]): Top-k sampling parameter. If specified, `top_p` should not be set.
        return_citations (bool): Whether to return citations in the response. Defaults to False.
        presence_penalty (Optional[float]): Penalty for introducing new topics. Defaults to None.
        frequency_penalty (Optional[float]): Penalty for repeating existing tokens. Defaults to None.

    Returns:
        List[Conversation]: List of updated conversation objects after processing.
    """
    return [
        self.predict(
            conversation=conv,
            temperature=temperature,
            max_tokens=max_tokens,
            top_p=top_p,
            top_k=top_k,
            return_citations=return_citations,
            presence_penalty=presence_penalty,
            frequency_penalty=frequency_penalty,
        )
        for conv in conversations
    ]

abatch async

abatch(
    conversations,
    temperature=0.7,
    max_tokens=256,
    top_p=None,
    top_k=None,
    return_citations=False,
    presence_penalty=None,
    frequency_penalty=None,
    max_concurrent=5,
)

Asynchronously processes a batch of conversations with a limit on concurrent tasks.

PARAMETER DESCRIPTION
conversations

List of conversation objects.

TYPE: List[Conversation]

temperature

Sampling temperature for response generation. Defaults to 0.7.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum number of tokens in the generated response. Defaults to 256.

TYPE: int DEFAULT: 256

top_p

Nucleus sampling parameter. If specified, top_k should not be set.

TYPE: Optional[float] DEFAULT: None

top_k

Top-k sampling parameter. If specified, top_p should not be set.

TYPE: Optional[int] DEFAULT: None

return_citations

Whether to return citations in the response. Defaults to False.

TYPE: bool DEFAULT: False

presence_penalty

Penalty for introducing new topics. Defaults to None.

TYPE: Optional[float] DEFAULT: None

frequency_penalty

Penalty for repeating existing tokens. Defaults to None.

TYPE: Optional[float] DEFAULT: None

max_concurrent

Maximum number of concurrent tasks. Defaults to 5.

TYPE: int DEFAULT: 5

RETURNS DESCRIPTION
List[Conversation]

List[Conversation]: List of updated conversation objects after processing asynchronously.

Source code in swarmauri_standard/llms/PerplexityModel.py
457
458
459
460
461
462
463
464
465
466
467
468
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
async def abatch(
    self,
    conversations: List[Conversation],
    temperature: float = 0.7,
    max_tokens: int = 256,
    top_p: Optional[float] = None,
    top_k: Optional[int] = None,
    return_citations: bool = False,
    presence_penalty: Optional[float] = None,
    frequency_penalty: Optional[float] = None,
    max_concurrent: int = 5,  # Maximum concurrent tasks
) -> List[Conversation]:
    """
    Asynchronously processes a batch of conversations with a limit on concurrent tasks.

    Args:
        conversations (List[Conversation]): List of conversation objects.
        temperature (float): Sampling temperature for response generation. Defaults to 0.7.
        max_tokens (int): Maximum number of tokens in the generated response. Defaults to 256.
        top_p (Optional[float]): Nucleus sampling parameter. If specified, `top_k` should not be set.
        top_k (Optional[int]): Top-k sampling parameter. If specified, `top_p` should not be set.
        return_citations (bool): Whether to return citations in the response. Defaults to False.
        presence_penalty (Optional[float]): Penalty for introducing new topics. Defaults to None.
        frequency_penalty (Optional[float]): Penalty for repeating existing tokens. Defaults to None.
        max_concurrent (int): Maximum number of concurrent tasks. Defaults to 5.

    Returns:
        List[Conversation]: List of updated conversation objects after processing asynchronously.
    """
    semaphore = asyncio.Semaphore(max_concurrent)

    async def process_conversation(conv: Conversation) -> Conversation:
        async with semaphore:
            return await self.apredict(
                conversation=conv,
                temperature=temperature,
                max_tokens=max_tokens,
                top_p=top_p,
                top_k=top_k,
                return_citations=return_citations,
                presence_penalty=presence_penalty,
                frequency_penalty=frequency_penalty,
            )

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

get_allowed_models

get_allowed_models()

Queries the LLMProvider API endpoint to retrieve the list of allowed models.

RETURNS DESCRIPTION
List[str]

List[str]: List of allowed model names.

Source code in swarmauri_standard/llms/PerplexityModel.py
504
505
506
507
508
509
510
511
512
513
514
515
516
517
def get_allowed_models(self) -> List[str]:
    """
    Queries the LLMProvider API endpoint to retrieve the list of allowed models.

    Returns:
        List[str]: List of allowed model names.
    """
    models_data = [
        "sonar-reasoning-pro",
        "sonar-reasoning",
        "sonar-pro",
        "sonar",
    ]
    return models_data

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)