Skip to content

Class swarmauri_standard.llms.DeepInfraModel.DeepInfraModel

swarmauri_standard.llms.DeepInfraModel.DeepInfraModel

DeepInfraModel(**data)

Bases: LLMBase

A class for interacting with DeepInfra's model API for text generation.

This implementation uses httpx for both synchronous and asynchronous HTTP requests, providing support for predictions, streaming responses, and batch processing.

ATTRIBUTE DESCRIPTION
api_key

DeepInfra API key for authentication Can be obtained from: https://deepinfra.com/dash/api_keys

TYPE: SecretStr

allowed_models

List of supported model identifiers on DeepInfra Full list available at: https://deepinfra.com/models/text-generation

TYPE: List[str]

name

The currently selected model name Defaults to "Qwen/Qwen2-72B-Instruct"

TYPE: str

type

Type identifier for the model class

TYPE: Literal['DeepInfraModel']

Link to Allowed Models: https://deepinfra.com/models/text-generation Link to API KEY: https://deepinfra.com/dash/api_keys

Initializes the DeepInfraModel instance with the provided API key and sets up httpx clients for both sync and async operations.

PARAMETER DESCRIPTION
**data

Keyword arguments for model initialization.

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

Source code in swarmauri_standard/llms/DeepInfraModel.py
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
def __init__(self, **data: Dict[str, Any]) -> None:
    """
    Initializes the DeepInfraModel instance with the provided API key
    and sets up httpx clients for both sync and async operations.

    Args:
        **data (Dict[str, Any]): Keyword arguments for model initialization.
    """
    super().__init__(**data)
    headers = {
        "Content-Type": "application/json",
        "Authorization": f"Bearer {self.api_key.get_secret_value()}",
    }
    self._client = httpx.Client(
        headers=headers, base_url=self._BASE_URL, timeout=self.timeout
    )
    self._async_client = httpx.AsyncClient(
        headers=headers, base_url=self._BASE_URL, timeout=self.timeout
    )

api_key instance-attribute

api_key

allowed_models class-attribute instance-attribute

allowed_models = [
    "01-ai/Yi-34B-Chat",
    "Gryphe/MythoMax-L2-13b",
    "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
    "Phind/Phind-CodeLlama-34B-v2",
    "Qwen/Qwen2-72B-Instruct",
    "Qwen/Qwen2-7B-Instruct",
    "Qwen/Qwen2.5-72B-Instruct",
    "Sao10K/L3-70B-Euryale-v2.1",
    "Sao10K/L3.1-70B-Euryale-v2.2",
    "bigcode/starcoder2-15b",
    "bigcode/starcoder2-15b-instruct-v0.1",
    "codellama/CodeLlama-34b-Instruct-hf",
    "codellama/CodeLlama-70b-Instruct-hf",
    "cognitivecomputations/dolphin-2.6-mixtral-8x7b",
    "cognitivecomputations/dolphin-2.9.1-llama-3-70b",
    "databricks/dbrx-instruct",
    "google/codegemma-7b-it",
    "google/gemma-1.1-7b-it",
    "google/gemma-2-27b-it",
    "google/gemma-2-9b-it",
    "lizpreciatior/lzlv_70b_fp16_hf",
    "mattshumer/Reflection-Llama-3.1-70B",
    "mattshumer/Reflection-Llama-3.1-70B",
    "meta-llama/Llama-2-13b-chat-hf",
    "meta-llama/Llama-2-70b-chat-hf",
    "meta-llama/Llama-2-7b-chat-hf",
    "meta-llama/Meta-Llama-3-70B-Instruct",
    "meta-llama/Meta-Llama-3-8B-Instruct",
    "meta-llama/Meta-Llama-3.1-405B-Instruct",
    "meta-llama/Meta-Llama-3.1-70B-Instruct",
    "meta-llama/Meta-Llama-3.1-8B-Instruct",
    "microsoft/Phi-3-medium-4k-instruct",
    "microsoft/WizardLM-2-7B",
    "microsoft/WizardLM-2-8x22B",
    "mistralai/Mistral-7B-Instruct-v0.1",
    "mistralai/Mistral-7B-Instruct-v0.2",
    "mistralai/Mistral-7B-Instruct-v0.3",
    "mistralai/Mistral-Nemo-Instruct-2407",
    "mistralai/Mixtral-8x22B-Instruct-v0.1",
    "mistralai/Mixtral-8x22B-v0.1",
    "mistralai/Mixtral-8x22B-v0.1",
    "mistralai/Mixtral-8x7B-Instruct-v0.1",
    "nvidia/Nemotron-4-340B-Instruct",
    "openbmb/MiniCPM-Llama3-V-2_5",
    "openchat/openchat-3.6-8b",
    "openchat/openchat_3.5",
]

name class-attribute instance-attribute

name = '01-ai/Yi-34B-Chat'

type class-attribute instance-attribute

type = 'DeepInfraModel'

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,
    enable_json=False,
    stop=None,
)

Sends a synchronous request to generate a response from the model.

PARAMETER DESCRIPTION
conversation

The conversation object containing message history.

TYPE: Conversation

temperature

Sampling temperature for response generation.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum number of tokens to generate.

TYPE: int DEFAULT: 256

enable_json

Flag for enabling JSON response format.

TYPE: bool DEFAULT: False

stop

Stop sequences for the response.

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

RETURNS DESCRIPTION
Conversation

Updated conversation with the model's response.

TYPE: Conversation

Source code in swarmauri_standard/llms/DeepInfraModel.py
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
@retry_on_status_codes((429, 529), max_retries=1)
def predict(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> Conversation:
    """
    Sends a synchronous request to generate a response from the model.

    Args:
        conversation (Conversation): The conversation object containing message history.
        temperature (float): Sampling temperature for response generation.
        max_tokens (int): Maximum number of tokens to generate.
        enable_json (bool): Flag for enabling JSON response format.
        stop (Optional[List[str]], optional): Stop sequences for the response.

    Returns:
        Conversation: Updated conversation with the model's response.
    """
    formatted_messages = self._format_messages(conversation.history)
    payload = self._create_request_payload(
        formatted_messages, temperature, max_tokens, enable_json, stop
    )

    response = self._client.post("/chat/completions", json=payload)
    response.raise_for_status()

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

    return conversation

apredict async

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

Sends an asynchronous request to generate a response from the model.

PARAMETER DESCRIPTION
conversation

The conversation object containing message history.

TYPE: Conversation

temperature

Sampling temperature for response generation.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum number of tokens to generate.

TYPE: int DEFAULT: 256

enable_json

Flag for enabling JSON response format.

TYPE: bool DEFAULT: False

stop

Stop sequences for the response.

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

RETURNS DESCRIPTION
Conversation

Updated conversation with the model's response.

TYPE: Conversation

Source code in swarmauri_standard/llms/DeepInfraModel.py
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
@retry_on_status_codes((429, 529), max_retries=1)
async def apredict(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> Conversation:
    """
    Sends an asynchronous request to generate a response from the model.

    Args:
        conversation (Conversation): The conversation object containing message history.
        temperature (float): Sampling temperature for response generation.
        max_tokens (int): Maximum number of tokens to generate.
        enable_json (bool): Flag for enabling JSON response format.
        stop (Optional[List[str]], optional): Stop sequences for the response.

    Returns:
        Conversation: Updated conversation with the model's response.
    """
    formatted_messages = self._format_messages(conversation.history)
    payload = self._create_request_payload(
        formatted_messages, temperature, max_tokens, enable_json, stop
    )

    response = await self._async_client.post("/chat/completions", json=payload)
    response.raise_for_status()

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

    return conversation

stream

stream(
    conversation, temperature=0.7, max_tokens=256, stop=None
)

Streams response content from the model synchronously.

PARAMETER DESCRIPTION
conversation

The conversation object containing message history.

TYPE: Conversation

temperature

Sampling temperature for response generation.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum number of tokens to generate.

TYPE: int DEFAULT: 256

stop

Stop sequences for the response.

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

YIELDS DESCRIPTION
str

Chunks of content from the model's response.

TYPE:: str

Source code in swarmauri_standard/llms/DeepInfraModel.py
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
@retry_on_status_codes((429, 529), max_retries=1)
def stream(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
    stop: Optional[List[str]] = None,
) -> Iterator[str]:
    """
    Streams response content from the model synchronously.

    Args:
        conversation (Conversation): The conversation object containing message history.
        temperature (float): Sampling temperature for response generation.
        max_tokens (int): Maximum number of tokens to generate.
        stop (Optional[List[str]], optional): Stop sequences for the response.

    Yields:
        str: Chunks of content from the model's response.
    """
    formatted_messages = self._format_messages(conversation.history)
    payload = self._create_request_payload(
        formatted_messages, temperature, max_tokens, False, stop, stream=True
    )

    with self._client.stream("POST", "/chat/completions", json=payload) as response:
        response.raise_for_status()
        collected_content = []

        for line in response.iter_lines():
            # Convert bytes to string if necessary
            if isinstance(line, bytes):
                line = line.decode("utf-8")

            if line.startswith("data: "):
                line = line[6:]  # Remove 'data: ' prefix
                if line != "[DONE]":
                    chunk = json.loads(line)
                    if chunk["choices"][0]["delta"].get("content"):
                        content = chunk["choices"][0]["delta"]["content"]
                        collected_content.append(content)
                        yield content

    full_content = "".join(collected_content)
    conversation.add_message(AgentMessage(content=full_content))

astream async

astream(
    conversation, temperature=0.7, max_tokens=256, stop=None
)

Streams response content from the model asynchronously.

PARAMETER DESCRIPTION
conversation

The conversation object containing message history.

TYPE: Conversation

temperature

Sampling temperature for response generation.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum number of tokens to generate.

TYPE: int DEFAULT: 256

stop

Stop sequences for the response.

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

YIELDS DESCRIPTION
str

Chunks of content from the model's response.

TYPE:: AsyncIterator[str]

Source code in swarmauri_standard/llms/DeepInfraModel.py
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
@retry_on_status_codes((429, 529), max_retries=1)
async def astream(
    self,
    conversation: Conversation,
    temperature: float = 0.7,
    max_tokens: int = 256,
    stop: Optional[List[str]] = None,
) -> AsyncIterator[str]:
    """
    Streams response content from the model asynchronously.

    Args:
        conversation (Conversation): The conversation object containing message history.
        temperature (float): Sampling temperature for response generation.
        max_tokens (int): Maximum number of tokens to generate.
        stop (Optional[List[str]], optional): Stop sequences for the response.

    Yields:
        str: Chunks of content from the model's response.
    """
    formatted_messages = self._format_messages(conversation.history)
    payload = self._create_request_payload(
        formatted_messages, temperature, max_tokens, False, stop, stream=True
    )

    async with self._async_client.stream(
        "POST", "/chat/completions", json=payload
    ) as response:
        response.raise_for_status()
        collected_content = []

        async for line in response.aiter_lines():
            if line.startswith("data: "):
                line = line[6:]  # Remove 'data: ' prefix
                if line != "[DONE]":
                    chunk = json.loads(line)
                    if chunk["choices"][0]["delta"].get("content"):
                        content = chunk["choices"][0]["delta"]["content"]
                        collected_content.append(content)
                        yield content

    full_content = "".join(collected_content)
    conversation.add_message(AgentMessage(content=full_content))

batch

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

Processes multiple conversations in batch synchronously.

PARAMETER DESCRIPTION
conversations

List of conversation objects.

TYPE: List[Conversation]

temperature

Sampling temperature for response generation.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum number of tokens to generate.

TYPE: int DEFAULT: 256

enable_json

Flag for enabling JSON response format.

TYPE: bool DEFAULT: False

stop

Stop sequences for responses.

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/DeepInfraModel.py
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
def batch(
    self,
    conversations: List[Conversation],
    temperature: float = 0.7,
    max_tokens: int = 256,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
) -> List[Conversation]:
    """
    Processes multiple conversations in batch synchronously.

    Args:
        conversations (List[Conversation]): List of conversation objects.
        temperature (float): Sampling temperature for response generation.
        max_tokens (int): Maximum number of tokens to generate.
        enable_json (bool): Flag for enabling JSON response format.
        stop (Optional[List[str]], optional): Stop sequences for responses.

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

abatch async

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

Processes multiple conversations asynchronously, with concurrency control.

PARAMETER DESCRIPTION
conversations

List of conversation objects.

TYPE: List[Conversation]

temperature

Sampling temperature for response generation.

TYPE: float DEFAULT: 0.7

max_tokens

Maximum number of tokens to generate.

TYPE: int DEFAULT: 256

enable_json

Flag for enabling JSON response format.

TYPE: bool DEFAULT: False

stop

Stop sequences for responses.

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

max_concurrent

Maximum number of concurrent tasks.

TYPE: int DEFAULT: 5

RETURNS DESCRIPTION
List[Conversation]

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

Source code in swarmauri_standard/llms/DeepInfraModel.py
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
async def abatch(
    self,
    conversations: List[Conversation],
    temperature: float = 0.7,
    max_tokens: int = 256,
    enable_json: bool = False,
    stop: Optional[List[str]] = None,
    max_concurrent: int = 5,
) -> List[Conversation]:
    """
    Processes multiple conversations asynchronously, with concurrency control.

    Args:
        conversations (List[Conversation]): List of conversation objects.
        temperature (float): Sampling temperature for response generation.
        max_tokens (int): Maximum number of tokens to generate.
        enable_json (bool): Flag for enabling JSON response format.
        stop (Optional[List[str]], optional): Stop sequences for responses.
        max_concurrent (int): Maximum number of concurrent tasks.

    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,
                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()

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

RETURNS DESCRIPTION
List[str]

List[str]: List of allowed model identifiers.

Source code in swarmauri_standard/llms/DeepInfraModel.py
410
411
412
413
414
415
416
417
418
419
420
421
def get_allowed_models(self) -> List[str]:
    """
    Queries the LLMProvider API endpoint to get the list of allowed models.

    Returns:
        List[str]: List of allowed model identifiers.
    """
    response = self._client.get("/models")
    response.raise_for_status()
    models = response.json()
    print(models)
    return [model["id"] for model in 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)