Class swarmauri_standard.llms.DeepSeekModel.DeepSeekModel
swarmauri_standard.llms.DeepSeekModel.DeepSeekModel
DeepSeekModel(**data)
Bases: LLMBase
A client class for interfacing with DeepSeek's language model for chat completions.
This class provides methods for synchronous and asynchronous prediction, streaming, and batch processing. It handles message formatting, payload construction, and response parsing to seamlessly integrate with the DeepSeek API.
ATTRIBUTE | DESCRIPTION |
---|---|
api_key |
The API key for authenticating with DeepSeek.
TYPE:
|
allowed_models |
List of models supported by DeepSeek, defaulting to ["deepseek-chat"].
TYPE:
|
name |
The model name, defaulting to "deepseek-chat".
TYPE:
|
type |
The class type for identifying the LLM, set to "DeepSeekModel".
TYPE:
|
Link to Allowed Models: https://platform.deepseek.com/api-docs/quick_start/pricing Link to API KEY: https://platform.deepseek.com/api_keys
Source code in swarmauri_standard/llms/DeepSeekModel.py
47 48 49 50 51 52 53 54 55 56 57 58 59 |
|
api_key
instance-attribute
api_key
allowed_models
class-attribute
instance-attribute
allowed_models = ['deepseek-chat', 'deepseek-reasoner']
name
class-attribute
instance-attribute
name = 'deepseek-chat'
type
class-attribute
instance-attribute
type = 'DeepSeekModel'
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
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,
frequency_penalty=0,
presence_penalty=0,
stop="\n",
top_p=1.0,
)
Sends a synchronous request to the DeepSeek API to generate a chat response.
PARAMETER | DESCRIPTION |
---|---|
conversation
|
The conversation object containing message history.
TYPE:
|
temperature
|
Sampling temperature for randomness in response.
TYPE:
|
max_tokens
|
Maximum number of tokens in the response.
TYPE:
|
frequency_penalty
|
Penalty for frequent tokens in the response.
TYPE:
|
presence_penalty
|
Penalty for new topics in the response.
TYPE:
|
stop
|
Token at which response generation should stop.
TYPE:
|
top_p
|
Top-p sampling value for nucleus sampling.
TYPE:
|
RETURNS | DESCRIPTION |
---|---|
Conversation
|
Updated conversation object with the generated response added.
TYPE:
|
Source code in swarmauri_standard/llms/DeepSeekModel.py
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 |
|
apredict
async
apredict(
conversation,
temperature=0.7,
max_tokens=256,
frequency_penalty=0,
presence_penalty=0,
stop="\n",
top_p=1.0,
)
Sends an asynchronous request to the DeepSeek API to generate a chat response.
PARAMETER | DESCRIPTION |
---|---|
conversation
|
The conversation object containing message history.
TYPE:
|
temperature
|
Sampling temperature for randomness in response.
TYPE:
|
max_tokens
|
Maximum number of tokens in the response.
TYPE:
|
frequency_penalty
|
Penalty for frequent tokens in the response.
TYPE:
|
presence_penalty
|
Penalty for new topics in the response.
TYPE:
|
stop
|
Token at which response generation should stop.
TYPE:
|
top_p
|
Top-p sampling value for nucleus sampling.
TYPE:
|
RETURNS | DESCRIPTION |
---|---|
Conversation
|
Updated conversation object with the generated response added.
TYPE:
|
Source code in swarmauri_standard/llms/DeepSeekModel.py
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 |
|
stream
stream(
conversation,
temperature=0.7,
max_tokens=256,
frequency_penalty=0,
presence_penalty=0,
stop="\n",
top_p=1.0,
)
Streams the response token by token synchronously from the DeepSeek API.
PARAMETER | DESCRIPTION |
---|---|
conversation
|
The conversation object containing message history.
TYPE:
|
temperature
|
Sampling temperature for randomness in response.
TYPE:
|
max_tokens
|
Maximum number of tokens in the response.
TYPE:
|
frequency_penalty
|
Penalty for frequent tokens in the response.
TYPE:
|
presence_penalty
|
Penalty for new topics in the response.
TYPE:
|
stop
|
Token at which response generation should stop.
TYPE:
|
top_p
|
Top-p sampling value for nucleus sampling.
TYPE:
|
YIELDS | DESCRIPTION |
---|---|
str
|
Token of the response being streamed.
TYPE::
|
Source code in swarmauri_standard/llms/DeepSeekModel.py
167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 |
|
astream
async
astream(
conversation,
temperature=0.7,
max_tokens=256,
frequency_penalty=0,
presence_penalty=0,
stop="\n",
top_p=1.0,
)
Asynchronously streams the response token by token from the DeepSeek API.
PARAMETER | DESCRIPTION |
---|---|
conversation
|
The conversation object containing message history.
TYPE:
|
temperature
|
Sampling temperature for randomness in response.
TYPE:
|
max_tokens
|
Maximum number of tokens in the response.
TYPE:
|
frequency_penalty
|
Penalty for frequent tokens in the response.
TYPE:
|
presence_penalty
|
Penalty for new topics in the response.
TYPE:
|
stop
|
Token at which response generation should stop.
TYPE:
|
top_p
|
Top-p sampling value for nucleus sampling.
TYPE:
|
YIELDS | DESCRIPTION |
---|---|
str
|
Token of the response being streamed.
TYPE::
|
Source code in swarmauri_standard/llms/DeepSeekModel.py
224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 |
|
batch
batch(
conversations,
temperature=0.7,
max_tokens=256,
frequency_penalty=0,
presence_penalty=0,
stop="\n",
top_p=1.0,
)
Processes multiple conversations synchronously in a batch.
PARAMETER | DESCRIPTION |
---|---|
conversations
|
List of conversation objects.
TYPE:
|
temperature
|
Sampling temperature for randomness in response.
TYPE:
|
max_tokens
|
Maximum number of tokens in the response.
TYPE:
|
frequency_penalty
|
Penalty for frequent tokens in the response.
TYPE:
|
presence_penalty
|
Penalty for new topics in the response.
TYPE:
|
stop
|
Token at which response generation should stop.
TYPE:
|
top_p
|
Top-p sampling value for nucleus sampling.
TYPE:
|
RETURNS | DESCRIPTION |
---|---|
List[Conversation]
|
List[Conversation]: List of updated conversation objects with responses added. |
Source code in swarmauri_standard/llms/DeepSeekModel.py
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 |
|
abatch
async
abatch(
conversations,
temperature=0.7,
max_tokens=256,
frequency_penalty=0,
presence_penalty=0,
stop="\n",
top_p=1.0,
max_concurrent=5,
)
Processes multiple conversations asynchronously in parallel, with concurrency control.
PARAMETER | DESCRIPTION |
---|---|
conversations
|
List of conversation objects.
TYPE:
|
temperature
|
Sampling temperature for randomness in response.
TYPE:
|
max_tokens
|
Maximum number of tokens in the response.
TYPE:
|
frequency_penalty
|
Penalty for frequent tokens in the response.
TYPE:
|
presence_penalty
|
Penalty for new topics in the response.
TYPE:
|
stop
|
Token at which response generation should stop.
TYPE:
|
top_p
|
Top-p sampling value for nucleus sampling.
TYPE:
|
max_concurrent
|
Maximum number of concurrent tasks allowed.
TYPE:
|
RETURNS | DESCRIPTION |
---|---|
List[Conversation]
|
List[Conversation]: List of updated conversation objects with responses added. |
Source code in swarmauri_standard/llms/DeepSeekModel.py
321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 |
|
get_allowed_models
get_allowed_models()
Queries the DeepSeek API to get the list of allowed models.
RETURNS | DESCRIPTION |
---|---|
List[str]
|
List[str]: List of allowed model names. |
Source code in swarmauri_standard/llms/DeepSeekModel.py
365 366 367 368 369 370 371 372 373 374 375 |
|
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:
|
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 |
|
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:
|
type_name
|
An optional custom type name for the subtype.
TYPE:
|
RETURNS | DESCRIPTION |
---|---|
Callable
|
A decorator function that registers the subtype.
TYPE:
|
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 |
|
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 |
|
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 |
|
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 |
|
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 |
|
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 |
|
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 |
|
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 |
|