strands.models
¶
SDK model providers.
This package includes an abstract base Model class along with concrete implementations for specific providers.
strands.models.bedrock
¶
AWS Bedrock model provider.
- Docs: https://aws.amazon.com/bedrock/
BedrockModel
¶
Bases: Model
AWS Bedrock model provider implementation.
The implementation handles Bedrock-specific features such as:
- Tool configuration for function calling
- Guardrails integration
- Caching points for system prompts and tools
- Streaming responses
- Context window overflow detection
Source code in strands/models/bedrock.py
39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 |
|
BedrockConfig
¶
Bases: TypedDict
Configuration options for Bedrock models.
Attributes:
Name | Type | Description |
---|---|---|
additional_args |
Optional[dict[str, Any]]
|
Any additional arguments to include in the request |
additional_request_fields |
Optional[dict[str, Any]]
|
Additional fields to include in the Bedrock request |
additional_response_field_paths |
Optional[list[str]]
|
Additional response field paths to extract |
cache_prompt |
Optional[str]
|
Cache point type for the system prompt |
cache_tools |
Optional[str]
|
Cache point type for tools |
guardrail_id |
Optional[str]
|
ID of the guardrail to apply |
guardrail_trace |
Optional[Literal['enabled', 'disabled', 'enabled_full']]
|
Guardrail trace mode. Defaults to enabled. |
guardrail_version |
Optional[str]
|
Version of the guardrail to apply |
guardrail_stream_processing_mode |
Optional[Literal['sync', 'async']]
|
The guardrail processing mode |
guardrail_redact_input |
Optional[bool]
|
Flag to redact input if a guardrail is triggered. Defaults to True. |
guardrail_redact_input_message |
Optional[str]
|
If a Bedrock Input guardrail triggers, replace the input with this message. |
guardrail_redact_output |
Optional[bool]
|
Flag to redact output if guardrail is triggered. Defaults to False. |
guardrail_redact_output_message |
Optional[str]
|
If a Bedrock Output guardrail triggers, replace output with this message. |
max_tokens |
Optional[int]
|
Maximum number of tokens to generate in the response |
model_id |
str
|
The Bedrock model ID (e.g., "us.anthropic.claude-3-7-sonnet-20250219-v1:0") |
stop_sequences |
Optional[list[str]]
|
List of sequences that will stop generation when encountered |
streaming |
Optional[bool]
|
Flag to enable/disable streaming. Defaults to True. |
temperature |
Optional[float]
|
Controls randomness in generation (higher = more random) |
top_p |
Optional[float]
|
Controls diversity via nucleus sampling (alternative to temperature) |
Source code in strands/models/bedrock.py
51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
|
__init__(*, boto_session=None, boto_client_config=None, region_name=None, **model_config)
¶
Initialize provider instance.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
boto_session
|
Optional[Session]
|
Boto Session to use when calling the Bedrock Model. |
None
|
boto_client_config
|
Optional[Config]
|
Configuration to use when creating the Bedrock-Runtime Boto Client. |
None
|
region_name
|
Optional[str]
|
AWS region to use for the Bedrock service. Defaults to the AWS_REGION environment variable if set, or "us-west-2" if not set. |
None
|
**model_config
|
Unpack[BedrockConfig]
|
Configuration options for the Bedrock model. |
{}
|
Source code in strands/models/bedrock.py
96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 |
|
format_chunk(event)
¶
Format the Bedrock response events into standardized message chunks.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
event
|
dict[str, Any]
|
A response event from the Bedrock model. |
required |
Returns:
Type | Description |
---|---|
StreamEvent
|
The formatted chunk. |
Source code in strands/models/bedrock.py
255 256 257 258 259 260 261 262 263 264 265 |
|
format_request(messages, tool_specs=None, system_prompt=None)
¶
Format a Bedrock converse stream request.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
messages
|
Messages
|
List of message objects to be processed by the model. |
required |
tool_specs
|
Optional[list[ToolSpec]]
|
List of tool specifications to make available to the model. |
None
|
system_prompt
|
Optional[str]
|
System prompt to provide context to the model. |
None
|
Returns:
Type | Description |
---|---|
dict[str, Any]
|
A Bedrock converse stream request. |
Source code in strands/models/bedrock.py
171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 |
|
get_config()
¶
Get the current Bedrock Model configuration.
Returns:
Type | Description |
---|---|
BedrockConfig
|
The Bedrock model configuration. |
Source code in strands/models/bedrock.py
162 163 164 165 166 167 168 169 |
|
stream(request)
¶
Send the request to the Bedrock model and get the response.
This method calls either the Bedrock converse_stream API or the converse API based on the streaming parameter in the configuration.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
request
|
dict[str, Any]
|
The formatted request to send to the Bedrock model |
required |
Returns:
Type | Description |
---|---|
Iterable[StreamEvent]
|
An iterable of response events from the Bedrock model |
Raises:
Type | Description |
---|---|
ContextWindowOverflowException
|
If the input exceeds the model's context window. |
ModelThrottledException
|
If the model service is throttling requests. |
Source code in strands/models/bedrock.py
323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 |
|
structured_output(output_model, prompt, callback_handler=None)
¶
Get structured output from the model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
output_model(Type[BaseModel])
|
The output model to use for the agent. |
required | |
prompt(Messages)
|
The prompt messages to use for the agent. |
required | |
callback_handler(Optional[Callable])
|
Optional callback handler for processing events. Defaults to None. |
required |
Source code in strands/models/bedrock.py
496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 |
|
update_config(**model_config)
¶
Update the Bedrock Model configuration with the provided arguments.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
**model_config
|
Unpack[BedrockConfig]
|
Configuration overrides. |
{}
|
Source code in strands/models/bedrock.py
153 154 155 156 157 158 159 160 |
|
strands.models.anthropic
¶
Anthropic Claude model provider.
- Docs: https://docs.anthropic.com/claude/reference/getting-started-with-the-api
AnthropicModel
¶
Bases: Model
Anthropic model provider implementation.
Source code in strands/models/anthropic.py
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 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 |
|
AnthropicConfig
¶
Bases: TypedDict
Configuration options for Anthropic models.
Attributes:
Name | Type | Description |
---|---|---|
max_tokens |
Required[str]
|
Maximum number of tokens to generate. |
model_id |
Required[str]
|
Calude model ID (e.g., "claude-3-7-sonnet-latest"). For a complete list of supported models, see https://docs.anthropic.com/en/docs/about-claude/models/all-models. |
params |
Optional[dict[str, Any]]
|
Additional model parameters (e.g., temperature). For a complete list of supported parameters, see https://docs.anthropic.com/en/api/messages. |
Source code in strands/models/anthropic.py
47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 |
|
__init__(*, client_args=None, **model_config)
¶
Initialize provider instance.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
client_args
|
Optional[dict[str, Any]]
|
Arguments for the underlying Anthropic client (e.g., api_key). For a complete list of supported arguments, see https://docs.anthropic.com/en/api/client-sdks. |
None
|
**model_config
|
Unpack[AnthropicConfig]
|
Configuration options for the Anthropic model. |
{}
|
Source code in strands/models/anthropic.py
63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
|
format_chunk(event)
¶
Format the Anthropic response events into standardized message chunks.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
event
|
dict[str, Any]
|
A response event from the Anthropic model. |
required |
Returns:
Type | Description |
---|---|
StreamEvent
|
The formatted chunk. |
Raises:
Type | Description |
---|---|
RuntimeError
|
If chunk_type is not recognized. This error should never be encountered as we control chunk_type in the stream method. |
Source code in strands/models/anthropic.py
229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 |
|
format_request(messages, tool_specs=None, system_prompt=None)
¶
Format an Anthropic streaming request.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
messages
|
Messages
|
List of message objects to be processed by the model. |
required |
tool_specs
|
Optional[list[ToolSpec]]
|
List of tool specifications to make available to the model. |
None
|
system_prompt
|
Optional[str]
|
System prompt to provide context to the model. |
None
|
Returns:
Type | Description |
---|---|
dict[str, Any]
|
An Anthropic streaming request. |
Raises:
Type | Description |
---|---|
TypeError
|
If a message contains a content block type that cannot be converted to an Anthropic-compatible format. |
Source code in strands/models/anthropic.py
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 |
|
get_config()
¶
Get the Anthropic model configuration.
Returns:
Type | Description |
---|---|
AnthropicConfig
|
The Anthropic model configuration. |
Source code in strands/models/anthropic.py
87 88 89 90 91 92 93 94 |
|
stream(request)
¶
Send the request to the Anthropic model and get the streaming response.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
request
|
dict[str, Any]
|
The formatted request to send to the Anthropic model. |
required |
Returns:
Type | Description |
---|---|
Iterable[dict[str, Any]]
|
An iterable of response events from the Anthropic model. |
Raises:
Type | Description |
---|---|
ContextWindowOverflowException
|
If the input exceeds the model's context window. |
ModelThrottledException
|
If the request is throttled by Anthropic. |
Source code in strands/models/anthropic.py
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 |
|
structured_output(output_model, prompt, callback_handler=None)
¶
Get structured output from the model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
output_model(Type[BaseModel])
|
The output model to use for the agent. |
required | |
prompt(Messages)
|
The prompt messages to use for the agent. |
required | |
callback_handler(Optional[Callable])
|
Optional callback handler for processing events. Defaults to None. |
required |
Source code in strands/models/anthropic.py
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 |
|
update_config(**model_config)
¶
Update the Anthropic model configuration with the provided arguments.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
**model_config
|
Unpack[AnthropicConfig]
|
Configuration overrides. |
{}
|
Source code in strands/models/anthropic.py
78 79 80 81 82 83 84 85 |
|
strands.models.litellm
¶
LiteLLM model provider.
- Docs: https://docs.litellm.ai/
LiteLLMModel
¶
Bases: OpenAIModel
LiteLLM model provider implementation.
Source code in strands/models/litellm.py
23 24 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 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 |
|
LiteLLMConfig
¶
Bases: TypedDict
Configuration options for LiteLLM models.
Attributes:
Name | Type | Description |
---|---|---|
model_id |
str
|
Model ID (e.g., "openai/gpt-4o", "anthropic/claude-3-sonnet"). For a complete list of supported models, see https://docs.litellm.ai/docs/providers. |
params |
Optional[dict[str, Any]]
|
Model parameters (e.g., max_tokens). For a complete list of supported parameters, see https://docs.litellm.ai/docs/completion/input#input-params-1. |
Source code in strands/models/litellm.py
26 27 28 29 30 31 32 33 34 35 36 37 38 |
|
__init__(client_args=None, **model_config)
¶
Initialize provider instance.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
client_args
|
Optional[dict[str, Any]]
|
Arguments for the LiteLLM client. For a complete list of supported arguments, see https://github.com/BerriAI/litellm/blob/main/litellm/main.py. |
None
|
**model_config
|
Unpack[LiteLLMConfig]
|
Configuration options for the LiteLLM model. |
{}
|
Source code in strands/models/litellm.py
40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 |
|
format_request_message_content(content)
classmethod
¶
Format a LiteLLM content block.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
content
|
ContentBlock
|
Message content. |
required |
Returns:
Type | Description |
---|---|
dict[str, Any]
|
LiteLLM formatted content block. |
Raises:
Type | Description |
---|---|
TypeError
|
If the content block type cannot be converted to a LiteLLM-compatible format. |
Source code in strands/models/litellm.py
74 75 76 77 78 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 |
|
get_config()
¶
Get the LiteLLM model configuration.
Returns:
Type | Description |
---|---|
LiteLLMConfig
|
The LiteLLM model configuration. |
Source code in strands/models/litellm.py
65 66 67 68 69 70 71 72 |
|
structured_output(output_model, prompt, callback_handler=None)
¶
Get structured output from the model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
output_model(Type[BaseModel])
|
The output model to use for the agent. |
required | |
prompt(Messages)
|
The prompt messages to use for the agent. |
required | |
callback_handler(Optional[Callable])
|
Optional callback handler for processing events. Defaults to None. |
required |
Source code in strands/models/litellm.py
106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 |
|
update_config(**model_config)
¶
Update the LiteLLM model configuration with the provided arguments.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
**model_config
|
Unpack[LiteLLMConfig]
|
Configuration overrides. |
{}
|
Source code in strands/models/litellm.py
56 57 58 59 60 61 62 63 |
|
strands.models.llamaapi
¶
Llama API model provider.
- Docs: https://llama.developer.meta.com/
LlamaAPIModel
¶
Bases: Model
Llama API model provider implementation.
Source code in strands/models/llamaapi.py
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 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 |
|
LlamaConfig
¶
Bases: TypedDict
Configuration options for Llama API models.
Attributes:
Name | Type | Description |
---|---|---|
model_id |
str
|
Model ID (e.g., "Llama-4-Maverick-17B-128E-Instruct-FP8"). |
repetition_penalty |
Optional[float]
|
Repetition penalty. |
temperature |
Optional[float]
|
Temperature. |
top_p |
Optional[float]
|
Top-p. |
max_completion_tokens |
Optional[int]
|
Maximum completion tokens. |
top_k |
Optional[int]
|
Top-k. |
Source code in strands/models/llamaapi.py
32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 |
|
__init__(*, client_args=None, **model_config)
¶
Initialize provider instance.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
client_args
|
Optional[dict[str, Any]]
|
Arguments for the Llama API client. |
None
|
**model_config
|
Unpack[LlamaConfig]
|
Configuration options for the Llama API model. |
{}
|
Source code in strands/models/llamaapi.py
51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
|
format_chunk(event)
¶
Format the Llama API model response events into standardized message chunks.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
event
|
dict[str, Any]
|
A response event from the model. |
required |
Returns:
Type | Description |
---|---|
StreamEvent
|
The formatted chunk. |
Source code in strands/models/llamaapi.py
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 |
|
format_request(messages, tool_specs=None, system_prompt=None)
¶
Format a Llama API chat streaming request.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
messages
|
Messages
|
List of message objects to be processed by the model. |
required |
tool_specs
|
Optional[list[ToolSpec]]
|
List of tool specifications to make available to the model. |
None
|
system_prompt
|
Optional[str]
|
System prompt to provide context to the model. |
None
|
Returns:
Type | Description |
---|---|
dict[str, Any]
|
An Llama API chat streaming request. |
Raises:
Type | Description |
---|---|
TypeError
|
If a message contains a content block type that cannot be converted to a LlamaAPI-compatible format. |
Source code in strands/models/llamaapi.py
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 |
|
get_config()
¶
Get the Llama API model configuration.
Returns:
Type | Description |
---|---|
LlamaConfig
|
The Llama API model configuration. |
Source code in strands/models/llamaapi.py
80 81 82 83 84 85 86 87 |
|
stream(request)
¶
Send the request to the model and get a streaming response.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
request
|
dict[str, Any]
|
The formatted request to send to the model. |
required |
Returns:
Type | Description |
---|---|
Iterable[dict[str, Any]]
|
The model's response. |
Raises:
Type | Description |
---|---|
ModelThrottledException
|
When the model service is throttling requests from the client. |
Source code in strands/models/llamaapi.py
326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 |
|
structured_output(output_model, prompt, callback_handler=None)
¶
Get structured output from the model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
output_model(Type[BaseModel])
|
The output model to use for the agent. |
required | |
prompt(Messages)
|
The prompt messages to use for the agent. |
required | |
callback_handler(Optional[Callable])
|
Optional callback handler for processing events. Defaults to None. |
required |
Raises:
Type | Description |
---|---|
NotImplementedError
|
Structured output is not currently supported for LlamaAPI models. |
Source code in strands/models/llamaapi.py
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 |
|
update_config(**model_config)
¶
Update the Llama API Model configuration with the provided arguments.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
**model_config
|
Unpack[LlamaConfig]
|
Configuration overrides. |
{}
|
Source code in strands/models/llamaapi.py
71 72 73 74 75 76 77 78 |
|
strands.models.ollama
¶
Ollama model provider.
- Docs: https://ollama.com/
OllamaModel
¶
Bases: Model
Ollama model provider implementation.
The implementation handles Ollama-specific features such as:
- Local model invocation
- Streaming responses
- Tool/function calling
Source code in strands/models/ollama.py
24 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 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 |
|
OllamaConfig
¶
Bases: TypedDict
Configuration parameters for Ollama models.
Attributes:
Name | Type | Description |
---|---|---|
additional_args |
Optional[dict[str, Any]]
|
Any additional arguments to include in the request. |
keep_alive |
Optional[str]
|
Controls how long the model will stay loaded into memory following the request (default: "5m"). |
max_tokens |
Optional[int]
|
Maximum number of tokens to generate in the response. |
model_id |
str
|
Ollama model ID (e.g., "llama3", "mistral", "phi3"). |
options |
Optional[dict[str, Any]]
|
Additional model parameters (e.g., top_k). |
stop_sequences |
Optional[list[str]]
|
List of sequences that will stop generation when encountered. |
temperature |
Optional[float]
|
Controls randomness in generation (higher = more random). |
top_p |
Optional[float]
|
Controls diversity via nucleus sampling (alternative to temperature). |
Source code in strands/models/ollama.py
34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
|
__init__(host, *, ollama_client_args=None, **model_config)
¶
Initialize provider instance.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
host
|
Optional[str]
|
The address of the Ollama server hosting the model. |
required |
ollama_client_args
|
Optional[dict[str, Any]]
|
Additional arguments for the Ollama client. |
None
|
**model_config
|
Unpack[OllamaConfig]
|
Configuration options for the Ollama model. |
{}
|
Source code in strands/models/ollama.py
57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
|
format_chunk(event)
¶
Format the Ollama response events into standardized message chunks.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
event
|
dict[str, Any]
|
A response event from the Ollama model. |
required |
Returns:
Type | Description |
---|---|
StreamEvent
|
The formatted chunk. |
Raises:
Type | Description |
---|---|
RuntimeError
|
If chunk_type is not recognized. This error should never be encountered as we control chunk_type in the stream method. |
Source code in strands/models/ollama.py
222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 |
|
format_request(messages, tool_specs=None, system_prompt=None)
¶
Format an Ollama chat streaming request.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
messages
|
Messages
|
List of message objects to be processed by the model. |
required |
tool_specs
|
Optional[list[ToolSpec]]
|
List of tool specifications to make available to the model. |
None
|
system_prompt
|
Optional[str]
|
System prompt to provide context to the model. |
None
|
Returns:
Type | Description |
---|---|
dict[str, Any]
|
An Ollama chat streaming request. |
Raises:
Type | Description |
---|---|
TypeError
|
If a message contains a content block type that cannot be converted to an Ollama-compatible format. |
Source code in strands/models/ollama.py
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 |
|
get_config()
¶
Get the Ollama model configuration.
Returns:
Type | Description |
---|---|
OllamaConfig
|
The Ollama model configuration. |
Source code in strands/models/ollama.py
88 89 90 91 92 93 94 95 |
|
stream(request)
¶
Send the request to the Ollama model and get the streaming response.
This method calls the Ollama chat API and returns the stream of response events.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
request
|
dict[str, Any]
|
The formatted request to send to the Ollama model. |
required |
Returns:
Type | Description |
---|---|
Iterable[dict[str, Any]]
|
An iterable of response events from the Ollama model. |
Source code in strands/models/ollama.py
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 |
|
structured_output(output_model, prompt, callback_handler=None)
¶
Get structured output from the model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
output_model(Type[BaseModel])
|
The output model to use for the agent. |
required | |
prompt(Messages)
|
The prompt messages to use for the agent. |
required | |
callback_handler(Optional[Callable])
|
Optional callback handler for processing events. Defaults to None. |
required |
Source code in strands/models/ollama.py
317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 |
|
update_config(**model_config)
¶
Update the Ollama Model configuration with the provided arguments.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
**model_config
|
Unpack[OllamaConfig]
|
Configuration overrides. |
{}
|
Source code in strands/models/ollama.py
79 80 81 82 83 84 85 86 |
|
strands.models.openai
¶
OpenAI model provider.
- Docs: https://platform.openai.com/docs/overview
Client
¶
Bases: Protocol
Protocol defining the OpenAI-compatible interface for the underlying provider client.
Source code in strands/models/openai.py
22 23 24 25 26 27 28 29 |
|
chat
property
¶
Chat completions interface.
OpenAIModel
¶
Bases: OpenAIModel
OpenAI model provider implementation.
Source code in strands/models/openai.py
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 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 |
|
OpenAIConfig
¶
Bases: TypedDict
Configuration options for OpenAI models.
Attributes:
Name | Type | Description |
---|---|---|
model_id |
str
|
Model ID (e.g., "gpt-4o"). For a complete list of supported models, see https://platform.openai.com/docs/models. |
params |
Optional[dict[str, Any]]
|
Model parameters (e.g., max_tokens). For a complete list of supported parameters, see https://platform.openai.com/docs/api-reference/chat/create. |
Source code in strands/models/openai.py
37 38 39 40 41 42 43 44 45 46 47 48 49 |
|
__init__(client_args=None, **model_config)
¶
Initialize provider instance.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
client_args
|
Optional[dict[str, Any]]
|
Arguments for the OpenAI client. For a complete list of supported arguments, see https://pypi.org/project/openai/. |
None
|
**model_config
|
Unpack[OpenAIConfig]
|
Configuration options for the OpenAI model. |
{}
|
Source code in strands/models/openai.py
51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
|
get_config()
¶
Get the OpenAI model configuration.
Returns:
Type | Description |
---|---|
OpenAIConfig
|
The OpenAI model configuration. |
Source code in strands/models/openai.py
75 76 77 78 79 80 81 82 |
|
stream(request)
¶
Send the request to the OpenAI model and get the streaming response.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
request
|
dict[str, Any]
|
The formatted request to send to the OpenAI model. |
required |
Returns:
Type | Description |
---|---|
Iterable[dict[str, Any]]
|
An iterable of response events from the OpenAI model. |
Source code in strands/models/openai.py
84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 |
|
structured_output(output_model, prompt, callback_handler=None)
¶
Get structured output from the model.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
output_model(Type[BaseModel])
|
The output model to use for the agent. |
required | |
prompt(Messages)
|
The prompt messages to use for the agent. |
required | |
callback_handler(Optional[Callable])
|
Optional callback handler for processing events. Defaults to None. |
required |
Source code in strands/models/openai.py
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 |
|
update_config(**model_config)
¶
Update the OpenAI model configuration with the provided arguments.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
**model_config
|
Unpack[OpenAIConfig]
|
Configuration overrides. |
{}
|
Source code in strands/models/openai.py
66 67 68 69 70 71 72 73 |
|