forked from anthropics/anthropic-sdk-typescript
-
Notifications
You must be signed in to change notification settings - Fork 0
/
messages.ts
729 lines (659 loc) · 22.2 KB
/
messages.ts
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
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
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
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
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
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
import * as Core from '@anthropic-ai/sdk/core';
import { APIPromise } from '@anthropic-ai/sdk/core';
import { APIResource } from '@anthropic-ai/sdk/resource';
import { MessageStream } from '@anthropic-ai/sdk/lib/MessageStream';
export { MessageStream } from '@anthropic-ai/sdk/lib/MessageStream';
import * as MessagesAPI from '@anthropic-ai/sdk/resources/messages';
import { Stream } from '@anthropic-ai/sdk/streaming';
export class Messages extends APIResource {
/**
* Create a Message.
*
* Send a structured list of input messages with text and/or image content, and the
* model will generate the next message in the conversation.
*
* The Messages API can be used for for either single queries or stateless
* multi-turn conversations.
*/
create(body: MessageCreateParamsNonStreaming, options?: Core.RequestOptions): APIPromise<Message>;
create(
body: MessageCreateParamsStreaming,
options?: Core.RequestOptions,
): APIPromise<Stream<MessageStreamEvent>>;
create(
body: MessageCreateParamsBase,
options?: Core.RequestOptions,
): APIPromise<Stream<MessageStreamEvent> | Message>;
create(
body: MessageCreateParams,
options?: Core.RequestOptions,
): APIPromise<Message> | APIPromise<Stream<MessageStreamEvent>> {
return this._client.post('/v1/messages', {
body,
timeout: 600000,
...options,
stream: body.stream ?? false,
}) as APIPromise<Message> | APIPromise<Stream<MessageStreamEvent>>;
}
/**
* Create a Message stream
*/
stream(body: MessageStreamParams, options?: Core.RequestOptions): MessageStream {
return MessageStream.createMessage(this, body, options);
}
}
export interface ContentBlock {
text: string;
type: 'text';
}
export interface ContentBlockDeltaEvent {
delta: TextDelta;
index: number;
type: 'content_block_delta';
}
export interface ContentBlockStartEvent {
content_block: ContentBlock;
index: number;
type: 'content_block_start';
}
export interface ContentBlockStopEvent {
index: number;
type: 'content_block_stop';
}
export interface ImageBlockParam {
source: ImageBlockParam.Source;
type?: 'image';
}
export namespace ImageBlockParam {
export interface Source {
data: string;
media_type: 'image/jpeg' | 'image/png' | 'image/gif' | 'image/webp';
type?: 'base64';
}
}
export interface Message {
/**
* Unique object identifier.
*
* The format and length of IDs may change over time.
*/
id: string;
/**
* Content generated by the model.
*
* This is an array of content blocks, each of which has a `type` that determines
* its shape. Currently, the only `type` in responses is `"text"`.
*
* Example:
*
* ```json
* [{ "type": "text", "text": "Hi, I'm Claude." }]
* ```
*
* If the request input `messages` ended with an `assistant` turn, then the
* response `content` will continue directly from that last turn. You can use this
* to constrain the model's output.
*
* For example, if the input `messages` were:
*
* ```json
* [
* {
* "role": "user",
* "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"
* },
* { "role": "assistant", "content": "The best answer is (" }
* ]
* ```
*
* Then the response `content` might be:
*
* ```json
* [{ "type": "text", "text": "B)" }]
* ```
*/
content: Array<ContentBlock>;
/**
* The model that handled the request.
*/
model: string;
/**
* Conversational role of the generated message.
*
* This will always be `"assistant"`.
*/
role: 'assistant';
/**
* The reason that we stopped.
*
* This may be one the following values:
*
* - `"end_turn"`: the model reached a natural stopping point
* - `"max_tokens"`: we exceeded the requested `max_tokens` or the model's maximum
* - `"stop_sequence"`: one of your provided custom `stop_sequences` was generated
*
* Note that these values are different than those in `/v1/complete`, where
* `end_turn` and `stop_sequence` were not differentiated.
*
* In non-streaming mode this value is always non-null. In streaming mode, it is
* null in the `message_start` event and non-null otherwise.
*/
stop_reason: 'end_turn' | 'max_tokens' | 'stop_sequence' | null;
/**
* Which custom stop sequence was generated, if any.
*
* This value will be a non-null string if one of your custom stop sequences was
* generated.
*/
stop_sequence: string | null;
/**
* Object type.
*
* For Messages, this is always `"message"`.
*/
type: 'message';
/**
* Billing and rate-limit usage.
*
* Anthropic's API bills and rate-limits by token counts, as tokens represent the
* underlying cost to our systems.
*
* Under the hood, the API transforms requests into a format suitable for the
* model. The model's output then goes through a parsing stage before becoming an
* API response. As a result, the token counts in `usage` will not match one-to-one
* with the exact visible content of an API request or response.
*
* For example, `output_tokens` will be non-zero, even for an empty string response
* from Claude.
*/
usage: Usage;
}
export interface MessageDeltaEvent {
delta: MessageDeltaEvent.Delta;
type: 'message_delta';
/**
* Billing and rate-limit usage.
*
* Anthropic's API bills and rate-limits by token counts, as tokens represent the
* underlying cost to our systems.
*
* Under the hood, the API transforms requests into a format suitable for the
* model. The model's output then goes through a parsing stage before becoming an
* API response. As a result, the token counts in `usage` will not match one-to-one
* with the exact visible content of an API request or response.
*
* For example, `output_tokens` will be non-zero, even for an empty string response
* from Claude.
*/
usage: MessageDeltaUsage;
}
export namespace MessageDeltaEvent {
export interface Delta {
stop_reason: 'end_turn' | 'max_tokens' | 'stop_sequence' | null;
stop_sequence: string | null;
}
}
export interface MessageDeltaUsage {
/**
* The cumulative number of output tokens which were used.
*/
output_tokens: number;
}
export interface MessageParam {
content: string | Array<TextBlock | ImageBlockParam>;
role: 'user' | 'assistant';
}
export interface MessageStartEvent {
message: Message;
type: 'message_start';
}
export interface MessageStopEvent {
type: 'message_stop';
}
export type MessageStreamEvent =
| MessageStartEvent
| MessageDeltaEvent
| MessageStopEvent
| ContentBlockStartEvent
| ContentBlockDeltaEvent
| ContentBlockStopEvent;
export interface TextBlock {
text: string;
type?: 'text';
}
export interface TextDelta {
text: string;
type: 'text_delta';
}
export interface Usage {
/**
* The number of input tokens which were used.
*/
input_tokens: number;
/**
* The number of output tokens which were used.
*/
output_tokens: number;
}
export type MessageCreateParams = MessageCreateParamsNonStreaming | MessageCreateParamsStreaming;
export interface MessageCreateParamsBase {
/**
* The maximum number of tokens to generate before stopping.
*
* Note that our models may stop _before_ reaching this maximum. This parameter
* only specifies the absolute maximum number of tokens to generate.
*
* Different models have different maximum values for this parameter. See
* [models](https://docs.anthropic.com/claude/docs/models-overview) for details.
*/
max_tokens: number;
/**
* Input messages.
*
* Our models are trained to operate on alternating `user` and `assistant`
* conversational turns. When creating a new `Message`, you specify the prior
* conversational turns with the `messages` parameter, and the model then generates
* the next `Message` in the conversation.
*
* Each input message must be an object with a `role` and `content`. You can
* specify a single `user`-role message, or you can include multiple `user` and
* `assistant` messages. The first message must always use the `user` role.
*
* If the final message uses the `assistant` role, the response content will
* continue immediately from the content in that message. This can be used to
* constrain part of the model's response.
*
* Example with a single `user` message:
*
* ```json
* [{ "role": "user", "content": "Hello, Claude" }]
* ```
*
* Example with multiple conversational turns:
*
* ```json
* [
* { "role": "user", "content": "Hello there." },
* { "role": "assistant", "content": "Hi, I'm Claude. How can I help you?" },
* { "role": "user", "content": "Can you explain LLMs in plain English?" }
* ]
* ```
*
* Example with a partially-filled response from Claude:
*
* ```json
* [
* {
* "role": "user",
* "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"
* },
* { "role": "assistant", "content": "The best answer is (" }
* ]
* ```
*
* Each input message `content` may be either a single `string` or an array of
* content blocks, where each block has a specific `type`. Using a `string` for
* `content` is shorthand for an array of one content block of type `"text"`. The
* following input messages are equivalent:
*
* ```json
* { "role": "user", "content": "Hello, Claude" }
* ```
*
* ```json
* { "role": "user", "content": [{ "type": "text", "text": "Hello, Claude" }] }
* ```
*
* Starting with Claude 3 models, you can also send image content blocks:
*
* ```json
* {
* "role": "user",
* "content": [
* {
* "type": "image",
* "source": {
* "type": "base64",
* "media_type": "image/jpeg",
* "data": "/9j/4AAQSkZJRg..."
* }
* },
* { "type": "text", "text": "What is in this image?" }
* ]
* }
* ```
*
* We currently support the `base64` source type for images, and the `image/jpeg`,
* `image/png`, `image/gif`, and `image/webp` media types.
*
* See [examples](https://docs.anthropic.com/claude/reference/messages-examples)
* for more input examples.
*
* Note that if you want to include a
* [system prompt](https://docs.anthropic.com/claude/docs/system-prompts), you can
* use the top-level `system` parameter — there is no `"system"` role for input
* messages in the Messages API.
*/
messages: Array<MessageParam>;
/**
* The model that will complete your prompt.
*
* See [models](https://docs.anthropic.com/claude/docs/models-overview) for
* additional details and options.
*/
model:
| (string & {})
| 'claude-3-opus-20240229'
| 'claude-3-sonnet-20240229'
| 'claude-3-haiku-20240307'
| "claude-2.1'"
| 'claude-2.0'
| 'claude-instant-1.2';
/**
* An object describing metadata about the request.
*/
metadata?: MessageCreateParams.Metadata;
/**
* Custom text sequences that will cause the model to stop generating.
*
* Our models will normally stop when they have naturally completed their turn,
* which will result in a response `stop_reason` of `"end_turn"`.
*
* If you want the model to stop generating when it encounters custom strings of
* text, you can use the `stop_sequences` parameter. If the model encounters one of
* the custom sequences, the response `stop_reason` value will be `"stop_sequence"`
* and the response `stop_sequence` value will contain the matched stop sequence.
*/
stop_sequences?: Array<string>;
/**
* Whether to incrementally stream the response using server-sent events.
*
* See [streaming](https://docs.anthropic.com/claude/reference/messages-streaming)
* for details.
*/
stream?: boolean;
/**
* System prompt.
*
* A system prompt is a way of providing context and instructions to Claude, such
* as specifying a particular goal or role. See our
* [guide to system prompts](https://docs.anthropic.com/claude/docs/system-prompts).
*/
system?: string;
/**
* Amount of randomness injected into the response.
*
* Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0`
* for analytical / multiple choice, and closer to `1.0` for creative and
* generative tasks.
*
* Note that even with `temperature` of `0.0`, the results will not be fully
* deterministic.
*/
temperature?: number;
/**
* Only sample from the top K options for each subsequent token.
*
* Used to remove "long tail" low probability responses.
* [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).
*
* Recommended for advanced use cases only. You usually only need to use
* `temperature`.
*/
top_k?: number;
/**
* Use nucleus sampling.
*
* In nucleus sampling, we compute the cumulative distribution over all the options
* for each subsequent token in decreasing probability order and cut it off once it
* reaches a particular probability specified by `top_p`. You should either alter
* `temperature` or `top_p`, but not both.
*
* Recommended for advanced use cases only. You usually only need to use
* `temperature`.
*/
top_p?: number;
}
export namespace MessageCreateParams {
/**
* An object describing metadata about the request.
*/
export interface Metadata {
/**
* An external identifier for the user who is associated with the request.
*
* This should be a uuid, hash value, or other opaque identifier. Anthropic may use
* this id to help detect abuse. Do not include any identifying information such as
* name, email address, or phone number.
*/
user_id?: string | null;
}
export type MessageCreateParamsNonStreaming = MessagesAPI.MessageCreateParamsNonStreaming;
export type MessageCreateParamsStreaming = MessagesAPI.MessageCreateParamsStreaming;
}
export interface MessageCreateParamsNonStreaming extends MessageCreateParamsBase {
/**
* Whether to incrementally stream the response using server-sent events.
*
* See [streaming](https://docs.anthropic.com/claude/reference/messages-streaming)
* for details.
*/
stream?: false;
}
export interface MessageCreateParamsStreaming extends MessageCreateParamsBase {
/**
* Whether to incrementally stream the response using server-sent events.
*
* See [streaming](https://docs.anthropic.com/claude/reference/messages-streaming)
* for details.
*/
stream: true;
}
export interface MessageStreamParams {
/**
* The maximum number of tokens to generate before stopping.
*
* Note that our models may stop _before_ reaching this maximum. This parameter
* only specifies the absolute maximum number of tokens to generate.
*
* Different models have different maximum values for this parameter. See
* [models](https://docs.anthropic.com/claude/docs/models-overview) for details.
*/
max_tokens: number;
/**
* Input messages.
*
* Our models are trained to operate on alternating `user` and `assistant`
* conversational turns. When creating a new `Message`, you specify the prior
* conversational turns with the `messages` parameter, and the model then generates
* the next `Message` in the conversation.
*
* Each input message must be an object with a `role` and `content`. You can
* specify a single `user`-role message, or you can include multiple `user` and
* `assistant` messages. The first message must always use the `user` role.
*
* If the final message uses the `assistant` role, the response content will
* continue immediately from the content in that message. This can be used to
* constrain part of the model's response.
*
* Example with a single `user` message:
*
* ```json
* [{ "role": "user", "content": "Hello, Claude" }]
* ```
*
* Example with multiple conversational turns:
*
* ```json
* [
* { "role": "user", "content": "Hello there." },
* { "role": "assistant", "content": "Hi, I'm Claude. How can I help you?" },
* { "role": "user", "content": "Can you explain LLMs in plain English?" }
* ]
* ```
*
* Example with a partially-filled response from Claude:
*
* ```json
* [
* {
* "role": "user",
* "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"
* },
* { "role": "assistant", "content": "The best answer is (" }
* ]
* ```
*
* Each input message `content` may be either a single `string` or an array of
* content blocks, where each block has a specific `type`. Using a `string` for
* `content` is shorthand for an array of one content block of type `"text"`. The
* following input messages are equivalent:
*
* ```json
* { "role": "user", "content": "Hello, Claude" }
* ```
*
* ```json
* { "role": "user", "content": [{ "type": "text", "text": "Hello, Claude" }] }
* ```
*
* Starting with Claude 3 models, you can also send image content blocks:
*
* ```json
* {
* "role": "user",
* "content": [
* {
* "type": "image",
* "source": {
* "type": "base64",
* "media_type": "image/jpeg",
* "data": "/9j/4AAQSkZJRg..."
* }
* },
* { "type": "text", "text": "What is in this image?" }
* ]
* }
* ```
*
* We currently support the `base64` source type for images, and the `image/jpeg`,
* `image/png`, `image/gif`, and `image/webp` media types.
*
* See [examples](https://docs.anthropic.com/claude/reference/messages-examples)
* for more input examples.
*
* Note that if you want to include a
* [system prompt](https://docs.anthropic.com/claude/docs/system-prompts), you can
* use the top-level `system` parameter — there is no `"system"` role for input
* messages in the Messages API.
*/
messages: Array<MessageParam>;
/**
* The model that will complete your prompt.
*
* See [models](https://docs.anthropic.com/claude/docs/models-overview) for
* additional details and options.
*/
model:
| (string & {})
| 'claude-3-opus-20240229'
| 'claude-3-sonnet-20240229'
| 'claude-3-haiku-20240307'
| "claude-2.1'"
| 'claude-2.0'
| 'claude-instant-1.2';
/**
* An object describing metadata about the request.
*/
metadata?: MessageStreamParams.Metadata;
/**
* Custom text sequences that will cause the model to stop generating.
*
* Our models will normally stop when they have naturally completed their turn,
* which will result in a response `stop_reason` of `"end_turn"`.
*
* If you want the model to stop generating when it encounters custom strings of
* text, you can use the `stop_sequences` parameter. If the model encounters one of
* the custom sequences, the response `stop_reason` value will be `"stop_sequence"`
* and the response `stop_sequence` value will contain the matched stop sequence.
*/
stop_sequences?: Array<string>;
/**
* System prompt.
*
* A system prompt is a way of providing context and instructions to Claude, such
* as specifying a particular goal or role. See our
* [guide to system prompts](https://docs.anthropic.com/claude/docs/system-prompts).
*/
system?: string;
/**
* Amount of randomness injected into the response.
*
* Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0`
* for analytical / multiple choice, and closer to `1.0` for creative and
* generative tasks.
*
* Note that even with `temperature` of `0.0`, the results will not be fully
* deterministic.
*/
temperature?: number;
/**
* Only sample from the top K options for each subsequent token.
*
* Used to remove "long tail" low probability responses.
* [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).
*
* Recommended for advanced use cases only. You usually only need to use
* `temperature`.
*/
top_k?: number;
/**
* Use nucleus sampling.
*
* In nucleus sampling, we compute the cumulative distribution over all the options
* for each subsequent token in decreasing probability order and cut it off once it
* reaches a particular probability specified by `top_p`. You should either alter
* `temperature` or `top_p`, but not both.
*
* Recommended for advanced use cases only. You usually only need to use
* `temperature`.
*/
top_p?: number;
}
export namespace MessageStreamParams {
/**
* An object describing metadata about the request.
*/
export interface Metadata {
/**
* An external identifier for the user who is associated with the request.
*
* This should be a uuid, hash value, or other opaque identifier. Anthropic may use
* this id to help detect abuse. Do not include any identifying information such as
* name, email address, or phone number.
*/
user_id?: string | null;
}
}
export namespace Messages {
export import ContentBlock = MessagesAPI.ContentBlock;
export import ContentBlockDeltaEvent = MessagesAPI.ContentBlockDeltaEvent;
export import ContentBlockStartEvent = MessagesAPI.ContentBlockStartEvent;
export import ContentBlockStopEvent = MessagesAPI.ContentBlockStopEvent;
export import ImageBlockParam = MessagesAPI.ImageBlockParam;
export import Message = MessagesAPI.Message;
export import MessageDeltaEvent = MessagesAPI.MessageDeltaEvent;
export import MessageDeltaUsage = MessagesAPI.MessageDeltaUsage;
export import MessageParam = MessagesAPI.MessageParam;
export import MessageStartEvent = MessagesAPI.MessageStartEvent;
export import MessageStopEvent = MessagesAPI.MessageStopEvent;
export import MessageStreamEvent = MessagesAPI.MessageStreamEvent;
export import TextBlock = MessagesAPI.TextBlock;
export import TextDelta = MessagesAPI.TextDelta;
export import Usage = MessagesAPI.Usage;
export import MessageCreateParams = MessagesAPI.MessageCreateParams;
export import MessageCreateParamsNonStreaming = MessagesAPI.MessageCreateParamsNonStreaming;
export import MessageCreateParamsStreaming = MessagesAPI.MessageCreateParamsStreaming;
export import MessageStreamParams = MessagesAPI.MessageStreamParams;
}