forked from abetlen/llama-cpp-python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathapp.py
More file actions
483 lines (411 loc) · 16.8 KB
/
app.py
File metadata and controls
483 lines (411 loc) · 16.8 KB
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
import json
import multiprocessing
from threading import Lock
from functools import partial
from typing import Iterator, List, Optional, Union, Dict
from typing_extensions import TypedDict, Literal
import llama_cpp
import anyio
from anyio.streams.memory import MemoryObjectSendStream
from starlette.concurrency import run_in_threadpool, iterate_in_threadpool
from fastapi import Depends, FastAPI, APIRouter, Request
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel, BaseSettings, Field, create_model_from_typeddict
from sse_starlette.sse import EventSourceResponse
class Settings(BaseSettings):
model: str = Field(
description="The path to the model to use for generating completions."
)
model_alias: Optional[str] = Field(
default=None,
description="The alias of the model to use for generating completions.",
)
n_ctx: int = Field(default=2048, ge=1, description="The context size.")
n_gpu_layers: int = Field(
default=0,
ge=0,
description="The number of layers to put on the GPU. The rest will be on the CPU.",
)
n_batch: int = Field(
default=512, ge=1, description="The batch size to use per eval."
)
n_threads: int = Field(
default=max(multiprocessing.cpu_count() // 2, 1),
ge=1,
description="The number of threads to use.",
)
f16_kv: bool = Field(default=True, description="Whether to use f16 key/value.")
use_mlock: bool = Field(
default=llama_cpp.llama_mlock_supported(),
description="Use mlock.",
)
use_mmap: bool = Field(
default=llama_cpp.llama_mmap_supported(),
description="Use mmap.",
)
embedding: bool = Field(default=True, description="Whether to use embeddings.")
last_n_tokens_size: int = Field(
default=64,
ge=0,
description="Last n tokens to keep for repeat penalty calculation.",
)
logits_all: bool = Field(default=True, description="Whether to return logits.")
cache: bool = Field(
default=False,
description="Use a cache to reduce processing times for evaluated prompts.",
)
cache_type: Literal["ram", "disk"] = Field(
default="ram",
description="The type of cache to use. Only used if cache is True.",
)
cache_size: int = Field(
default=2 << 30,
description="The size of the cache in bytes. Only used if cache is True.",
)
vocab_only: bool = Field(
default=False, description="Whether to only return the vocabulary."
)
verbose: bool = Field(
default=True, description="Whether to print debug information."
)
router = APIRouter()
settings: Optional[Settings] = None
llama: Optional[llama_cpp.Llama] = None
def create_app(settings: Optional[Settings] = None):
if settings is None:
settings = Settings()
app = FastAPI(
title="🦙 llama.cpp Python API",
version="0.0.1",
)
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
app.include_router(router)
global llama
llama = llama_cpp.Llama(
model_path=settings.model,
n_gpu_layers=settings.n_gpu_layers,
f16_kv=settings.f16_kv,
use_mlock=settings.use_mlock,
use_mmap=settings.use_mmap,
embedding=settings.embedding,
logits_all=settings.logits_all,
n_threads=settings.n_threads,
n_batch=settings.n_batch,
n_ctx=settings.n_ctx,
last_n_tokens_size=settings.last_n_tokens_size,
vocab_only=settings.vocab_only,
verbose=settings.verbose,
)
if settings.cache:
if settings.cache_type == "disk":
cache = llama_cpp.LlamaDiskCache(capacity_bytes=settings.cache_size)
else:
cache = llama_cpp.LlamaRAMCache(capacity_bytes=settings.cache_size)
cache = llama_cpp.LlamaCache(capacity_bytes=settings.cache_size)
llama.set_cache(cache)
def set_settings(_settings: Settings):
global settings
settings = _settings
set_settings(settings)
return app
llama_lock = Lock()
def get_llama():
with llama_lock:
yield llama
def get_settings():
yield settings
model_field = Field(description="The model to use for generating completions.")
max_tokens_field = Field(
default=16, ge=1, le=2048, description="The maximum number of tokens to generate."
)
temperature_field = Field(
default=0.8,
ge=0.0,
le=2.0,
description="Adjust the randomness of the generated text.\n\n"
+ "Temperature is a hyperparameter that controls the randomness of the generated text. It affects the probability distribution of the model's output tokens. A higher temperature (e.g., 1.5) makes the output more random and creative, while a lower temperature (e.g., 0.5) makes the output more focused, deterministic, and conservative. The default value is 0.8, which provides a balance between randomness and determinism. At the extreme, a temperature of 0 will always pick the most likely next token, leading to identical outputs in each run.",
)
top_p_field = Field(
default=0.95,
ge=0.0,
le=1.0,
description="Limit the next token selection to a subset of tokens with a cumulative probability above a threshold P.\n\n"
+ "Top-p sampling, also known as nucleus sampling, is another text generation method that selects the next token from a subset of tokens that together have a cumulative probability of at least p. This method provides a balance between diversity and quality by considering both the probabilities of tokens and the number of tokens to sample from. A higher value for top_p (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text.",
)
stop_field = Field(
default=None,
description="A list of tokens at which to stop generation. If None, no stop tokens are used.",
)
stream_field = Field(
default=False,
description="Whether to stream the results as they are generated. Useful for chatbots.",
)
top_k_field = Field(
default=40,
ge=0,
description="Limit the next token selection to the K most probable tokens.\n\n"
+ "Top-k sampling is a text generation method that selects the next token only from the top k most likely tokens predicted by the model. It helps reduce the risk of generating low-probability or nonsensical tokens, but it may also limit the diversity of the output. A higher value for top_k (e.g., 100) will consider more tokens and lead to more diverse text, while a lower value (e.g., 10) will focus on the most probable tokens and generate more conservative text.",
)
repeat_penalty_field = Field(
default=1.1,
ge=0.0,
description="A penalty applied to each token that is already generated. This helps prevent the model from repeating itself.\n\n"
+ "Repeat penalty is a hyperparameter used to penalize the repetition of token sequences during text generation. It helps prevent the model from generating repetitive or monotonous text. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient.",
)
presence_penalty_field = Field(
default=0.0,
ge=-2.0,
le=2.0,
description="Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.",
)
frequency_penalty_field = Field(
default=0.0,
ge=-2.0,
le=2.0,
description="Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
)
mirostat_mode_field = Field(
default=0,
ge=0,
le=2,
description="Enable Mirostat constant-perplexity algorithm of the specified version (1 or 2; 0 = disabled)"
)
mirostat_tau_field = Field(
default=5.0,
ge=0.0,
le=10.0,
description="Mirostat target entropy, i.e. the target perplexity - lower values produce focused and coherent text, larger values produce more diverse and less coherent text"
)
mirostat_eta_field = Field(
default=0.1,
ge=0.001,
le=1.0,
description="Mirostat learning rate"
)
class CreateCompletionRequest(BaseModel):
prompt: Union[str, List[str]] = Field(
default="", description="The prompt to generate completions for."
)
suffix: Optional[str] = Field(
default=None,
description="A suffix to append to the generated text. If None, no suffix is appended. Useful for chatbots.",
)
max_tokens: int = max_tokens_field
temperature: float = temperature_field
top_p: float = top_p_field
mirostat_mode: int = mirostat_mode_field
mirostat_tau: float = mirostat_tau_field
mirostat_eta: float = mirostat_eta_field
echo: bool = Field(
default=False,
description="Whether to echo the prompt in the generated text. Useful for chatbots.",
)
stop: Optional[Union[str, List[str]]] = stop_field
stream: bool = stream_field
logprobs: Optional[int] = Field(
default=None,
ge=0,
description="The number of logprobs to generate. If None, no logprobs are generated.",
)
presence_penalty: Optional[float] = presence_penalty_field
frequency_penalty: Optional[float] = frequency_penalty_field
# ignored or currently unsupported
model: Optional[str] = model_field
n: Optional[int] = 1
logprobs: Optional[int] = Field(None)
best_of: Optional[int] = 1
logit_bias: Optional[Dict[str, float]] = Field(None)
user: Optional[str] = Field(None)
# llama.cpp specific parameters
top_k: int = top_k_field
repeat_penalty: float = repeat_penalty_field
class Config:
schema_extra = {
"example": {
"prompt": "\n\n### Instructions:\nWhat is the capital of France?\n\n### Response:\n",
"stop": ["\n", "###"],
}
}
CreateCompletionResponse = create_model_from_typeddict(llama_cpp.Completion)
@router.post(
"/v1/completions",
response_model=CreateCompletionResponse,
)
async def create_completion(
request: Request,
body: CreateCompletionRequest,
llama: llama_cpp.Llama = Depends(get_llama),
):
if isinstance(body.prompt, list):
assert len(body.prompt) <= 1
body.prompt = body.prompt[0] if len(body.prompt) > 0 else ""
exclude = {
"n",
"best_of",
"logit_bias",
"user",
}
kwargs = body.dict(exclude=exclude)
if body.stream:
send_chan, recv_chan = anyio.create_memory_object_stream(10)
async def event_publisher(inner_send_chan: MemoryObjectSendStream):
async with inner_send_chan:
try:
iterator: Iterator[llama_cpp.CompletionChunk] = await run_in_threadpool(llama, **kwargs) # type: ignore
async for chunk in iterate_in_threadpool(iterator):
await inner_send_chan.send(dict(data=json.dumps(chunk)))
if await request.is_disconnected():
raise anyio.get_cancelled_exc_class()()
await inner_send_chan.send(dict(data="[DONE]"))
except anyio.get_cancelled_exc_class() as e:
print("disconnected")
with anyio.move_on_after(1, shield=True):
print(
f"Disconnected from client (via refresh/close) {request.client}"
)
await inner_send_chan.send(dict(closing=True))
raise e
return EventSourceResponse(
recv_chan, data_sender_callable=partial(event_publisher, send_chan)
)
else:
completion: llama_cpp.Completion = await run_in_threadpool(llama, **kwargs) # type: ignore
return completion
class CreateEmbeddingRequest(BaseModel):
model: Optional[str] = model_field
input: Union[str, List[str]] = Field(description="The input to embed.")
user: Optional[str]
class Config:
schema_extra = {
"example": {
"input": "The food was delicious and the waiter...",
}
}
CreateEmbeddingResponse = create_model_from_typeddict(llama_cpp.Embedding)
@router.post(
"/v1/embeddings",
response_model=CreateEmbeddingResponse,
)
async def create_embedding(
request: CreateEmbeddingRequest, llama: llama_cpp.Llama = Depends(get_llama)
):
return await run_in_threadpool(
llama.create_embedding, **request.dict(exclude={"user"})
)
class ChatCompletionRequestMessage(BaseModel):
role: Literal["system", "user", "assistant"] = Field(
default="user", description="The role of the message."
)
content: str = Field(default="", description="The content of the message.")
class CreateChatCompletionRequest(BaseModel):
messages: List[ChatCompletionRequestMessage] = Field(
default=[], description="A list of messages to generate completions for."
)
max_tokens: int = max_tokens_field
temperature: float = temperature_field
top_p: float = top_p_field
mirostat_mode: int = mirostat_mode_field
mirostat_tau: float = mirostat_tau_field
mirostat_eta: float = mirostat_eta_field
stop: Optional[List[str]] = stop_field
stream: bool = stream_field
presence_penalty: Optional[float] = presence_penalty_field
frequency_penalty: Optional[float] = frequency_penalty_field
# ignored or currently unsupported
model: Optional[str] = model_field
n: Optional[int] = 1
logit_bias: Optional[Dict[str, float]] = Field(None)
user: Optional[str] = Field(None)
# llama.cpp specific parameters
top_k: int = top_k_field
repeat_penalty: float = repeat_penalty_field
class Config:
schema_extra = {
"example": {
"messages": [
ChatCompletionRequestMessage(
role="system", content="You are a helpful assistant."
),
ChatCompletionRequestMessage(
role="user", content="What is the capital of France?"
),
]
}
}
CreateChatCompletionResponse = create_model_from_typeddict(llama_cpp.ChatCompletion)
@router.post(
"/v1/chat/completions",
response_model=CreateChatCompletionResponse,
)
async def create_chat_completion(
request: Request,
body: CreateChatCompletionRequest,
llama: llama_cpp.Llama = Depends(get_llama),
) -> Union[llama_cpp.ChatCompletion, EventSourceResponse]:
exclude = {
"n",
"logit_bias",
"user",
}
kwargs = body.dict(exclude=exclude)
if body.stream:
send_chan, recv_chan = anyio.create_memory_object_stream(10)
async def event_publisher(inner_send_chan: MemoryObjectSendStream):
async with inner_send_chan:
try:
iterator: Iterator[llama_cpp.ChatCompletionChunk] = await run_in_threadpool(llama.create_chat_completion, **kwargs) # type: ignore
async for chat_chunk in iterate_in_threadpool(iterator):
await inner_send_chan.send(dict(data=json.dumps(chat_chunk)))
if await request.is_disconnected():
raise anyio.get_cancelled_exc_class()()
await inner_send_chan.send(dict(data="[DONE]"))
except anyio.get_cancelled_exc_class() as e:
print("disconnected")
with anyio.move_on_after(1, shield=True):
print(
f"Disconnected from client (via refresh/close) {request.client}"
)
await inner_send_chan.send(dict(closing=True))
raise e
return EventSourceResponse(
recv_chan,
data_sender_callable=partial(event_publisher, send_chan),
)
else:
completion: llama_cpp.ChatCompletion = await run_in_threadpool(
llama.create_chat_completion, **kwargs # type: ignore
)
return completion
class ModelData(TypedDict):
id: str
object: Literal["model"]
owned_by: str
permissions: List[str]
class ModelList(TypedDict):
object: Literal["list"]
data: List[ModelData]
GetModelResponse = create_model_from_typeddict(ModelList)
@router.get("/v1/models", response_model=GetModelResponse)
async def get_models(
settings: Settings = Depends(get_settings),
llama: llama_cpp.Llama = Depends(get_llama),
) -> ModelList:
return {
"object": "list",
"data": [
{
"id": settings.model_alias
if settings.model_alias is not None
else llama.model_path,
"object": "model",
"owned_by": "me",
"permissions": [],
}
],
}