Repository navigation
Expand file tree
/
Copy pathapp.py
More file actions
344 lines (303 loc) · 11.4 KB
/
Copy pathapp.py
File metadata and controls
344 lines (303 loc) · 11.4 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
from enum import auto, Enum
import json
import dataclasses
from typing import List
import aiohttp
from PIL import Image
import io
import os
import chainlit as cl
from chainlit.input_widget import Select, Slider
CONTROLLER_URL = os.environ.get("LLAVA_CONTROLLER_URL")
class SeparatorStyle(Enum):
"""Different separator style."""
SINGLE = auto()
TWO = auto()
MPT = auto()
PLAIN = auto()
LLAMA_2 = auto()
@dataclasses.dataclass
class Conversation:
"""A class that keeps all conversation history."""
system: str
roles: List[str]
messages: List[List[str]]
offset: int
sep_style: SeparatorStyle = SeparatorStyle.SINGLE
sep: str = "###"
sep2: str = None
version: str = "Unknown"
skip_next: bool = False
def get_prompt(self):
messages = self.messages
if self.sep_style == SeparatorStyle.SINGLE:
ret = self.system + self.sep
for role, message in messages:
if message:
if type(message) is tuple:
message, _, _ = message
ret += role + ": " + message + self.sep
else:
ret += role + ":"
elif self.sep_style == SeparatorStyle.TWO:
seps = [self.sep, self.sep2]
ret = self.system + seps[0]
for i, (role, message) in enumerate(messages):
if message:
if type(message) is tuple:
message, _, _ = message
ret += role + ": " + message + seps[i % 2]
else:
ret += role + ":"
elif self.sep_style == SeparatorStyle.MPT:
ret = self.system + self.sep
for role, message in messages:
if message:
if type(message) is tuple:
message, _, _ = message
ret += role + message + self.sep
else:
ret += role
elif self.sep_style == SeparatorStyle.LLAMA_2:
wrap_sys = lambda msg: f"<<SYS>>\n{msg}\n<</SYS>>\n\n"
wrap_inst = lambda msg: f"[INST] {msg} [/INST]"
ret = ""
for i, (role, message) in enumerate(messages):
if i == 0:
assert message, "first message should not be none"
assert role == self.roles[0], "first message should come from user"
if message:
if type(message) is tuple:
message, _, _ = message
if i == 0:
message = wrap_sys(self.system) + message
if i % 2 == 0:
message = wrap_inst(message)
ret += self.sep + message
else:
ret += " " + message + " " + self.sep2
else:
ret += ""
ret = ret.lstrip(self.sep)
elif self.sep_style == SeparatorStyle.PLAIN:
seps = [self.sep, self.sep2]
ret = self.system
for i, (role, message) in enumerate(messages):
if message:
if type(message) is tuple:
message, _, _ = message
ret += message + seps[i % 2]
else:
ret += ""
else:
raise ValueError(f"Invalid style: {self.sep_style}")
return ret
def append_message(self, role, message):
self.messages.append([role, message])
def get_images(self, return_pil=False):
images = []
for i, (role, msg) in enumerate(self.messages[self.offset :]):
if i % 2 == 0:
if type(msg) is tuple:
import base64
from io import BytesIO
from PIL import Image
msg, image, image_process_mode = msg
if image == None:
continue
if image_process_mode == "Pad":
def expand2square(pil_img, background_color=(122, 116, 104)):
width, height = pil_img.size
if width == height:
return pil_img
elif width > height:
result = Image.new(
pil_img.mode, (width, width), background_color
)
result.paste(pil_img, (0, (width - height) // 2))
return result
else:
result = Image.new(
pil_img.mode, (height, height), background_color
)
result.paste(pil_img, ((height - width) // 2, 0))
return result
image = expand2square(image)
elif image_process_mode in ["Default", "Crop"]:
pass
elif image_process_mode == "Resize":
image = image.resize((336, 336))
else:
raise ValueError(
f"Invalid image_process_mode: {image_process_mode}"
)
max_hw, min_hw = max(image.size), min(image.size)
aspect_ratio = max_hw / min_hw
max_len, min_len = 800, 400
shortest_edge = int(min(max_len / aspect_ratio, min_len, min_hw))
longest_edge = int(shortest_edge * aspect_ratio)
W, H = image.size
if longest_edge != max(image.size):
if H > W:
H, W = longest_edge, shortest_edge
else:
H, W = shortest_edge, longest_edge
image = image.resize((W, H))
if return_pil:
images.append(image)
else:
buffered = BytesIO()
image.save(buffered, format="PNG")
img_b64_str = base64.b64encode(buffered.getvalue()).decode()
images.append(img_b64_str)
return images
def copy(self):
return Conversation(
system=self.system,
roles=self.roles,
messages=[[x, y] for x, y in self.messages],
offset=self.offset,
sep_style=self.sep_style,
sep=self.sep,
sep2=self.sep2,
version=self.version,
)
def dict(self):
if len(self.get_images()) > 0:
return {
"system": self.system,
"roles": self.roles,
"messages": [
[x, y[0] if type(y) is tuple else y] for x, y in self.messages
],
"offset": self.offset,
"sep": self.sep,
"sep2": self.sep2,
}
return {
"system": self.system,
"roles": self.roles,
"messages": self.messages,
"offset": self.offset,
"sep": self.sep,
"sep2": self.sep2,
}
default_conversation = Conversation(
system="A chat between a curious human and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the human's questions.",
roles=("USER", "ASSISTANT"),
version="v1",
messages=(),
offset=0,
sep_style=SeparatorStyle.TWO,
sep=" ",
sep2="</s>",
)
headers = {"User-Agent": "LLaVA Client"}
image_process_mode = "Default"
async def request(conversation: Conversation, settings):
pload = {
"model": settings["model"],
"prompt": conversation.get_prompt(),
"temperature": settings["temperature"],
"top_p": settings["top_p"],
"max_new_tokens": int(settings["max_token"]),
"stop": conversation.sep
if conversation.sep_style in [SeparatorStyle.SINGLE, SeparatorStyle.MPT]
else conversation.sep2,
}
pload["images"] = conversation.get_images()
async with aiohttp.ClientSession() as session:
async with session.post(
CONTROLLER_URL + "/worker_generate_stream",
headers=headers,
data=json.dumps(pload),
timeout=10,
) as response:
chainlit_message = cl.Message(content="")
async for chunk in response.content.iter_any():
for json_str in chunk.decode().split("\0"):
if json_str:
data = json.loads(json_str)
if data["error_code"] == 0:
output = data["text"][len(pload["prompt"]) :].strip()
conversation.messages[-1][-1] = output + "▌"
await chainlit_message.stream_token(
output, is_sequence=True
)
else:
output = (
data["text"] + f" (error_code: {data['error_code']})"
)
conversation.messages[-1][-1] = output
chainlit_message.content = output
await chainlit_message.send()
return conversation
@cl.on_chat_start
async def start():
settings = await cl.ChatSettings(
[
Select(
id="model",
label="Model",
values=["llava-v1.5-13b"],
initial_index=0,
),
Slider(
id="temperature",
label="Temperature",
initial=0,
min=0,
max=1,
step=0.1,
),
Slider(
id="top_p",
label="Top P",
initial=0.7,
min=0,
max=1,
step=0.1,
),
Slider(
id="max_token",
label="Max output tokens",
initial=512,
min=0,
max=1024,
step=64,
),
]
).send()
conversation = default_conversation.copy()
cl.user_session.set("conversation", conversation)
cl.user_session.set("settings", settings)
@cl.on_settings_update
async def setup_agent(settings):
cl.user_session.set("settings", settings)
@cl.on_message
async def main(message: cl.Message):
image = next(
(
Image.open(file.path)
for file in message.elements or []
if "image" in file.mime and file.path is not None
),
None,
)
conv = cl.user_session.get("conversation") # type: Conversation
settings = cl.user_session.get("settings")
if image:
if len(conv.get_images(return_pil=True)) > 0:
# reset
conv = default_conversation.copy()
text = message.content[:1200]
if "<image>" not in text:
text = "<image>\n" + text
else:
text = message.content[:1536]
conv_message = (text, image, image_process_mode)
conv.append_message(conv.roles[0], conv_message)
conv.append_message(conv.roles[1], None)
conv = await request(conv, settings)
cl.user_session.set("conversation", conv)