forked from DeepAuto-AI/sglang
-
Notifications
You must be signed in to change notification settings - Fork 0
/
readme_examples.py
109 lines (82 loc) · 2.61 KB
/
readme_examples.py
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
"""
Usage:
python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000
python readme_examples.py
"""
import sglang as sgl
@sgl.function
def tool_use(s, question):
s += "To answer this question: " + question + ". "
s += (
"I need to use a "
+ sgl.gen("tool", choices=["calculator", "search engine"])
+ ". "
)
if s["tool"] == "calculator":
s += "The math expression is" + sgl.gen("expression")
elif s["tool"] == "search engine":
s += "The key word to search is" + sgl.gen("word")
@sgl.function
def tip_suggestion(s):
s += (
"Here are two tips for staying healthy: "
"1. Balanced Diet. 2. Regular Exercise.\n\n"
)
forks = s.fork(2)
for i, f in enumerate(forks):
f += f"Now, expand tip {i+1} into a paragraph:\n"
f += sgl.gen(f"detailed_tip", max_tokens=256, stop="\n\n")
s += "Tip 1:" + forks[0]["detailed_tip"] + "\n"
s += "Tip 2:" + forks[1]["detailed_tip"] + "\n"
s += "In summary" + sgl.gen("summary")
@sgl.function
def regular_expression_gen(s):
s += "Q: What is the IP address of the Google DNS servers?\n"
s += "A: " + sgl.gen(
"answer",
temperature=0,
regex=r"((25[0-5]|2[0-4]\d|[01]?\d\d?).){3}(25[0-5]|2[0-4]\d|[01]?\d\d?)",
)
@sgl.function
def text_qa(s, question):
s += "Q: " + question + "\n"
s += "A:" + sgl.gen("answer", stop="\n")
def driver_tool_use():
state = tool_use.run(question="What is the capital of the United States?")
print(state.text())
print("\n")
def driver_tip_suggestion():
state = tip_suggestion.run()
print(state.text())
print("\n")
def driver_regex():
state = regular_expression_gen.run()
print(state.text())
print("\n")
def driver_batching():
states = text_qa.run_batch(
[
{"question": "What is the capital of the United Kingdom?"},
{"question": "What is the capital of France?"},
{"question": "What is the capital of Japan?"},
],
progress_bar=True,
)
for s in states:
print(s.text())
print("\n")
def driver_stream():
state = text_qa.run(
question="What is the capital of France?", temperature=0.1, stream=True
)
for out in state.text_iter():
print(out, end="", flush=True)
print("\n")
if __name__ == "__main__":
# sgl.set_default_backend(sgl.OpenAI("gpt-3.5-turbo-instruct"))
sgl.set_default_backend(sgl.RuntimeEndpoint("http://localhost:30000"))
driver_tool_use()
driver_tip_suggestion()
driver_regex()
driver_batching()
driver_stream()