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
|
import argparse
from flask import Flask, jsonify, request, Response
import urllib.parse
import requests
import time
import json
app = Flask(__name__)
parser = argparse.ArgumentParser(description="An example of using server.cpp with a similar API to OAI. It must be used together with server.cpp.")
parser.add_argument("--chat-prompt", type=str, help="the top prompt in chat completions(default: 'A chat between a curious user and an artificial intelligence assistant. The assistant follows the given rules no matter what.\\n')", default='A chat between a curious user and an artificial intelligence assistant. The assistant follows the given rules no matter what.\\n')
parser.add_argument("--user-name", type=str, help="USER name in chat completions(default: '\\nUSER: ')", default="\\nUSER: ")
parser.add_argument("--ai-name", type=str, help="ASSISTANT name in chat completions(default: '\\nASSISTANT: ')", default="\\nASSISTANT: ")
parser.add_argument("--system-name", type=str, help="SYSTEM name in chat completions(default: '\\nASSISTANT's RULE: ')", default="\\nASSISTANT's RULE: ")
parser.add_argument("--stop", type=str, help="the end of response in chat completions(default: '</s>')", default="</s>")
parser.add_argument("--llama-api", type=str, help="Set the address of server.cpp in llama.cpp(default: http://127.0.0.1:8080)", default='http://127.0.0.1:8080')
parser.add_argument("--api-key", type=str, help="Set the api key to allow only few user(default: NULL)", default="")
parser.add_argument("--host", type=str, help="Set the ip address to listen.(default: 127.0.0.1)", default='127.0.0.1')
parser.add_argument("--port", type=int, help="Set the port to listen.(default: 8081)", default=8081)
args = parser.parse_args()
def is_present(json, key):
try:
buf = json[key]
except KeyError:
return False
return True
#convert chat to prompt
def convert_chat(messages):
prompt = "" + args.chat_prompt.replace("\\n", "\n")
system_n = args.system_name.replace("\\n", "\n")
user_n = args.user_name.replace("\\n", "\n")
ai_n = args.ai_name.replace("\\n", "\n")
stop = args.stop.replace("\\n", "\n")
for line in messages:
if (line["role"] == "system"):
prompt += f"{system_n}{line['content']}"
if (line["role"] == "user"):
prompt += f"{user_n}{line['content']}"
if (line["role"] == "assistant"):
prompt += f"{ai_n}{line['content']}{stop}"
prompt += ai_n.rstrip()
return prompt
def make_postData(body, chat=False, stream=False):
postData = {}
if (chat):
postData["prompt"] = convert_chat(body["messages"])
else:
postData["prompt"] = body["prompt"]
if(is_present(body, "temperature")): postData["temperature"] = body["temperature"]
if(is_present(body, "top_k")): postData["top_k"] = body["top_k"]
if(is_present(body, "top_p")): postData["top_p"] = body["top_p"]
if(is_present(body, "max_tokens")): postData["n_predict"] = body["max_tokens"]
if(is_present(body, "presence_penalty")): postData["presence_penalty"] = body["presence_penalty"]
if(is_present(body, "frequency_penalty")): postData["frequency_penalty"] = body["frequency_penalty"]
if(is_present(body, "repeat_penalty")): postData["repeat_penalty"] = body["repeat_penalty"]
if(is_present(body, "mirostat")): postData["mirostat"] = body["mirostat"]
if(is_present(body, "mirostat_tau")): postData["mirostat_tau"] = body["mirostat_tau"]
if(is_present(body, "mirostat_eta")): postData["mirostat_eta"] = body["mirostat_eta"]
if(is_present(body, "seed")): postData["seed"] = body["seed"]
if(is_present(body, "logit_bias")): postData["logit_bias"] = [[int(token), body["logit_bias"][token]] for token in body["logit_bias"].keys()]
if (args.stop != ""):
postData["stop"] = [args.stop]
else:
postData["stop"] = []
if(is_present(body, "stop")): postData["stop"] += body["stop"]
postData["n_keep"] = -1
postData["stream"] = stream
return postData
def make_resData(data, chat=False, promptToken=[]):
resData = {
"id": "chatcmpl" if (chat) else "cmpl",
"object": "chat.completion" if (chat) else "text_completion",
"created": int(time.time()),
"truncated": data["truncated"],
"model": "LLaMA_CPP",
"usage": {
"prompt_tokens": data["tokens_evaluated"],
"completion_tokens": data["tokens_predicted"],
"total_tokens": data["tokens_evaluated"] + data["tokens_predicted"]
}
}
if (len(promptToken) != 0):
resData["promptToken"] = promptToken
if (chat):
#only one choice is supported
resData["choices"] = [{
"index": 0,
"message": {
"role": "assistant",
"content": data["content"],
},
"finish_reason": "stop" if (data["stopped_eos"] or data["stopped_word"]) else "length"
}]
else:
#only one choice is supported
resData["choices"] = [{
"text": data["content"],
"index": 0,
"logprobs": None,
"finish_reason": "stop" if (data["stopped_eos"] or data["stopped_word"]) else "length"
}]
return resData
def make_resData_stream(data, chat=False, time_now = 0, start=False):
resData = {
"id": "chatcmpl" if (chat) else "cmpl",
"object": "chat.completion.chunk" if (chat) else "text_completion.chunk",
"created": time_now,
"model": "LLaMA_CPP",
"choices": [
{
"finish_reason": None,
"index": 0
}
]
}
if (chat):
if (start):
resData["choices"][0]["delta"] = {
"role": "assistant"
}
else:
resData["choices"][0]["delta"] = {
"content": data["content"]
}
if (data["stop"]):
resData["choices"][0]["finish_reason"] = "stop" if (data["stopped_eos"] or data["stopped_word"]) else "length"
else:
resData["choices"][0]["text"] = data["content"]
if (data["stop"]):
resData["choices"][0]["finish_reason"] = "stop" if (data["stopped_eos"] or data["stopped_word"]) else "length"
return resData
@app.route('/chat/completions', methods=['POST'])
@app.route('/v1/chat/completions', methods=['POST'])
def chat_completions():
if (args.api_key != "" and request.headers["Authorization"].split()[1] != args.api_key):
return Response(status=403)
body = request.get_json()
stream = False
tokenize = False
if(is_present(body, "stream")): stream = body["stream"]
if(is_present(body, "tokenize")): tokenize = body["tokenize"]
postData = make_postData(body, chat=True, stream=stream)
promptToken = []
if (tokenize):
tokenData = requests.request("POST", urllib.parse.urljoin(args.llama_api, "/tokenize"), data=json.dumps({"content": postData["prompt"]})).json()
promptToken = tokenData["tokens"]
if (not stream):
data = requests.request("POST", urllib.parse.urljoin(args.llama_api, "/completion"), data=json.dumps(postData))
print(data.json())
resData = make_resData(data.json(), chat=True, promptToken=promptToken)
return jsonify(resData)
else:
def generate():
data = requests.request("POST", urllib.parse.urljoin(args.llama_api, "/completion"), data=json.dumps(postData), stream=True)
time_now = int(time.time())
resData = make_resData_stream({}, chat=True, time_now=time_now, start=True)
yield 'data: {}\n'.format(json.dumps(resData))
for line in data.iter_lines():
if line:
decoded_line = line.decode('utf-8')
resData = make_resData_stream(json.loads(decoded_line[6:]), chat=True, time_now=time_now)
yield 'data: {}\n'.format(json.dumps(resData))
return Response(generate(), mimetype='text/event-stream')
@app.route('/completions', methods=['POST'])
@app.route('/v1/completions', methods=['POST'])
def completion():
if (args.api_key != "" and request.headers["Authorization"].split()[1] != args.api_key):
return Response(status=403)
body = request.get_json()
stream = False
tokenize = False
if(is_present(body, "stream")): stream = body["stream"]
if(is_present(body, "tokenize")): tokenize = body["tokenize"]
postData = make_postData(body, chat=False, stream=stream)
promptToken = []
if (tokenize):
tokenData = requests.request("POST", urllib.parse.urljoin(args.llama_api, "/tokenize"), data=json.dumps({"content": postData["prompt"]})).json()
promptToken = tokenData["tokens"]
if (not stream):
data = requests.request("POST", urllib.parse.urljoin(args.llama_api, "/completion"), data=json.dumps(postData))
print(data.json())
resData = make_resData(data.json(), chat=False, promptToken=promptToken)
return jsonify(resData)
else:
def generate():
data = requests.request("POST", urllib.parse.urljoin(args.llama_api, "/completion"), data=json.dumps(postData), stream=True)
time_now = int(time.time())
for line in data.iter_lines():
if line:
decoded_line = line.decode('utf-8')
resData = make_resData_stream(json.loads(decoded_line[6:]), chat=False, time_now=time_now)
yield 'data: {}\n'.format(json.dumps(resData))
return Response(generate(), mimetype='text/event-stream')
if __name__ == '__main__':
app.run(args.host, port=args.port)
|
