File size: 6,486 Bytes
a8b3f00
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import logging

from flask_restful import reqparse
from werkzeug.exceptions import InternalServerError, NotFound

import services
from controllers.web import api
from controllers.web.error import (
    AppUnavailableError,
    CompletionRequestError,
    ConversationCompletedError,
    NotChatAppError,
    NotCompletionAppError,
    ProviderModelCurrentlyNotSupportError,
    ProviderNotInitializeError,
    ProviderQuotaExceededError,
)
from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
from controllers.web.wraps import WebApiResource
from core.app.apps.base_app_queue_manager import AppQueueManager
from core.app.entities.app_invoke_entities import InvokeFrom
from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
from core.model_runtime.errors.invoke import InvokeError
from libs import helper
from libs.helper import uuid_value
from models.model import AppMode
from services.app_generate_service import AppGenerateService
from services.errors.llm import InvokeRateLimitError


# define completion api for user
class CompletionApi(WebApiResource):
    def post(self, app_model, end_user):
        if app_model.mode != "completion":
            raise NotCompletionAppError()

        parser = reqparse.RequestParser()
        parser.add_argument("inputs", type=dict, required=True, location="json")
        parser.add_argument("query", type=str, location="json", default="")
        parser.add_argument("files", type=list, required=False, location="json")
        parser.add_argument("response_mode", type=str, choices=["blocking", "streaming"], location="json")
        parser.add_argument("retriever_from", type=str, required=False, default="web_app", location="json")

        args = parser.parse_args()

        streaming = args["response_mode"] == "streaming"
        args["auto_generate_name"] = False

        try:
            response = AppGenerateService.generate(
                app_model=app_model, user=end_user, args=args, invoke_from=InvokeFrom.WEB_APP, streaming=streaming
            )

            return helper.compact_generate_response(response)
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
        except services.errors.conversation.ConversationCompletedError:
            raise ConversationCompletedError()
        except services.errors.app_model_config.AppModelConfigBrokenError:
            logging.exception("App model config broken.")
            raise AppUnavailableError()
        except ProviderTokenNotInitError as ex:
            raise ProviderNotInitializeError(ex.description)
        except QuotaExceededError:
            raise ProviderQuotaExceededError()
        except ModelCurrentlyNotSupportError:
            raise ProviderModelCurrentlyNotSupportError()
        except InvokeError as e:
            raise CompletionRequestError(e.description)
        except ValueError as e:
            raise e
        except Exception as e:
            logging.exception("internal server error.")
            raise InternalServerError()


class CompletionStopApi(WebApiResource):
    def post(self, app_model, end_user, task_id):
        if app_model.mode != "completion":
            raise NotCompletionAppError()

        AppQueueManager.set_stop_flag(task_id, InvokeFrom.WEB_APP, end_user.id)

        return {"result": "success"}, 200


class ChatApi(WebApiResource):
    def post(self, app_model, end_user):
        app_mode = AppMode.value_of(app_model.mode)
        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        parser = reqparse.RequestParser()
        parser.add_argument("inputs", type=dict, required=True, location="json")
        parser.add_argument("query", type=str, required=True, location="json")
        parser.add_argument("files", type=list, required=False, location="json")
        parser.add_argument("response_mode", type=str, choices=["blocking", "streaming"], location="json")
        parser.add_argument("conversation_id", type=uuid_value, location="json")
        parser.add_argument("parent_message_id", type=uuid_value, required=False, location="json")
        parser.add_argument("retriever_from", type=str, required=False, default="web_app", location="json")

        args = parser.parse_args()

        streaming = args["response_mode"] == "streaming"
        args["auto_generate_name"] = False

        try:
            response = AppGenerateService.generate(
                app_model=app_model, user=end_user, args=args, invoke_from=InvokeFrom.WEB_APP, streaming=streaming
            )

            return helper.compact_generate_response(response)
        except services.errors.conversation.ConversationNotExistsError:
            raise NotFound("Conversation Not Exists.")
        except services.errors.conversation.ConversationCompletedError:
            raise ConversationCompletedError()
        except services.errors.app_model_config.AppModelConfigBrokenError:
            logging.exception("App model config broken.")
            raise AppUnavailableError()
        except ProviderTokenNotInitError as ex:
            raise ProviderNotInitializeError(ex.description)
        except QuotaExceededError:
            raise ProviderQuotaExceededError()
        except ModelCurrentlyNotSupportError:
            raise ProviderModelCurrentlyNotSupportError()
        except InvokeRateLimitError as ex:
            raise InvokeRateLimitHttpError(ex.description)
        except InvokeError as e:
            raise CompletionRequestError(e.description)
        except ValueError as e:
            raise e
        except Exception as e:
            logging.exception("internal server error.")
            raise InternalServerError()


class ChatStopApi(WebApiResource):
    def post(self, app_model, end_user, task_id):
        app_mode = AppMode.value_of(app_model.mode)
        if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:
            raise NotChatAppError()

        AppQueueManager.set_stop_flag(task_id, InvokeFrom.WEB_APP, end_user.id)

        return {"result": "success"}, 200


api.add_resource(CompletionApi, "/completion-messages")
api.add_resource(CompletionStopApi, "/completion-messages/<string:task_id>/stop")
api.add_resource(ChatApi, "/chat-messages")
api.add_resource(ChatStopApi, "/chat-messages/<string:task_id>/stop")