File size: 6,554 Bytes
c2bd343
 
 
 
1488dea
c2bd343
 
1815722
 
 
 
 
 
 
 
c2bd343
1815722
c2bd343
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1815722
c2bd343
1815722
c2bd343
 
 
 
 
 
 
 
 
1815722
 
 
 
 
 
 
c2bd343
 
1815722
c2bd343
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1815722
 
c2bd343
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1815722
 
 
 
 
c2bd343
 
 
 
 
 
 
 
 
 
1815722
 
 
 
 
 
 
c2bd343
 
1815722
c2bd343
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1815722
 
 
c2bd343
 
 
1815722
 
 
c2bd343
 
 
 
1815722
 
c2bd343
 
 
 
 
 
 
 
 
 
1815722
1488dea
c2bd343
 
 
 
1815722
c2bd343
 
 
 
 
 
 
 
 
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
from datetime import datetime
import json
from typing import Any, Dict, Optional
import uuid
import re

import httpx
from api.config import (
    MODEL_MAPPING,
    MODEL_ALIASES,
    headers,
    AGENT_MODE,
    TRENDING_AGENT_MODE,
    BASE_URL
)
from fastapi import HTTPException
from api.models import ChatRequest

from api.logger import setup_logger

logger = setup_logger(__name__)


def create_chat_completion_data(
    content: str, model: str, timestamp: int, finish_reason: Optional[str] = None
) -> Dict[str, Any]:
    return {
        "id": f"chatcmpl-{uuid.uuid4()}",
        "object": "chat.completion.chunk",
        "created": timestamp,
        "model": model,
        "choices": [
            {
                "index": 0,
                "delta": {"content": content, "role": "assistant"},
                "finish_reason": finish_reason,
            }
        ],
        "usage": None,
    }


def message_to_dict(message):
    if isinstance(message.content, str):
        return {"role": message.role, "content": message.content}
    elif isinstance(message.content, list) and len(message.content) == 2:
        return {
            "role": message.role,
            "content": message.content[0]["text"],
            "data": {
                "imageBase64": message.content[1]["image_url"]["url"],
                "fileText": "",
                "title": "snapshot",
            },
        }
    else:
        return {"role": message.role, "content": message.content}


async def process_streaming_response(request: ChatRequest):
    # Map the requested model to the actual model used by the API
    model = MODEL_MAPPING.get(request.model, MODEL_ALIASES.get(request.model, "blackboxai"))

    logger.info(f"Using model: {model}")

    agent_mode = AGENT_MODE.get(model, {})
    trending_agent_mode = TRENDING_AGENT_MODE.get(model, {})

    json_data = {
        "messages": [message_to_dict(msg) for msg in request.messages],
        "previewToken": None,
        "userId": None,
        "codeModelMode": True,
        "agentMode": agent_mode,
        "trendingAgentMode": trending_agent_mode,
        "isMicMode": False,
        "userSystemPrompt": None,
        "maxTokens": request.max_tokens,
        "playgroundTopP": request.top_p,
        "playgroundTemperature": request.temperature,
        "isChromeExt": False,
        "githubToken": None,
        "clickedAnswer2": False,
        "clickedAnswer3": False,
        "clickedForceWebSearch": False,
        "visitFromDelta": False,
        "mobileClient": False,
        "userSelectedModel": model,
    }

    logger.debug(f"Payload for streaming request: {json.dumps(json_data)}")

    async with httpx.AsyncClient() as client:
        try:
            async with client.stream(
                "POST",
                f"{BASE_URL}/api/chat",
                headers=headers,
                json=json_data,
                timeout=100,
            ) as response:
                response.raise_for_status()
                async for line in response.aiter_lines():
                    timestamp = int(datetime.now().timestamp())
                    if line:
                        content = line
                        if content.startswith("$@$v=undefined-rv1$@$"):
                            content = content[21:]
                        yield f"data: {json.dumps(create_chat_completion_data(content, model, timestamp))}\n\n"

                # Indicate the end of the stream
                timestamp = int(datetime.now().timestamp())
                yield f"data: {json.dumps(create_chat_completion_data('', model, timestamp, 'stop'))}\n\n"
                yield "data: [DONE]\n\n"
        except httpx.HTTPStatusError as e:
            logger.error(f"HTTP error occurred: {e}")
            raise HTTPException(status_code=e.response.status_code, detail=str(e))
        except httpx.RequestError as e:
            logger.error(f"Error occurred during request: {e}")
            raise HTTPException(status_code=500, detail=str(e))


async def process_non_streaming_response(request: ChatRequest):
    # Map the requested model to the actual model used by the API
    model = MODEL_MAPPING.get(request.model, MODEL_ALIASES.get(request.model, "blackboxai"))

    logger.info(f"Using model: {model}")

    agent_mode = AGENT_MODE.get(model, {})
    trending_agent_mode = TRENDING_AGENT_MODE.get(model, {})

    json_data = {
        "messages": [message_to_dict(msg) for msg in request.messages],
        "previewToken": None,
        "userId": None,
        "codeModelMode": True,
        "agentMode": agent_mode,
        "trendingAgentMode": trending_agent_mode,
        "isMicMode": False,
        "userSystemPrompt": None,
        "maxTokens": request.max_tokens,
        "playgroundTopP": request.top_p,
        "playgroundTemperature": request.temperature,
        "isChromeExt": False,
        "githubToken": None,
        "clickedAnswer2": False,
        "clickedAnswer3": False,
        "clickedForceWebSearch": False,
        "visitFromDelta": False,
        "mobileClient": False,
        "userSelectedModel": model,
    }

    logger.debug(f"Payload for non-streaming request: {json.dumps(json_data)}")

    full_response = ""
    async with httpx.AsyncClient() as client:
        try:
            async with client.stream(
                method="POST",
                url=f"{BASE_URL}/api/chat",
                headers=headers,
                json=json_data,
            ) as response:
                response.raise_for_status()
                async for chunk in response.aiter_text():
                    full_response += chunk
        except httpx.HTTPStatusError as e:
            logger.error(f"HTTP error occurred: {e}")
            raise HTTPException(status_code=e.response.status_code, detail=str(e))
        except httpx.RequestError as e:
            logger.error(f"Error occurred during request: {e}")
            raise HTTPException(status_code=500, detail=str(e))

    if full_response.startswith("$@$v=undefined-rv1$@$"):
        full_response = full_response[21:]

    logger.debug(f"Full non-streaming response: {full_response}")

    return {
        "id": f"chatcmpl-{uuid.uuid4()}",
        "object": "chat.completion",
        "created": int(datetime.now().timestamp()),
        "model": model,
        "choices": [
            {
                "index": 0,
                "message": {"role": "assistant", "content": full_response},
                "finish_reason": "stop",
            }
        ],
        "usage": None,
    }