File size: 4,734 Bytes
88a6b83
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import asyncio
import json
from concurrent.futures import ThreadPoolExecutor
from typing import List

import g4f

from fastapi import FastAPI, HTTPException, Header
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import StreamingResponse
from pydantic import BaseModel

# =====================================
# CONFIG
# =====================================

API_KEY = "sk-your-secret-key"

PROVIDERS = [
    g4f.Provider.DuckDuckGo,
    g4f.Provider.Blackbox,
]

executor = ThreadPoolExecutor(max_workers=5)

# =====================================
# APP
# =====================================

app = FastAPI(
    title="HuggingFace AI Gateway"
)

app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_methods=["*"],
    allow_headers=["*"],
)

# =====================================
# MODELS
# =====================================

class Message(BaseModel):
    role: str
    content: str

class ChatRequest(BaseModel):
    model: str = "gpt-4o-mini"
    messages: List[Message]
    stream: bool = False

# =====================================
# AUTH
# =====================================

def verify_api_key(auth: str):

    if not auth.startswith("Bearer "):
        raise HTTPException(
            status_code=401,
            detail="Invalid Authorization"
        )

    token = auth.replace("Bearer ", "")

    if token != API_KEY:
        raise HTTPException(
            status_code=403,
            detail="Invalid API Key"
        )

# =====================================
# GENERATE
# =====================================

def generate(model, messages):

    last_error = None

    for provider in PROVIDERS:

        try:

            response = g4f.ChatCompletion.create(
                model=model,
                provider=provider,
                messages=messages
            )

            return response

        except Exception as e:

            print(f"{provider.__name__}: {e}")

            last_error = e

    raise Exception(str(last_error))

# =====================================
# STREAM
# =====================================

async def stream_generate(model, messages):

    loop = asyncio.get_event_loop()

    for provider in PROVIDERS:

        try:

            response = await loop.run_in_executor(
                executor,
                lambda: g4f.ChatCompletion.create(
                    model=model,
                    provider=provider,
                    messages=messages,
                    stream=True
                )
            )

            for chunk in response:

                if chunk:

                    payload = {
                        "choices": [
                            {
                                "delta": {
                                    "content": chunk
                                }
                            }
                        ]
                    }

                    yield f"data: {json.dumps(payload)}\\n\\n"

            yield "data: [DONE]\\n\\n"

            return

        except Exception as e:

            print(f"Streaming Error: {e}")

            continue

    yield f"data: {json.dumps({'error':'All providers failed'})}\\n\\n"

# =====================================
# API
# =====================================

@app.get("/")
async def home():

    return {
        "status": "online"
    }

@app.post("/v1/chat/completions")
async def chat(
    req: ChatRequest,
    authorization: str = Header(None)
):

    if not authorization:
        raise HTTPException(
            status_code=401,
            detail="Missing Authorization"
        )

    verify_api_key(authorization)

    messages = [
        m.model_dump()
        for m in req.messages
    ]

    # =================================
    # STREAM
    # =================================

    if req.stream:

        return StreamingResponse(
            stream_generate(
                req.model,
                messages
            ),
            media_type="text/event-stream"
        )

    # =================================
    # NORMAL
    # =================================

    loop = asyncio.get_event_loop()

    try:

        response = await loop.run_in_executor(
            executor,
            lambda: generate(
                req.model,
                messages
            )
        )

        return {
            "choices": [
                {
                    "message": {
                        "role": "assistant",
                        "content": response
                    }
                }
            ]
        }

    except Exception as e:

        raise HTTPException(
            status_code=500,
            detail=str(e)
        )