Upload 20 files

.github/workflows/docker-deploy.yml

@@ -0,0 +1,43 @@
+name: Docker Build and Push
+
+on:
+  push:
+    branches:
+      - main  # Triggers the workflow when changes are pushed to the 'main' branch
+  pull_request:
+    branches:
+      - main  # Optional: Trigger on pull requests to 'main' for testing
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    
+    steps:
+    # Step 1: Check out the repository
+    - name: Checkout code
+      uses: actions/checkout@v3  # Check out your GitHub repository
+
+    # Step 2: Set up Docker Buildx
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v2  # Set up Docker Buildx to support advanced features like multi-platform builds
+      with:
+        install: true
+
+    # Step 3: Log in to Docker Hub
+    - name: Log in to Docker Hub
+      uses: docker/login-action@v2  # Logs in to Docker Hub
+      with:
+        username: ${{ secrets.DOCKER_USERNAME }}  # Your Docker Hub username stored as a GitHub secret
+        password: ${{ secrets.DOCKER_PASSWORD }}  # Your Docker Hub password stored as a GitHub secret
+
+    # Step 4: Build and push the Docker image
+    - name: Build and Push Docker Image
+      uses: docker/build-push-action@v5  # Build and push the Docker image
+      with:
+        context: .  # The context is the root of your repository
+        push: true  # Automatically push the image after building
+        tags: ${{ secrets.DOCKER_USERNAME }}/blackboxv2:v2  # Replace 'your-app-name' with your desired Docker image name
+
+    # Step 5: Log out of Docker Hub
+    - name: Log out of Docker Hub
+      run: docker logout

Dockerfile

@@ -23,4 +23,4 @@ COPY . /app
 EXPOSE 8001
 
 # Command to run the app with Gunicorn and Uvicorn workers
-CMD ["gunicorn", "-k", "uvicorn.workers.UvicornWorker", "--workers", "4", "--bind", "0.0.0.0:8001", "main:app"]
+CMD ["gunicorn", "-k", "uvicorn.workers.UvicornWorker", "--workers", "4", "--bind", "0.0.0.0:8001", "main:app"]

api/app.py

@@ -1,40 +1,40 @@
-from fastapi import FastAPI, Request
-from starlette.middleware.cors import CORSMiddleware
-from fastapi.responses import JSONResponse
-from api.logger import setup_logger
-from api.routes import router
-
-logger = setup_logger(__name__)
-
-def create_app():
-    app = FastAPI(
-        title="Production API",
-        docs_url=None,          # Disable Swagger UI
-        redoc_url=None,         # Disable ReDoc
-        openapi_url=None,       # Disable OpenAPI schema
-    )
-
-    # CORS settings
-    app.add_middleware(
-        CORSMiddleware,
-        allow_origins=["*"],                   # Adjust as needed for security
-        allow_credentials=True,
-        allow_methods=["*"],
-        allow_headers=["*"],
-    )
-
-    # Include routes
-    app.include_router(router)
-
-    # Global exception handler for better error reporting
-    @app.exception_handler(Exception)
-    async def global_exception_handler(request: Request, exc: Exception):
-        logger.error(f"An error occurred: {str(exc)}")
-        return JSONResponse(
-            status_code=500,
-            content={"message": "An internal server error occurred."},
-        )
-
-    return app
-
-app = create_app()
+from fastapi import FastAPI, Request
+from starlette.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse
+from api.logger import setup_logger
+from api.routes import router
+
+logger = setup_logger(__name__)
+
+def create_app():
+    app = FastAPI(
+        title="NiansuhAI API Gateway",
+        docs_url=None,          # Disable Swagger UI
+        redoc_url=None,         # Disable ReDoc
+        openapi_url=None,       # Disable OpenAPI schema
+    )
+
+    # CORS settings
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=["*"],                   # Adjust as needed for security
+        allow_credentials=True,
+        allow_methods=["*"],
+        allow_headers=["*"],
+    )
+
+    # Include routes
+    app.include_router(router)
+
+    # Global exception handler for better error reporting
+    @app.exception_handler(Exception)
+    async def global_exception_handler(request: Request, exc: Exception):
+        logger.error(f"An error occurred: {str(exc)}")
+        return JSONResponse(
+            status_code=500,
+            content={"message": "An internal server error occurred."},
+        )
+
+    return app
+
+app = create_app()

api/auth.py

@@ -1,10 +1,10 @@
-from fastapi import Depends, HTTPException
-from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
-from api.config import APP_SECRET
-
-security = HTTPBearer()
-
-def verify_app_secret(credentials: HTTPAuthorizationCredentials = Depends(security)):
-    if credentials.credentials != APP_SECRET:
-        raise HTTPException(status_code=403, detail="Invalid APP_SECRET")
-    return credentials.credentials
+from fastapi import Depends, HTTPException
+from fastapi.security import HTTPAuthorizationCredentials, HTTPBearer
+from api.config import APP_SECRET
+
+security = HTTPBearer()
+
+def verify_app_secret(credentials: HTTPAuthorizationCredentials = Depends(security)):
+    if credentials.credentials != APP_SECRET:
+        raise HTTPException(status_code=403, detail="Invalid APP_SECRET")
+    return credentials.credentials

api/config.py

@@ -1,115 +1,115 @@
-import os
-from dotenv import load_dotenv
-
-load_dotenv()
-
-BASE_URL = "https://www.blackbox.ai"
-headers = {
-    'accept': '*/*',
-    'accept-language': 'en-US,en;q=0.9',
-    'origin': 'https://www.blackbox.ai',
-    'priority': 'u=1, i',
-    'sec-ch-ua': '"Google Chrome";v="129", "Not=A?Brand";v="8", "Chromium";v="129"',
-    'sec-ch-ua-mobile': '?0',
-    'sec-ch-ua-platform': '"Windows"',
-    'sec-fetch-dest': 'empty',
-    'sec-fetch-mode': 'cors',
-    'sec-fetch-site': 'same-origin',
-    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
-                  'AppleWebKit/537.36 (KHTML, like Gecko) '
-                  'Chrome/129.0.0.0 Safari/537.36',
-}
-APP_SECRET = os.getenv("APP_SECRET")
-
-ALLOWED_MODELS = [
-    {"id": "blackboxai", "name": "blackboxai"},
-    {"id": "blackboxai-pro", "name": "blackboxai-pro"},
-    {"id": "flux", "name": "flux"},  # Changed from "ImageGeneration" to "flux"
-    {"id": "llama-3.1-8b", "name": "llama-3.1-8b"},
-    {"id": "llama-3.1-70b", "name": "llama-3.1-70b"},
-    {"id": "llama-3.1-405b", "name": "llama-3.1-405b"},
-    {"id": "gpt-4o", "name": "gpt-4o"},
-    {"id": "gemini-pro", "name": "gemini-pro"},
-    {"id": "gemini-1.5-flash", "name": "gemini-1.5-flash"},
-    {"id": "claude-sonnet-3.5", "name": "claude-sonnet-3.5"},
-    {"id": "PythonAgent", "name": "PythonAgent"},
-    {"id": "JavaAgent", "name": "JavaAgent"},
-    {"id": "JavaScriptAgent", "name": "JavaScriptAgent"},
-    {"id": "HTMLAgent", "name": "HTMLAgent"},
-    {"id": "GoogleCloudAgent", "name": "GoogleCloudAgent"},
-    {"id": "AndroidDeveloper", "name": "AndroidDeveloper"},
-    {"id": "SwiftDeveloper", "name": "SwiftDeveloper"},
-    {"id": "Next.jsAgent", "name": "Next.jsAgent"},
-    {"id": "MongoDBAgent", "name": "MongoDBAgent"},
-    {"id": "PyTorchAgent", "name": "PyTorchAgent"},
-    {"id": "ReactAgent", "name": "ReactAgent"},
-    {"id": "XcodeAgent", "name": "XcodeAgent"},
-    {"id": "AngularJSAgent", "name": "AngularJSAgent"},
-    {"id": "RepoMap", "name": "RepoMap"},
-    {"id": "gemini-1.5-pro-latest", "name": "gemini-pro"},
-    {"id": "gemini-1.5-pro", "name": "gemini-1.5-pro"},
-    {"id": "claude-3-5-sonnet-20240620", "name": "claude-sonnet-3.5"},
-    {"id": "claude-3-5-sonnet", "name": "claude-sonnet-3.5"},
-]
-
-MODEL_MAPPING = {
-    "blackboxai": "blackboxai",
-    "blackboxai-pro": "blackboxai-pro",
-    "ImageGeneration": "flux",  # Changed mapping for "ImageGeneration" to "flux"
-    "llama-3.1-8b": "llama-3.1-8b",
-    "llama-3.1-70b": "llama-3.1-70b",
-    "llama-3.1-405b": "llama-3.1-405b",
-    "gpt-4o": "gpt-4o",
-    "gemini-pro": "gemini-pro",
-    "gemini-1.5-flash": "gemini-1.5-flash",
-    "claude-sonnet-3.5": "claude-sonnet-3.5",
-    "PythonAgent": "PythonAgent",
-    "JavaAgent": "JavaAgent",
-    "JavaScriptAgent": "JavaScriptAgent",
-    "HTMLAgent": "HTMLAgent",
-    "GoogleCloudAgent": "GoogleCloudAgent",
-    "AndroidDeveloper": "AndroidDeveloper",
-    "SwiftDeveloper": "SwiftDeveloper",
-    "Next.jsAgent": "Next.jsAgent",
-    "MongoDBAgent": "MongoDBAgent",
-    "PyTorchAgent": "PyTorchAgent",
-    "ReactAgent": "ReactAgent",
-    "XcodeAgent": "XcodeAgent",
-    "AngularJSAgent": "AngularJSAgent",
-    "RepoMap": "RepoMap",
-    # Additional mappings
-    "gemini-flash": "gemini-1.5-flash",
-    "claude-3.5-sonnet": "claude-sonnet-3.5",
-    "gemini-1.5-pro-latest": "gemini-pro",
-    "gemini-1.5-pro": "gemini-1.5-pro",
-    "claude-3-5-sonnet-20240620": "claude-sonnet-3.5",
-    "claude-3-5-sonnet": "claude-sonnet-3.5",
-}
-
-# Agent modes
-AGENT_MODE = {
-    'flux': {'mode': True, 'id': "ImageGenerationLV45LJp", 'name': "flux"},  # Renamed to "flux"
-}
-
-TRENDING_AGENT_MODE = {
-    "blackboxai": {},
-    "gemini-1.5-flash": {'mode': True, 'id': 'Gemini'},
-    "llama-3.1-8b": {'mode': True, 'id': "llama-3.1-8b"},
-    'llama-3.1-70b': {'mode': True, 'id': "llama-3.1-70b"},
-    'llama-3.1-405b': {'mode': True, 'id': "llama-3.1-405b"},
-    'blackboxai-pro': {'mode': True, 'id': "BLACKBOXAI-PRO"},
-    'PythonAgent': {'mode': True, 'id': "Python Agent"},
-    'JavaAgent': {'mode': True, 'id': "Java Agent"},
-    'JavaScriptAgent': {'mode': True, 'id': "JavaScript Agent"},
-    'HTMLAgent': {'mode': True, 'id': "HTML Agent"},
-    'GoogleCloudAgent': {'mode': True, 'id': "Google Cloud Agent"},
-    'AndroidDeveloper': {'mode': True, 'id': "Android Developer"},
-    'SwiftDeveloper': {'mode': True, 'id': "Swift Developer"},
-    'Next.jsAgent': {'mode': True, 'id': "Next.js Agent"},
-    'MongoDBAgent': {'mode': True, 'id': "MongoDB Agent"},
-    'PyTorchAgent': {'mode': True, 'id': "PyTorch Agent"},
-    'ReactAgent': {'mode': True, 'id': "React Agent"},
-    'XcodeAgent': {'mode': True, 'id': "Xcode Agent"},
-    'AngularJSAgent': {'mode': True, 'id': "AngularJS Agent"},
-    'RepoMap': {'mode': True, 'id': "repomap"},
-}
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+BASE_URL = "https://www.blackbox.ai"
+headers = {
+    'accept': '*/*',
+    'accept-language': 'en-US,en;q=0.9',
+    'origin': 'https://www.blackbox.ai',
+    'priority': 'u=1, i',
+    'sec-ch-ua': '"Google Chrome";v="129", "Not=A?Brand";v="8", "Chromium";v="129"',
+    'sec-ch-ua-mobile': '?0',
+    'sec-ch-ua-platform': '"Windows"',
+    'sec-fetch-dest': 'empty',
+    'sec-fetch-mode': 'cors',
+    'sec-fetch-site': 'same-origin',
+    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
+                  'AppleWebKit/537.36 (KHTML, like Gecko) '
+                  'Chrome/129.0.0.0 Safari/537.36',
+}
+APP_SECRET = os.getenv("APP_SECRET")
+
+ALLOWED_MODELS = [
+    {"id": "blackboxai", "name": "blackboxai"},
+    {"id": "blackboxai-pro", "name": "blackboxai-pro"},
+    {"id": "flux", "name": "flux"},
+    {"id": "llama-3.1-8b", "name": "llama-3.1-8b"},
+    {"id": "llama-3.1-70b", "name": "llama-3.1-70b"},
+    {"id": "llama-3.1-405b", "name": "llama-3.1-405b"},
+    {"id": "gpt-4o", "name": "gpt-4o"},
+    {"id": "gemini-pro", "name": "gemini-pro"},
+    {"id": "gemini-1.5-flash", "name": "gemini-1.5-flash"},
+    {"id": "claude-sonnet-3.5", "name": "claude-sonnet-3.5"},
+    {"id": "PythonAgent", "name": "PythonAgent"},
+    {"id": "JavaAgent", "name": "JavaAgent"},
+    {"id": "JavaScriptAgent", "name": "JavaScriptAgent"},
+    {"id": "HTMLAgent", "name": "HTMLAgent"},
+    {"id": "GoogleCloudAgent", "name": "GoogleCloudAgent"},
+    {"id": "AndroidDeveloper", "name": "AndroidDeveloper"},
+    {"id": "SwiftDeveloper", "name": "SwiftDeveloper"},
+    {"id": "Next.jsAgent", "name": "Next.jsAgent"},
+    {"id": "MongoDBAgent", "name": "MongoDBAgent"},
+    {"id": "PyTorchAgent", "name": "PyTorchAgent"},
+    {"id": "ReactAgent", "name": "ReactAgent"},
+    {"id": "XcodeAgent", "name": "XcodeAgent"},
+    {"id": "AngularJSAgent", "name": "AngularJSAgent"},
+    {"id": "RepoMap", "name": "RepoMap"},
+    {"id": "gemini-1.5-pro-latest", "name": "gemini-pro"},
+    {"id": "gemini-1.5-pro", "name": "gemini-1.5-pro"},
+    {"id": "claude-3-5-sonnet-20240620", "name": "claude-sonnet-3.5"},
+    {"id": "claude-3-5-sonnet", "name": "claude-sonnet-3.5"},
+]
+
+MODEL_MAPPING = {
+    "blackboxai": "blackboxai",
+    "blackboxai-pro": "blackboxai-pro",
+    "ImageGeneration": "flux",
+    "llama-3.1-8b": "llama-3.1-8b",
+    "llama-3.1-70b": "llama-3.1-70b",
+    "llama-3.1-405b": "llama-3.1-405b",
+    "gpt-4o": "gpt-4o",
+    "gemini-pro": "gemini-pro",
+    "gemini-1.5-flash": "gemini-1.5-flash",
+    "claude-sonnet-3.5": "claude-sonnet-3.5",
+    "PythonAgent": "PythonAgent",
+    "JavaAgent": "JavaAgent",
+    "JavaScriptAgent": "JavaScriptAgent",
+    "HTMLAgent": "HTMLAgent",
+    "GoogleCloudAgent": "GoogleCloudAgent",
+    "AndroidDeveloper": "AndroidDeveloper",
+    "SwiftDeveloper": "SwiftDeveloper",
+    "Next.jsAgent": "Next.jsAgent",
+    "MongoDBAgent": "MongoDBAgent",
+    "PyTorchAgent": "PyTorchAgent",
+    "ReactAgent": "ReactAgent",
+    "XcodeAgent": "XcodeAgent",
+    "AngularJSAgent": "AngularJSAgent",
+    "RepoMap": "RepoMap",
+    # Additional mappings
+    "gemini-flash": "gemini-1.5-flash",
+    "claude-3.5-sonnet": "claude-sonnet-3.5",
+    "gemini-1.5-pro-latest": "gemini-pro",
+    "gemini-1.5-pro": "gemini-1.5-pro",
+    "claude-3-5-sonnet-20240620": "claude-sonnet-3.5",
+    "claude-3-5-sonnet": "claude-sonnet-3.5",
+}
+
+# Agent modes
+AGENT_MODE = {
+    'flux': {'mode': True, 'id': "ImageGenerationLV45LJp", 'name': "flux"},
+}
+
+TRENDING_AGENT_MODE = {
+    "blackboxai": {},
+    "gemini-1.5-flash": {'mode': True, 'id': 'Gemini'},
+    "llama-3.1-8b": {'mode': True, 'id': "llama-3.1-8b"},
+    'llama-3.1-70b': {'mode': True, 'id': "llama-3.1-70b"},
+    'llama-3.1-405b': {'mode': True, 'id': "llama-3.1-405b"},
+    'blackboxai-pro': {'mode': True, 'id': "BLACKBOXAI-PRO"},
+    'PythonAgent': {'mode': True, 'id': "Python Agent"},
+    'JavaAgent': {'mode': True, 'id': "Java Agent"},
+    'JavaScriptAgent': {'mode': True, 'id': "JavaScript Agent"},
+    'HTMLAgent': {'mode': True, 'id': "HTML Agent"},
+    'GoogleCloudAgent': {'mode': True, 'id': "Google Cloud Agent"},
+    'AndroidDeveloper': {'mode': True, 'id': "Android Developer"},
+    'SwiftDeveloper': {'mode': True, 'id': "Swift Developer"},
+    'Next.jsAgent': {'mode': True, 'id': "Next.js Agent"},
+    'MongoDBAgent': {'mode': True, 'id': "MongoDB Agent"},
+    'PyTorchAgent': {'mode': True, 'id': "PyTorch Agent"},
+    'ReactAgent': {'mode': True, 'id': "React Agent"},
+    'XcodeAgent': {'mode': True, 'id': "Xcode Agent"},
+    'AngularJSAgent': {'mode': True, 'id': "AngularJS Agent"},
+    'RepoMap': {'mode': True, 'id': "repomap"},
+}

api/logger.py

@@ -1,20 +1,20 @@
-import logging
-
-def setup_logger(name):
-    logger = logging.getLogger(name)
-    if not logger.handlers:
-        logger.setLevel(logging.INFO)
-        formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
-        
-        # Console handler
-        console_handler = logging.StreamHandler()
-        console_handler.setFormatter(formatter)
-        logger.addHandler(console_handler)
-        
-        # File Handler - Error Level
-        # error_file_handler = logging.FileHandler('error.log')
-        # error_file_handler.setFormatter(formatter)
-        # error_file_handler.setLevel(logging.ERROR)
-        # logger.addHandler(error_file_handler)
-    
-    return logger
+import logging
+
+def setup_logger(name):
+    logger = logging.getLogger(name)
+    if not logger.handlers:
+        logger.setLevel(logging.INFO)
+        formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+        
+        # Console handler
+        console_handler = logging.StreamHandler()
+        console_handler.setFormatter(formatter)
+        logger.addHandler(console_handler)
+        
+        # File Handler - Error Level
+        # error_file_handler = logging.FileHandler('error.log')
+        # error_file_handler.setFormatter(formatter)
+        # error_file_handler.setLevel(logging.ERROR)
+        # logger.addHandler(error_file_handler)
+    
+    return logger

api/models.py

@@ -1,14 +1,14 @@
-from typing import List, Optional
-from pydantic import BaseModel
-
-class Message(BaseModel):
-    role: str
-    content: str | list
-
-class ChatRequest(BaseModel):
-    model: str
-    messages: List[Message]
-    stream: Optional[bool] = False
-    temperature: Optional[float] = 0.7
-    top_p: Optional[float] = 0.9
-    max_tokens: Optional[int] = 8192
+from typing import List, Optional
+from pydantic import BaseModel
+
+class Message(BaseModel):
+    role: str
+    content: str | list
+
+class ChatRequest(BaseModel):
+    model: str
+    messages: List[Message]
+    stream: Optional[bool] = False
+    temperature: Optional[float] = 0.7
+    top_p: Optional[float] = 0.9
+    max_tokens: Optional[int] = 8192

api/routes.py

@@ -1,60 +1,60 @@
-import json
-from fastapi import APIRouter, Depends, HTTPException, Request, Response
-from fastapi.responses import StreamingResponse
-from api.auth import verify_app_secret
-from api.config import ALLOWED_MODELS
-from api.models import ChatRequest
-from api.utils import process_non_streaming_response, process_streaming_response
-from api.logger import setup_logger
-
-logger = setup_logger(__name__)
-
-router = APIRouter()
-
-@router.options("/v1/chat/completions")
-@router.options("/api/v1/chat/completions")
-async def chat_completions_options():
-    return Response(
-        status_code=200,
-        headers={
-            "Access-Control-Allow-Origin": "*",
-            "Access-Control-Allow-Methods": "POST, OPTIONS",
-            "Access-Control-Allow-Headers": "Content-Type, Authorization",
-        },
-    )
-
-@router.get("/v1/models")
-@router.get("/api/v1/models")
-async def list_models():
-    return {"object": "list", "data": ALLOWED_MODELS}
-
-@router.post("/v1/chat/completions")
-@router.post("/api/v1/chat/completions")
-async def chat_completions(
-    request: ChatRequest, app_secret: str = Depends(verify_app_secret)
-):
-    logger.info("Entering chat_completions route")
-    logger.info(f"Processing chat completion request for model: {request.model}")
-
-    if request.model not in [model["id"] for model in ALLOWED_MODELS]:
-        raise HTTPException(
-            status_code=400,
-            detail=f"Model {request.model} is not allowed. Allowed models are: {', '.join(model['id'] for model in ALLOWED_MODELS)}",
-        )
-
-    if request.stream:
-        logger.info("Streaming response")
-        return StreamingResponse(process_streaming_response(request), media_type="text/event-stream")
-    else:
-        logger.info("Non-streaming response")
-        return await process_non_streaming_response(request)
-
-
-@router.route('/')
-@router.route('/healthz')
-@router.route('/ready')
-@router.route('/alive')
-@router.route('/status')
-@router.get("/health")
-def health_check(request: Request):
-    return Response(content=json.dumps({"status": "ok"}), media_type="application/json")
+import json
+from fastapi import APIRouter, Depends, HTTPException, Request, Response
+from fastapi.responses import StreamingResponse
+from api.auth import verify_app_secret
+from api.config import ALLOWED_MODELS
+from api.models import ChatRequest
+from api.utils import process_non_streaming_response, process_streaming_response
+from api.logger import setup_logger
+
+logger = setup_logger(__name__)
+
+router = APIRouter()
+
+@router.options("/v1/chat/completions")
+@router.options("/api/v1/chat/completions")
+async def chat_completions_options():
+    return Response(
+        status_code=200,
+        headers={
+            "Access-Control-Allow-Origin": "*",
+            "Access-Control-Allow-Methods": "POST, OPTIONS",
+            "Access-Control-Allow-Headers": "Content-Type, Authorization",
+        },
+    )
+
+@router.get("/v1/models")
+@router.get("/api/v1/models")
+async def list_models():
+    return {"object": "list", "data": ALLOWED_MODELS}
+
+@router.post("/v1/chat/completions")
+@router.post("/api/v1/chat/completions")
+async def chat_completions(
+    request: ChatRequest, app_secret: str = Depends(verify_app_secret)
+):
+    logger.info("Entering chat_completions route")
+    logger.info(f"Processing chat completion request for model: {request.model}")
+
+    if request.model not in [model["id"] for model in ALLOWED_MODELS]:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Model {request.model} is not allowed. Allowed models are: {', '.join(model['id'] for model in ALLOWED_MODELS)}",
+        )
+
+    if request.stream:
+        logger.info("Streaming response")
+        return StreamingResponse(process_streaming_response(request), media_type="text/event-stream")
+    else:
+        logger.info("Non-streaming response")
+        return await process_non_streaming_response(request)
+
+
+@router.route('/')
+@router.route('/healthz')
+@router.route('/ready')
+@router.route('/alive')
+@router.route('/status')
+@router.get("/health")
+def health_check(request: Request):
+    return Response(content=json.dumps({"status": "ok"}), media_type="application/json")

api/utils.py

@@ -1,160 +1,480 @@
-from datetime import datetime
-import json
-from typing import Any, Dict, Optional
-import uuid
-
-import httpx
-from api.config import MODEL_MAPPING, 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):
-    agent_mode = AGENT_MODE.get(request.model, {})
-    trending_agent_mode = TRENDING_AGENT_MODE.get(request.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_MAPPING.get(request.model, request.model),
-    }
-
-    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, request.model, timestamp))}\n\n"
-
-                yield f"data: {json.dumps(create_chat_completion_data('', request.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):
-    agent_mode = AGENT_MODE.get(request.model, {})
-    trending_agent_mode = TRENDING_AGENT_MODE.get(request.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_MAPPING.get(request.model, request.model),
-    }
-    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:]
-
-    return {
-        "id": f"chatcmpl-{uuid.uuid4()}",
-        "object": "chat.completion",
-        "created": int(datetime.now().timestamp()),
-        "model": request.model,
-        "choices": [
-            {
-                "index": 0,
-                "message": {"role": "assistant", "content": full_response},
-                "finish_reason": "stop",
-            }
-        ],
-        "usage": None,
-    }
+from datetime import datetime
+import json
+from typing import Any, Dict, Optional
+import uuid
+
+import httpx
+from api.config import MODEL_MAPPING, 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):
+    agent_mode = AGENT_MODE.get(request.model, {})
+    trending_agent_mode = TRENDING_AGENT_MODE.get(request.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_MAPPING.get(request.model, request.model),
+    }
+
+    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, request.model, timestamp))}\n\n"
+
+                yield f"data: {json.dumps(create_chat_completion_data('', request.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):
+    agent_mode = AGENT_MODE.get(request.model, {})
+    trending_agent_mode = TRENDING_AGENT_MODE.get(request.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_MAPPING.get(request.model, request.model),
+    }
+    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:]
+
+    return {
+        "id": f"chatcmpl-{uuid.uuid4()}",
+        "object": "chat.completion",
+        "created": int(datetime.now().timestamp()),
+        "model": request.model,
+        "choices": [
+            {
+                "index": 0,
+                "message": {"role": "assistant", "content": full_response},
+                "finish_reason": "stop",
+            }
+        ],
+        "usage": None,
+    }
+from datetime import datetime
+import json
+from typing import Any, Dict, Optional
+import uuid
+
+import httpx
+from api.config import MODEL_MAPPING, 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):
+    agent_mode = AGENT_MODE.get(request.model, {})
+    trending_agent_mode = TRENDING_AGENT_MODE.get(request.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_MAPPING.get(request.model, request.model),
+    }
+
+    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, request.model, timestamp))}\n\n"
+
+                yield f"data: {json.dumps(create_chat_completion_data('', request.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):
+    agent_mode = AGENT_MODE.get(request.model, {})
+    trending_agent_mode = TRENDING_AGENT_MODE.get(request.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_MAPPING.get(request.model, request.model),
+    }
+    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:]
+
+    return {
+        "id": f"chatcmpl-{uuid.uuid4()}",
+        "object": "chat.completion",
+        "created": int(datetime.now().timestamp()),
+        "model": request.model,
+        "choices": [
+            {
+                "index": 0,
+                "message": {"role": "assistant", "content": full_response},
+                "finish_reason": "stop",
+            }
+        ],
+        "usage": None,
+    }
+from datetime import datetime
+import json
+from typing import Any, Dict, Optional
+import uuid
+
+import httpx
+from api.config import MODEL_MAPPING, 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):
+    agent_mode = AGENT_MODE.get(request.model, {})
+    trending_agent_mode = TRENDING_AGENT_MODE.get(request.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_MAPPING.get(request.model, request.model),
+    }
+
+    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, request.model, timestamp))}\n\n"
+
+                yield f"data: {json.dumps(create_chat_completion_data('', request.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):
+    agent_mode = AGENT_MODE.get(request.model, {})
+    trending_agent_mode = TRENDING_AGENT_MODE.get(request.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_MAPPING.get(request.model, request.model),
+    }
+    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:]
+
+    return {
+        "id": f"chatcmpl-{uuid.uuid4()}",
+        "object": "chat.completion",
+        "created": int(datetime.now().timestamp()),
+        "model": request.model,
+        "choices": [
+            {
+                "index": 0,
+                "message": {"role": "assistant", "content": full_response},
+                "finish_reason": "stop",
+            }
+        ],
+        "usage": None,
+    }

main.py

@@ -1,5 +1,5 @@
-import uvicorn
-from api.app import app
-
-if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=8001)
+import uvicorn
+from api.app import app
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=8001)

requirements.txt

@@ -1,6 +1,6 @@
-fastapi==0.95.2
-httpx==0.23.3
-pydantic==1.10.4
-python-dotenv==0.21.0
-uvicorn==0.21.1
-gunicorn==20.1.0
+fastapi==0.95.2
+httpx==0.23.3
+pydantic==1.10.4
+python-dotenv==0.21.0
+uvicorn==0.21.1
+gunicorn==20.1.0