feat: metadata service

.env

@@ -0,0 +1,6 @@
+# PROJECT INFORMATION
+HOST=0.0.0.0
+PORT=7860
+CORS_HEADERS=["*"]
+CORS_ORIGINS=["*"]
+POLICY_FILE_PATH="./policy.json"

Dockerfile

@@ -0,0 +1,33 @@
+FROM python:3.8-slim
+
+RUN apt-get update && \
+    apt-get install git bash wget iputils-ping -y && \
+    apt clean && \
+    rm -rf /var/cache/apt/*
+
+WORKDIR /code
+
+COPY requirements.txt /code/requirements.txt
+
+# PYTHONDONTWRITEBYTECODE=1: Disables the creation of .pyc files (compiled bytecode)
+# PYTHONUNBUFFERED=1: Disables buffering of the standard output stream
+# PYTHONIOENCODING: specifies the encoding to be used for the standard input, output, and error streams
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PYTHONIOENCODING=utf-8
+
+RUN pip install -U pip && \
+    python -m pip install -r /code/requirements.txt
+
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+CMD python ./src/main.py

policy.json

@@ -0,0 +1,13 @@
+{
+  "type": "service_account",
+  "project_id": "vinid-playground",
+  "private_key_id": "5546404edff790939b5175043e6b50edd10332ab",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\nXgoIt1blT7sM2raf6+Gl+SdM\n-----END PRIVATE KEY-----\n",
+  "client_email": "[email protected]",
+  "client_id": "103848892899493800751",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/iac-demo%40vinid-playground.iam.gserviceaccount.com",
+  "universe_domain": "googleapis.com"
+}

requirements.txt

@@ -0,0 +1,6 @@
+fastapi==0.103.1
+uvicorn==0.23.2
+pydantic-settings==2.0.3
+firebase_admin
+# Project settings, for development only
+# pre-commit

src/config.py

@@ -0,0 +1,21 @@
+from pathlib import Path
+
+from pydantic_settings import BaseSettings
+
+FILE = Path(__file__)
+ROOT = FILE.parent.parent
+
+
+class Settings(BaseSettings):
+    # API SETTINGS
+    HOST: str
+    PORT: int
+    CORS_ORIGINS: list
+    CORS_HEADERS: list
+    POLICY_FILE_PATH: str
+
+    class Config:
+        env_file = ROOT / ".env"
+
+
+settings = Settings()

src/itr/router.py

@@ -0,0 +1,115 @@
+from fastapi import APIRouter, status, Response, Path
+from fastapi.responses import JSONResponse, StreamingResponse
+from pydantic import BaseModel
+
+# from google.cloud import storage
+from config import settings
+import datetime
+import firebase_admin
+from firebase_admin import credentials
+from firebase_admin import storage
+
+from google.cloud import storage
+from pathlib import Path
+
+import numpy as np
+import csv
+import json
+import os
+
+# cred = credentials.Certificate(settings.POLICY_FILE_PATH)
+# app = firebase_admin.initialize_app(cred, {'storageBucket': 'cnc-designs.appspot.com'}, name='storage')
+# bucket = storage.bucket(app=app)
+
+CWD = Path(__file__).parent
+
+# client = storage.Client()
+client = storage.Client.from_service_account_json(
+    os.path.join(CWD.parent.parent, settings.POLICY_FILE_PATH)
+)
+bucket = client.bucket("thangtd1")
+
+router = APIRouter()
+
+
+@router.get("/{video}/metadata")
+async def get_length(video: str) -> JSONResponse:
+    print(video)
+    try:
+        path_file = "metadata/" + video + ".json"
+        blob = bucket.blob(path_file)
+
+        metadata = {}
+
+        with blob.open("r") as f:
+            metadata = json.load(f)
+
+    except Exception:
+        return JSONResponse(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            content={"message": "err"},
+        )
+
+    return JSONResponse(status_code=status.HTTP_200_OK, content=metadata)
+
+
+@router.get("/{video}/keyframes/list")
+async def get_list_keyframes(video: str) -> JSONResponse:
+    path_file = "Keyframes/" + video
+    list_keyframes = []
+    meta_data = []
+
+    path_meta_file = "map-keyframes/" + video + ".csv"
+
+    blob = bucket.blob(path_meta_file)
+    with blob.open("r") as f:
+        reader = csv.reader(f)
+        meta_data = list(reader)
+        # print(meta_data[0])
+        meta_data = np.array(meta_data[1:])
+
+    for blob in client.list_blobs("thangtd1", prefix=path_file):
+        list_keyframes.append([str(blob.name)])
+
+    list_keyframes = np.array(list_keyframes)
+
+    list_keyframes = np.append(list_keyframes, meta_data, axis=1)
+
+    return JSONResponse(
+        status_code=status.HTTP_200_OK,
+        content={"list_keyframes": list_keyframes.tolist()},
+    )
+
+
+@router.get("/stream_video/{bucket_name}/{video_blob_name}")
+async def stream_video(
+    bucket_name: str,
+    video_blob_name: str,
+    response: Response = None,
+) -> JSONResponse:
+    path_file = "Video/" + video_blob_name
+
+    # blob = bucket.blob(path_file)
+
+    # url = blob.generate_signed_url(
+    # This URL is valid for 15 minutes
+    #  expiration=datetime.timedelta(minutes=15),
+    # Allow GET requests using this URL.
+    #  method='GET'
+    # )
+
+    # print(url)
+
+    # return JSONResponse(status_code=status.HTTP_200_OK, content = {"url" : url})
+
+    # if not blob.exists():
+    #     return StreamingResponse(
+    #         content_generator([b"Video not found"]), media_type="text/plain"
+    #     )
+
+    # # Stream the video in chunks
+    # def content_generator():
+    #     for chunk in blob.download_as_bytes(start=0, end=blob.size, raw_download=True):
+    #         yield chunk
+
+    # return StreamingResponse(content_generator(), media_type="video/mp4")

src/itr/router/README.md

@@ -0,0 +1,6 @@
+# BEiT-3 Weight and Sentencepiece models
+
+1. Please download [beit3_base_patch16_384_retrieval.pth](https://conversationhub.blob.core.windows.net/beit-share-public/beit3/f30k_retrieval/beit3_base_patch16_384_f30k_retrieval.pth?sv=2021-10-04&st=2023-06-08T11%3A16%3A02Z&se=2033-06-09T11%3A16%3A00Z&sr=c&sp=r&sig=N4pfCVmSeq4L4tS8QbrFVsX6f6q844eft8xSuXdxU48%3D) and [beit3.spm](https://conversationhub.blob.core.windows.net/beit-share-public/beit3/sentencepiece/beit3.spm?sv=2021-10-04&st=2023-06-08T11%3A16%3A02Z&se=2033-06-09T11%3A16%3A00Z&sr=c&sp=r&sig=N4pfCVmSeq4L4tS8QbrFVsX6f6q844eft8xSuXdxU48%3D) model.
+
+2. Put those 2 model inside this folder
+

src/main.py

@@ -0,0 +1,63 @@
+import os
+from pathlib import Path
+
+from config import settings
+from fastapi import FastAPI, Request, status
+from fastapi.exceptions import RequestValidationError
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse, RedirectResponse
+from itr.router import router as router
+
+import os
+
+os.environ["KMP_DUPLICATE_LIB_OK"] = "True"
+
+
+app = FastAPI(title="Metadata API")
+
+SERVICE_ROOT = Path(__file__).parent.parent
+
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_headers=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+)
+
+
+@app.exception_handler(RequestValidationError)
+async def validation_exception_handler(request: Request, exc: RequestValidationError):
+    # Get the original 'detail' list of errors
+    details = exc.errors()
+    error_details = []
+
+    for error in details:
+        error_details.append({"error": f"{error['msg']} {str(error['loc'])}"})
+    return JSONResponse(content={"message": error_details})
+
+
+@app.on_event("startup")
+async def startup_event():
+    pass
+
+
+@app.get("/", include_in_schema=False)
+async def root() -> None:
+    return RedirectResponse("/docs")
+
+
+@app.get("/health", status_code=status.HTTP_200_OK, tags=["health"])
+async def perform_healthcheck() -> None:
+    return JSONResponse(content={"message": "success"})
+
+
+app.include_router(router)
+
+
+# Start API
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run("main:app", host=settings.HOST, port=settings.PORT, reload=True)