Ajout

.env

@@ -0,0 +1,4 @@
+QDRANT_URL=https://006817a4-0b45-4db8-a4e5-1f916808e19b.us-east4-0.gcp.cloud.qdrant.io:6333
+QDRANT_KEY=d9MUWQOMUA7JGBdpoFRtmou-h4Pf-e9uCrr0jMtUfAvvk4osqL_JtA
+AWS_ACCESS_KEY_ID=AKIAWOUASMWP5DM6RZG2
+AWS_SECRET_ACCESS_KEY=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

.gitignore

@@ -0,0 +1,2 @@
+# Ignore le fichier .env
+.env

app.py

@@ -0,0 +1,66 @@
+import os
+import gradio as gr
+from qdrant_client import QdrantClient
+from transformers import ClapModel, ClapProcessor
+from dotenv import load_dotenv
+import requests
+
+# Charger les variables d'environnement à partir du fichier .env
+load_dotenv()
+
+# Récupérer les variables d'environnement
+QDRANT_URL = os.getenv('QDRANT_URL')
+QDRANT_KEY = os.getenv('QDRANT_KEY')
+
+# Vérifier les valeurs récupérées
+print(f"QDRANT_URL: {QDRANT_URL}")
+print(f"QDRANT_KEY: {QDRANT_KEY}")
+
+try:
+    # Tester la connexion à l'URL de Qdrant
+    response = requests.get(QDRANT_URL)
+    print(f"Test de la connexion à Qdrant: {response.status_code}")
+
+    # Vérifier que les variables sont correctement récupérées
+    if not QDRANT_URL or not QDRANT_KEY:
+        raise ValueError("Les variables d'environnement QDRANT_URL ou QDRANT_KEY ne sont pas définies")
+
+    # Connexion au client Qdrant
+    client = QdrantClient(QDRANT_URL, api_key=QDRANT_KEY)
+    print("[INFO] Client created...")
+
+    # Chargement du modèle
+    print("[INFO] Loading the model...")
+    model_name = "laion/larger_clap_general"
+    model = ClapModel.from_pretrained(model_name)
+    processor = ClapProcessor.from_pretrained(model_name)
+
+    # Interface Gradio
+    max_results = 10
+
+    def sound_search(query):
+        text_inputs = processor(text=query, return_tensors="pt")
+        text_embed = model.get_text_features(**text_inputs)[0]
+
+        hits = client.search(
+            collection_name="demo_spaces_db",
+            query_vector=text_embed,
+            limit=max_results,
+        )
+        return [
+            gr.Audio(
+                hit.payload['audio_path'],
+                label=f"style: {hit.payload['style']} -- score: {hit.score}")
+            for hit in hits
+        ]
+
+    with gr.Blocks() as demo:
+        gr.Markdown("# Sound search database")
+        inp = gr.Textbox(placeholder="What sound are you looking for ?")
+        out = [gr.Audio(label=f"{x}") for x in range(max_results)]
+        inp.change(sound_search, inp, out)
+
+    demo.launch()
+
+except Exception as e:
+    print(f"[ERROR] Failed to create Qdrant client: {e}")

requirements.txt

@@ -0,0 +1,170 @@
+aioboto3==12.3.0
+aiobotocore==2.11.2
+aiofiles==23.2.1
+aiohttp==3.9.3
+aioitertools==0.11.0
+aiosignal==1.3.1
+altair==5.3.0
+annotated-types==0.6.0
+antlr4-python3-runtime==4.9.3
+anyio==4.3.0
+appdirs==1.4.4
+async-timeout==4.0.3
+attrs==23.2.0
+audioread==3.0.1
+boto3==1.34.34
+botocore==1.34.34
+braceexpand==0.1.7
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpickle==3.0.0
+contourpy==1.2.1
+cycler==0.12.1
+datasets==2.19.1
+decorator==5.1.1
+demucs==4.0.1
+dill==0.3.8
+diskcache==5.6.3
+docker-pycreds==0.4.0
+dora_search==0.1.12
+einops==0.7.0
+essentia==2.1b6.dev1110
+exceptiongroup==1.2.0
+fastapi==0.110.1
+ffmpy==0.3.2
+filelock==3.13.3
+filetype==1.2.0
+fonttools==4.51.0
+frozenlist==1.4.1
+fsspec==2024.3.1
+ftfy==6.2.0
+gitdb==4.0.11
+GitPython==3.1.43
+gradio==4.26.0
+gradio_client==0.15.1
+grpcio==1.62.1
+grpcio-tools==1.62.1
+h11==0.14.0
+h2==4.1.0
+h5py==3.10.0
+hpack==4.0.0
+httpcore==1.0.5
+httpx==0.27.0
+huggingface-hub==0.22.2
+hyperframe==6.0.1
+idna==3.6
+importlib_resources==6.4.0
+Jinja2==3.1.3
+jmespath==1.0.1
+joblib==1.3.2
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+julius==0.2.7
+kiwisolver==1.4.5
+laion-clap==1.1.4
+lameenc==1.7.0
+lazy_loader==0.4
+librosa==0.10.1
+llvmlite==0.42.0
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.8.4
+mdurl==0.1.2
+miditoolkit==1.0.1
+mido==1.3.2
+mpmath==1.3.0
+msgpack==1.0.8
+multidict==6.0.5
+multiprocess==0.70.16
+networkx==3.3
+numba==0.59.1
+numpy==1.23.5
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.19.3
+nvidia-nvjitlink-cu12==12.4.127
+nvidia-nvtx-cu12==12.1.105
+omegaconf==2.3.0
+openunmix==1.2.1
+orjson==3.10.0
+packaging==23.2
+pandas==2.2.1
+pillow==10.3.0
+platformdirs==4.2.0
+pooch==1.8.1
+portalocker==2.8.2
+progressbar==2.5
+protobuf==4.25.3
+psutil==5.9.8
+pyarrow==16.1.0
+pyarrow-hotfix==0.6
+pycparser==2.22
+pydantic==2.6.4
+pydantic_core==2.16.3
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+qdrant-client==1.8.2
+referencing==0.34.0
+regex==2023.12.25
+requests==2.31.0
+retrying==1.3.4
+rich==13.7.1
+rpds-py==0.18.0
+ruff==0.3.5
+s3transfer==0.10.1
+safetensors==0.4.2
+scikit-learn==1.4.1.post1
+scipy==1.13.0
+semantic-version==2.10.0
+sentry-sdk==1.44.1
+setproctitle==1.3.3
+sf_segmenter==0.0.2
+shellingham==1.5.4
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+soundfile==0.12.1
+soxr==0.3.7
+starlette==0.37.2
+submitit==1.5.1
+sympy==1.12
+threadpoolctl==3.4.0
+tokenizers==0.13.3
+tomlkit==0.12.0
+toolz==0.12.1
+torch==2.2.2
+torchaudio==2.2.2
+torchlibrosa==0.1.0
+torchvision==0.17.2
+tqdm==4.66.2
+transformers==4.30.0
+treetable==0.2.5
+triton==2.2.0
+typer==0.12.2
+typing_extensions==4.11.0
+tzdata==2024.1
+urllib3==2.0.7
+uvicorn==0.29.0
+wandb==0.16.6
+wcwidth==0.2.13
+webdataset==0.2.86
+websockets==11.0.3
+wget==3.2
+wrapt==1.16.0
+xxhash==3.4.1
+yarl==1.9.4

s3_utils.py

@@ -0,0 +1,66 @@
+import hashlib
+from enum import Enum
+
+import boto3
+from botocore.client import BaseClient
+
+
+# S3 HANDLING ######################################################################################
+def get_md5(fpath):
+    with open(fpath, "rb") as f:
+        file_hash = hashlib.md5()
+        while chunk := f.read(8192):
+            file_hash.update(chunk)
+    return file_hash.hexdigest()
+
+
+def upload_file_to_bucket(s3_client, file_obj, bucket, s3key):
+    """Upload a file to an S3 bucket
+    :param file_obj: File to upload
+    :param bucket: Bucket to upload to
+    :param s3key: s3key
+    :param object_name: S3 object name. If not specified then file_name is used
+    :return: True if file was uploaded, else False
+    """
+    # Upload the file
+    return s3_client.upload_fileobj(
+        file_obj, bucket, s3key,
+        ExtraArgs={"ACL": "public-read", "ContentType": "Content-Type: audio/mpeg"}
+    )
+
+
+def s3_auth(aws_access_key_id, aws_secret_access_key, region_name) -> BaseClient:
+    s3 = boto3.client(
+        service_name='s3',
+        aws_access_key_id=aws_access_key_id,
+        aws_secret_access_key=aws_secret_access_key,
+        region_name=region_name
+    )
+    return s3
+
+
+def get_list_of_buckets(s3: BaseClient):
+    response = s3.list_buckets()
+    buckets = {}
+
+    for buckets in response['Buckets']:
+        buckets[response['Name']] = response['Name']
+
+    BucketName = Enum('BucketName', buckets)
+    return BucketName
+
+
+if __name__ == '__main__':
+    import os
+
+    AWS_ACCESS_KEY_ID = os.environ['AWS_ACCESS_KEY_ID']
+    AWS_SECRET_ACCESS_KEY = os.environ['AWS_SECRET_ACCESS_KEY']
+    S3_BUCKET = "synthia-research"
+    S3_FOLDER = "huggingface_spaces_demo"
+    AWS_REGION = "eu-west-3"
+
+    s3 = s3_auth(AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_REGION)
+    print(s3.list_buckets())
+
+    s3key = f'{S3_FOLDER}/015.WAV'
+    #print(upload_file_to_bucket(s3, file_obj, S3_BUCKET, s3key))