make it work

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.index filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

README.md

@@ -1,10 +1,11 @@
 ---
 title: Xbgp
-emoji: 🌍
+emoji: 🎮
 colorFrom: gray
-colorTo: red
+colorTo: green
 sdk: gradio
 sdk_version: 4.4.1
+python_version: 3.11
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,98 @@
+import gradio as gr
+import os
+from transformers import AutoImageProcessor, AutoModel
+import torch
+from pymongo import MongoClient
+from PIL import Image
+import json
+import numpy as np
+import faiss
+from dotenv import load_dotenv
+
+load_dotenv()
+
+
+# Init similarity search AI model and processor
+torch_device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+dino_v2_model = AutoModel.from_pretrained("facebook/dinov2-base").to(torch_device)
+dino_v2_image_processor = AutoImageProcessor.from_pretrained("facebook/dinov2-base")
+
+# MongoDB
+MONGO_URI = os.environ.get("MONGO_URI")
+mongo = MongoClient(MONGO_URI)
+db = mongo["xbgp"]
+
+
+def process_image(image):
+    """
+    Process the image and extract features using the DINOv2 model.
+    """
+    # Add your image processing code here.
+    # This will include preprocessing the image, passing it through the model,
+    # and then formatting the output (extracted features).
+
+    # Load the index
+    with open("images.json", "r") as f:
+        images = json.load(f)
+
+    # Convert to RGB if it isn't already
+    if image.mode != "RGB":
+        image = image.convert("RGB")
+
+    # Resize to 64px while maintaining aspect ratio
+    width, height = image.size
+    if width < height:
+        w_percent = 64 / float(width)
+        new_width = 64
+        new_height = int(float(height) * float(w_percent))
+    else:
+        h_percent = 64 / float(height)
+        new_height = 64
+        new_width = int(float(width) * float(h_percent))
+    image = image.resize((new_width, new_height), Image.LANCZOS)
+
+    # Extract the features from the uploaded image
+    with torch.no_grad():
+        inputs = dino_v2_image_processor(images=image, return_tensors="pt").to(
+            torch_device
+        )
+        outputs = dino_v2_model(**inputs)
+
+    # Normalize the features before search, whatever that means
+    embeddings = outputs.last_hidden_state
+    embeddings = embeddings.mean(dim=1)
+    vector = embeddings.detach().cpu().numpy()
+    vector = np.float32(vector)
+    faiss.normalize_L2(vector)
+
+    # Read the index file and perform search of top 50 images
+    index = faiss.read_index("vector.index")
+    distances, indices = index.search(vector, 50)
+    matches = []
+    for idx, matching_gamerpic in enumerate(indices[0]):
+        gamerpic = images[matching_gamerpic]
+        print(gamerpic)
+        # Return the corresponding title with only the matched gamerpic
+        title = db.titles.find_one(
+            {"gamerpics.cdn": gamerpic},
+            {"name": 1, "type": 1, "url": 1, "gamerpics.$": 1},
+        )
+
+        print(title)
+
+        title["rank"] = idx
+        title["score"] = str(round((1 / (distances[0][idx] + 1) * 100), 2)) + "%"
+        matches.append(title)
+
+    return matches
+
+
+# Create a Gradio interface
+iface = gr.Interface(
+    fn=process_image,
+    inputs=gr.Image(type="pil"),  # Adjust the shape as needed
+    outputs="json",  # Or any other output format that suits your needs
+)
+
+# Launch the Gradio app
+iface.launch(share="true")

requirements.txt

@@ -0,0 +1,10 @@
+--extra-index-url https://download.pytorch.org/whl/cpu
+
+torch==2.1.1+cpu
+numpy==1.26.0
+pillow==10.0.1
+transformers==4.34.0
+pymongo[srv]==3.11
+faiss-cpu==1.7.4
+gradio
+python-dotenv

vector.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0902a19181cd3f4abd47ac168e1547522f64d615d566b42846618c5021eeefe
+size 99370029