intial commit

.gitignore

@@ -0,0 +1,163 @@
+# 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/
+
+
+models

app.py

@@ -0,0 +1,98 @@
+import glob
+import os
+
+import streamlit as st
+from datastore import ChromaStore
+from embeddings import Embedding
+from PIL import Image
+from tqdm import tqdm
+
+from utils import base64_to_image, image_to_base64
+
+##### Image database
+root_dir = os.path.join(os.getcwd(), "data")
+jpg_files = glob.glob(os.path.join(root_dir, "**", "*.jpg"), recursive=True)
+IMAGE_DATABASE = [Image.open(f).resize((224, 224)) for f in jpg_files]
+
+
+def display_image_database():
+    image_database_expander = st.expander(label="Image Database")
+    with image_database_expander:
+        st.image(IMAGE_DATABASE)
+
+
+def display_sample_images():
+    sample_img_path = os.path.join(os.getcwd(), "sample_imgs")
+    sample_images = os.listdir(sample_img_path)
+
+    images = []
+    for i, img in enumerate(sample_images):
+        images.append(Image.open(os.path.join(sample_img_path, img)).resize((224, 224)))
+
+    st.image(images)
+
+
+def main():
+    st.set_page_config(page_icon="🖼️", page_title="image-search-engine", layout="wide")
+    st.markdown(
+        """<h1 style="text-align: center;">🔍️ Image Search Engine</h1>""",
+        unsafe_allow_html=True,
+    )
+    st.markdown(
+        """<h3 style="text-align: center;">Image to Image search using transformer embeddings</h3>""",
+        unsafe_allow_html=True,
+    )
+
+    main_layout = st.columns(2)
+
+    with main_layout[0]:
+        with st.container(border=True, height=550):
+            st.markdown(
+                """<h3 style="text-align: center;">Search</h3>""",
+                unsafe_allow_html=True,
+            )
+            upload_img = st.file_uploader(
+                label="Query Image",
+                accept_multiple_files=False,
+                type=["jpg", "png", "jpeg"],
+            )
+
+            submit = st.button(label="Submit")
+            display_sample_images()
+
+    with main_layout[1]:
+        with st.container(border=True, height=550):
+            st.markdown(
+                """<h3 style="text-align: center;">Results</h3>""",
+                unsafe_allow_html=True,
+            )
+            top_k = st.slider(label="Search top k results", min_value=3, max_value=10)
+            if submit and upload_img:
+                ## encode uplaoded img
+                query_embedding = Embedding.encode_image(Image.open(upload_img))
+                ## query vectorstore
+                vectorstore = ChromaStore(collection_name="image_store")
+                collection = vectorstore.create()
+                # print(collection)
+                # print(vectorstore.collection_info(collection))
+                st.toast("Vectorstore loaded successfully", icon="✅")
+                results = vectorstore.query(
+                    collection,
+                    query_embedding,
+                    top_k=top_k,
+                )
+                ## show results
+
+                res_images = []
+                for res in tqdm(results, desc="Results"):
+                    res_images.append(res[0])
+
+                st.image(res_images)
+            else:
+                st.warning("Please upload an image")
+
+    display_image_database()
+
+
+if __name__ == "__main__":
+    main()