reorganizing

.gitignore

@@ -1 +1,5 @@
 chroma_db/
+.gradio/
+src/
+src1/
+old_app_code/

README.md

@@ -1,6 +1,6 @@
 ---
-title: Ask FashionDB
-emoji: 🐠
+title: High Fashion Explorer
+emoji: 🧵
 colorFrom: red
 colorTo: pink
 sdk: gradio

app_old.py

@@ -1,118 +0,0 @@
-import gradio as gr
-#example just for fun 
-from src.visual_qa import main_text_retrieve_images
-from src.generate_queries_alternative import main_generate_queries
-import time
-import pandas as pd
-
-import spacy
-
-# Try to load the model, and download it if missing
-try:
-    nlp = spacy.load("en_core_web_sm")
-except OSError:
-    from spacy.cli import download
-    download("en_core_web_sm")
-    nlp = spacy.load("en_core_web_sm")
-
-
-
-def handle_structured_query(question, sort_by=""):
-    if not question:
-        return "Please ask something 🙂", pd.DataFrame(), []
-
-    try:
-        start = time.time()
-        result_query, sparql_query = main_generate_queries(question)
-        elapsed = round(time.time() - start, 2)
-    except Exception as e:
-        return f"⚠️ Query failed: {e}", pd.DataFrame(), []
-
-    if isinstance(result_query, str):
-        return result_query, pd.DataFrame(), []
-
-    if not result_query:
-        return f"No results for '{question}'. Try rephrasing. (⏱ {elapsed}s)", pd.DataFrame(), []
-
-    df = pd.DataFrame(result_query)
-    if sort_by and sort_by in df.columns:
-        df = df.sort_values(by=sort_by)
-
-
-    if "image_url" in df.columns:
-        columns_of_interest = ["image_url", "year","fashion_collectionLabel", "reference_URL"]
-        df = df[columns_of_interest]
-        # Create a gallery: each item is (image_url, metadata string)
-        gallery_items = []
-        for _, row in df.iterrows():
-            image_url = row.get("image_url")
-            if not image_url:
-                continue
-            # Caption from other fields
-            caption = " | ".join(f"{k}: {v}" for k, v in row.items() if k != "image_url" and pd.notnull(v))
-            gallery_items.append((image_url, caption))
-        return f"Query returned {len(gallery_items)} image(s) in {elapsed} seconds.", pd.DataFrame(), gallery_items
-
-    return f"Query returned a table with {len(df)} row(s) in {elapsed} seconds.", df, []
-
-
-
-
-def handle_image_query(text):
-    if not text:
-        return []
-
-    try:
-        records = main_text_retrieve_images(text)
-        print(f"Retrieved {len(records)} records for query: {text}")
-        print(records)
-    except Exception as e:
-        return [("https://via.placeholder.com/300x200?text=Error", f"Error: {e}")]
-
-    gallery_items = []
-    for item in records:
-        image_url = item.get("image_url")
-        if not image_url:
-            continue
-        # Build a simple caption from the remaining fields
-        caption = " | ".join(f"{k}: {v}" for k, v in item.items() if k != "image_url")
-        gallery_items.append((image_url, caption))
-
-    return gallery_items
-
-# --- UI --- #
-with gr.Blocks() as demo:
-    gr.Markdown("# 🧵 FashionDB Interface")
-
-
-    with gr.Tab("Structured Query"):
-        gr.Markdown("Ask FashionDB anything and view results with images + metadata.")
-
-        with gr.Row():
-            query_input = gr.Textbox(label="Your question")
-            sort_input = gr.Textbox(label="Sort by (optional column name)", placeholder="e.g. year")
-
-        query_submit = gr.Button("Submit")
-
-        query_text_output = gr.Textbox(label="Message", interactive=False)
-        query_table_output = gr.Dataframe(label="Tabular Result", interactive=False)
-        query_gallery_output = gr.Gallery(label="Image Gallery")
-        query_submit.click(
-            fn=handle_structured_query,
-            inputs=[query_input, sort_input],
-            outputs=[
-                query_text_output,
-                query_table_output,
-                query_gallery_output
-            ]
-        )
-
-    with gr.Tab("Image Retrieval"):
-        gr.Markdown("Search for similar fashion show images based on a text description.")
-        image_text = gr.Textbox(label="Describe the kind of images you're looking for")
-        image_submit = gr.Button("Find Images")
-        image_gallery = gr.Gallery(label="Retrieved Images")
-
-        image_submit.click(handle_image_query, inputs=image_text, outputs=image_gallery)
-
-demo.launch()

app_onetab.py

@@ -1,223 +0,0 @@
-import gradio as gr
-import pandas as pd
-import numpy as np
-from search import search_images_by_text, get_similar_images, search_images_by_image
-import requests
-from io import BytesIO
-
-def create_collection_url(row):
-    base_url = "https://www.vogue.com/fashion-shows/"
-    season = str(row["season"]).lower()
-    year = str(row["year"])
-    category = str(row["category"]).lower() if pd.notna(row["category"]) and row["category"] and str(row["category"]).lower() != "nan" else None
-    designer = str(row["designer"]).lower().replace(" ", "-")
-    
-    # Add city if available
-    city = str(row["city"]).lower().replace(" ", "-") if pd.notna(row["city"]) and row["city"] and str(row["city"]).lower() != "nan" else None
-    
-    if pd.isna(category) or category is None or category == "nan":
-        if city:
-            return f"{base_url}{city}-{season}-{year}/{designer}"
-        else:
-            return f"{base_url}{season}-{year}/{designer}"
-    else:
-        if city:
-            return f"{base_url}{city}-{season}-{year}-{category}/{designer}"
-        else:
-            return f"{base_url}{season}-{year}-{category}/{designer}"
-
-import requests
-from io import BytesIO
-#@st.cache_data(show_spinner="Loading FashionDB...")
-def load_data_hf():
-    # Load the Parquet file directly from Hugging Face
-    df_url = "https://huggingface.co/datasets/traopia/vogue_runway_small/resolve/main/VogueRunway.parquet"
-    df = pd.read_parquet(df_url)
-
-    # Load the .npy file using requests
-    npy_url = "https://huggingface.co/datasets/traopia/vogue_runway_small/resolve/main/VogueRunway_image.npy"
-    response = requests.get(npy_url)
-    response.raise_for_status()  # Raise error if download fails
-    embeddings = np.load(BytesIO(response.content))
-    df['collection'] = df.apply(create_collection_url, axis=1)
-    return df, embeddings
-
-
-# from huggingface_hub import hf_hub_download
-# def load_data1():
-# # Login using e.g. `huggingface-cli login` to access this dataset
-#     path = hf_hub_download(
-#         repo_id="traopia/fashion_show_data_all_embeddings",
-#         filename="fashion_show_data_all_embeddings.json"
-#     )
-#     df = pd.read_json(path, lines = True)
-
-#     #df = pd.read_json("hf://datasets/traopia/fashion_show_data_all_embeddings.json/fashion_show_data_all_embeddings.json", lines=True)
-#     df["fashion_clip_image"] = df["fashion_clip_image"].apply(lambda x: x[0] if isinstance(x, list) else x)
-#     df["image_urls"] = df["image_urls"].apply(lambda x: x[0] if x is not None else None)
-#     df = df.rename(columns={"fashion_house":"designer", "image_urls":"url", "URL":"collection"})
-    
-#     df = df.dropna(subset="fashion_clip_image")
-#     df = df.reset_index(drop=True)
-#     df["key"] = df.index
-#     embeddings = np.vstack(df["fashion_clip_image"].values)
-    
-#     return df, embeddings
-
-df, embeddings = load_data_hf()
-
-# Filter and search
-def filter_and_search(fashion_house, category, season, start_year, end_year, query):
-    filtered = df.copy()
-
-    if fashion_house:
-        filtered = filtered[filtered['designer'].isin(fashion_house)]
-    if category:
-        filtered = filtered[filtered['category'].isin(category)]
-    if season:
-        filtered = filtered[filtered['season'].isin(season)]
-    filtered = filtered[(filtered['year'] >= start_year) & (filtered['year'] <= end_year)]
-
-    if query:
-        results = search_images_by_text(query, filtered, embeddings)
-    else:
-        results = filtered.head(30)
-    
-    image_urls = results["url"].tolist()
-    metadata = results.to_dict(orient="records")
-    return image_urls, metadata
-
-# Display metadata and similar
-def show_metadata(idx, metadata):
-    item = metadata[idx]
-    out = ""
-    for field in ["designer", "season", "year", "category"]:
-        if field in item and pd.notna(item[field]):
-            out += f"**{field.title()}**: {item[field]}\n"
-    if 'collection' in item and pd.notna(item['collection']):
-        out += f"\n[View Collection]({item['collection']})"
-    return out
-
-def find_similar(idx, metadata):
-    if not isinstance(idx, int) or idx >= len(metadata) or idx < 0:
-        return []  # or gr.update(visible=False)
-    key = metadata[idx]["key"]
-    similar_df = get_similar_images(df, key, embeddings, top_k=5)
-    return similar_df["url"].tolist(), similar_df.to_dict(orient="records")
-
-
-
-# Gradio UI
-with gr.Blocks() as demo:
-    gr.Markdown("# 👗 FashionDB Explorer")
-
-    with gr.Row():
-        fashion_house = gr.Dropdown(label="Fashion House", choices=sorted(df["designer"].dropna().unique()), multiselect=True)
-        category = gr.Dropdown(label="Category", choices=sorted(df["category"].dropna().unique()), multiselect=True)
-        season = gr.Dropdown(label="Season", choices=sorted(df["season"].dropna().unique()), multiselect=True)
-
-        
-        min_year = int(df['year'].min())
-        max_year = int(df['year'].max())
-
-        start_year = gr.Slider(label="Start Year", minimum=min_year, maximum=max_year, value=2000, step=1)
-        end_year = gr.Slider(label="End Year", minimum=min_year, maximum=max_year, value=2024, step=1)
-
-    query = gr.Textbox(label="Search by text", placeholder="(optional): e.g., pink dress ")
-    search_button = gr.Button("Search by text")
-
-    uploaded_image = gr.Image(label="Upload an image", type="pil")  # or type="pil" if you prefer PIL Image object
-    search_by_image_button = gr.Button("Search by Image")
-
-    def handle_search_by_image(uploaded_image):
-        if uploaded_image is None:
-            return [], "Please upload an image first."
-        results_df = search_images_by_image(uploaded_image, df, embeddings)
-        # Convert results DataFrame to image URLs (or paths) for gallery display
-        images = results_df['url'].tolist()
-        metadata = results_df.to_dict(orient='records')
-        return images, metadata, ""
-
-    uploaded_metadata_state = gr.State([])
-    uploaded_metadata_output = gr.Markdown()
-    uploaded_result_gallery = gr.Gallery(label="Search Results by Image", columns=5, height="auto")
-
-    search_by_image_button.click(
-        fn=handle_search_by_image,
-        inputs=[uploaded_image],
-        outputs=[uploaded_result_gallery, uploaded_metadata_state, uploaded_metadata_output]
-    )
-    
-    result_gallery = gr.Gallery(label="Search Results", columns=5, height="auto")
-    metadata_output = gr.Markdown()
-    reference_image = gr.Image(label="Reference Image", interactive=False)
-    similar_gallery = gr.Gallery(label="Similar Images", columns = 5, height="auto")
-
-    metadata_state = gr.State([])
-    selected_idx = gr.Number(value=0, visible=False)
-
-    def handle_search(*args):
-        imgs, meta = filter_and_search(*args)
-        return imgs, meta, "", []
-
-    search_button.click(
-        handle_search,
-        inputs=[fashion_house, category, season, start_year, end_year, query],
-        outputs=[result_gallery, metadata_state, metadata_output, similar_gallery]
-    )
-
-
-    def handle_click(evt: gr.SelectData, metadata):
-        idx = evt.index
-        md = show_metadata(idx, metadata)
-        img_path = metadata[idx]["url"]
-        return idx, md, img_path
-
-
-
-    result_gallery.select(
-        handle_click,
-        inputs=[metadata_state],
-        outputs=[selected_idx, metadata_output, reference_image]
-    )
-
-    def show_similar(idx, metadata):
-        if idx is None or not str(idx).isdigit():
-            return [],[]  # safe fallback
-        return find_similar(int(idx), metadata)
-
-    similar_metadata_state = gr.State()
-    similar_metadata_output = gr.Markdown()
-    
-    show_similar_button = gr.Button("Show Similar Images")
-    show_similar_button.click(
-        show_similar,
-        inputs=[selected_idx, metadata_state],
-        outputs=[similar_gallery, similar_metadata_state]
-    )
-
-
-    def handle_similar_click(evt: gr.SelectData, metadata):
-        idx = evt.index
-        md = show_metadata(idx, metadata)
-        img_path = metadata[idx]["url"]
-        return idx, md, img_path
-    
-
-    similar_gallery.select(
-    handle_similar_click,
-    inputs=[similar_metadata_state],
-    outputs=[selected_idx, similar_metadata_output, reference_image]
-    )
-
-    back_button = gr.Button("Back to Home")
-
-    def back_to_home():
-        return [], "", None  # clear similar_gallery, metadata_output, reference image
-
-    back_button.click(
-        back_to_home,
-        outputs=[similar_gallery, similar_metadata_output, reference_image]
-    )
-
-demo.launch()

gradio_app1.py

@@ -1,110 +0,0 @@
-import gradio as gr
-
-# --- Handlers --- #
-from src1.generate_queries_alternative import main_generate_queries
-import time
-import pandas as pd
-
-
-
-
-def handle_structured_query(question, sort_by=""):
-    if not question:
-        return "Please ask something 🙂", pd.DataFrame(), []
-
-    try:
-        start = time.time()
-        result_query, sparql_query = main_generate_queries(question)
-        elapsed = round(time.time() - start, 2)
-    except Exception as e:
-        return f"⚠️ Query failed: {e}", pd.DataFrame(), []
-
-    if isinstance(result_query, str):
-        return result_query, pd.DataFrame(), []
-
-    if not result_query:
-        return f"No results for '{question}'. Try rephrasing. (⏱ {elapsed}s)", pd.DataFrame(), []
-
-    df = pd.DataFrame(result_query)
-    if sort_by and sort_by in df.columns:
-        df = df.sort_values(by=sort_by)
-
-
-    if "image_url" in df.columns:
-        columns_of_interest = ["image_url", "year","fashion_collectionLabel", "reference_URL"]
-        df = df[columns_of_interest]
-        # Create a gallery: each item is (image_url, metadata string)
-        gallery_items = []
-        for _, row in df.iterrows():
-            image_url = row.get("image_url")
-            if not image_url:
-                continue
-            # Caption from other fields
-            caption = " | ".join(f"{k}: {v}" for k, v in row.items() if k != "image_url" and pd.notnull(v))
-            gallery_items.append((image_url, caption))
-        return f"Query returned {len(gallery_items)} image(s) in {elapsed} seconds.", pd.DataFrame(), gallery_items
-
-    return f"Query returned a table with {len(df)} row(s) in {elapsed} seconds.", df, []
-
-
-
-
-
-from src1.visual_qa import main_text_retrieve_images
-
-def handle_image_query(text):
-    if not text:
-        return []
-
-    try:
-        records = main_text_retrieve_images(text)
-    except Exception as e:
-        return [("https://via.placeholder.com/300x200?text=Error", f"Error: {e}")]
-
-    gallery_items = []
-    for item in records:
-        image_url = item.get("image_url")
-        if not image_url:
-            continue
-        # Build a simple caption from the remaining fields
-        caption = " | ".join(f"{k}: {v}" for k, v in item.items() if k != "image_url")
-        gallery_items.append((image_url, caption))
-
-    return gallery_items
-
-# --- UI --- #
-with gr.Blocks() as demo:
-    gr.Markdown("# 🧵 FashionDB Interface")
-
-
-    with gr.Tab("Structured Query"):
-        gr.Markdown("Ask FashionDB anything and view results with images + metadata.")
-
-        with gr.Row():
-            query_input = gr.Textbox(label="Your question")
-            sort_input = gr.Textbox(label="Sort by (optional column name)", placeholder="e.g. start_year")
-
-        query_submit = gr.Button("Submit")
-
-        query_text_output = gr.Textbox(label="Message", interactive=False)
-        query_table_output = gr.Dataframe(label="Tabular Result", interactive=False)
-        query_gallery_output = gr.Gallery(label="Image Gallery")
-        query_submit.click(
-            fn=handle_structured_query,
-            inputs=[query_input, sort_input],
-            outputs=[
-                query_text_output,
-                query_table_output,
-                query_gallery_output
-            ]
-        )
-
-    with gr.Tab("Image Retrieval"):
-        gr.Markdown("Search for similar fashion show images based on a text description.")
-        image_text = gr.Textbox(label="Describe the kind of images you're looking for")
-        image_submit = gr.Button("Find Images")
-        image_gallery = gr.Gallery(label="Retrieved Images")
-
-        image_submit.click(handle_image_query, inputs=image_text, outputs=image_gallery)
-
-demo.launch( share=True)

playground.ipynb

@@ -1,23 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "883693d5",
-   "metadata": {
-    "vscode": {
-     "languageId": "plaintext"
-    }
-   },
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

playground.py

@@ -1,23 +0,0 @@
-import chromadb
-client = chromadb.PersistentClient(path="./chroma_db")  # Change path if needed
-
-# Get a list of existing collection names
-existing_collections = [col for col in client.list_collections()]
-collection_name = "clip_image_embeddings"
-if collection_name in existing_collections:
-    collection = client.get_collection(name=collection_name)
-    print(f"Using existing collection: {collection_name}")
-print(existing_collections)
-
-# Show up to 3 items
-results = collection.get(limit=3)
-
-for i in range(len(results["ids"])):
-    print(f"\nItem {i + 1}:")
-    print(f"ID: {results['ids'][i]}")
-    print(f"Document: {results['documents'][i]}")
-    print(f"Metadata: {results['metadatas'][i]}")
-
-print("Number of items:", len(collection.get()["ids"]))
-
-collection_data = collection.get()