Clean large files and re-commit

.gitignore

@@ -0,0 +1 @@
+chroma_db/

app.py

@@ -1,6 +1,6 @@
 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
@@ -15,7 +15,7 @@ except OSError:
     download("en_core_web_sm")
     nlp = spacy.load("en_core_web_sm")
 
-from src.visual_qa import main_text_retrieve_images
+
 
 def handle_structured_query(question, sort_by=""):
     if not question:
@@ -64,6 +64,8 @@ def handle_image_query(text):
 
     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}")]
 

playground.ipynb

@@ -0,0 +1,23 @@
+{
+ "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

@@ -0,0 +1,10 @@
+import chromadb
+client = chromadb.PersistentClient(path="./chroma_db")  # Change path if needed
+
+# Get a list of existing collection names
+existing_collections = [col.name 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)