Update app.py

app.py

@@ -1,9 +1,23 @@
-from sentence_transformers import SentenceTransformer
+from huggingface_hub import hf_hub_download
 from chromadb import PersistentClient
+from sentence_transformers import SentenceTransformer
 import gradio as gr
+import os
+
+# Download your chroma.sqlite3 from the Hugging Face dataset
+persist_dir = "chromadb"
+os.makedirs(persist_dir, exist_ok=True)
+db_path = os.path.join(persist_dir, "chroma.sqlite3")
+
+if not os.path.exists(db_path):
+    print("⬇️ Downloading ChromaDB from Hugging Face Dataset...")
+    db_path = hf_hub_download(
+        repo_id="tiffany101/my-chromadb",   # <-- replace with your dataset name
+        filename="chroma.sqlite3"
+    )
 
-# Load ChromaDB
-client = PersistentClient(path="chromadb")
+# Load the ChromaDB
+client = PersistentClient(path=persist_dir)
 collection = client.get_collection("my_collection")
 
 # Load embedding model
@@ -15,13 +29,13 @@ def semantic_search(query):
     results = collection.query(query_embeddings=query_embedding.tolist(), n_results=3)
     return "\n\n".join(results["documents"][0])
 
-# Launch Gradio interface
+# Launch Gradio app
 demo = gr.Interface(
     fn=semantic_search,
     inputs=gr.Textbox(label="Enter your search query"),
     outputs=gr.Textbox(label="Top Matches"),
     title="Semantic Search Engine",
-    description="Search over your custom dataset using semantic similarity."
+    description="Search over your dataset using semantic similarity."
 )
 
 if __name__ == "__main__":