added new model for embeddings

app.py

@@ -15,7 +15,7 @@ splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
 chunks = splitter.split_documents(docs)
 
 # Local embedding model (Tamil capable)
-embedding_model = HuggingFaceEmbeddings(model_name="intfloat/multilingual-e5-large")
+embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
 
 # Store in Chroma
 vectorstore = Chroma.from_documents(chunks, embedding=embedding_model)