build_index.py

import os
from llama_index.core import SimpleDirectoryReader, VectorStoreIndex, StorageContext, Settings
from llama_index.embeddings.fastembed import FastEmbedEmbedding



# ----- 1) Load Data -----

files_to_index = [
    "./Lebenslauf_SuhasKamuni.pdf",
    "./about_me.txt",
    "./more_about_me.txt"
]

try:
    documents = SimpleDirectoryReader(input_files=files_to_index).load_data()
    print(f"Loaded {len(documents)} document(s) from ./Portfolio_German/")
except FileNotFoundError:
    print("Error: './Portfolio_German/' folder not found.")
    exit()



# ----- 2) Configure Embedding Model -----

try:
    embed_model = FastEmbedEmbedding(model_name="BAAI/bge-small-en-v1.5")
    Settings.embed_model = embed_model
    print("✅ Hugging Face embedding model configured.")
except Exception as e:
    print(f"Error configuring Hugging Face model: {e}")
    exit()



# ----- 3) Build and Store Index -----

index = VectorStoreIndex.from_documents(documents, show_progress=True)
index.storage_context.persist(persist_dir="./index_storage")

print("\n✅ Portfolio index built.")