generated_project/utils/llama_index_utils.py

import os
from llama_index.core import Settings
from llama_index.llms.huggingface import HuggingFaceInferenceAPI
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from dotenv import load_dotenv

# Load environment variables
load_dotenv()

# Configure the Llama index settings
def initialize_llama_settings():
 Settings.llm = HuggingFaceInferenceAPI(
 model_name="google/gemma-1.1-7b-it",
 tokenizer_name="google/gemma-1.1-7b-it",
 context_window=3000,
 token=os.getenv("HF_TOKEN"),
 max_new_tokens=512,
 generate_kwargs={"temperature": 0.1},
 )
 Settings.embed_model = HuggingFaceEmbedding(
 model_name="BAAI/bge-small-en-v1.5"
 )

# Ensure data directory and persistent storage directory exist
def setup_directories(data_dir="data", persist_dir="./db"):
 os.makedirs(data_dir, exist_ok=True)
 os.makedirs(persist_dir, exist_ok=True)
 return data_dir, persist_dir