from llama_index.core import VectorStoreIndex, SimpleDirectoryReader


from llama_index.llms.openai import OpenAI


from llama_index.core import Settings




# Configure LLM


Settings.llm = OpenAI(model="gpt-4o", api_key="your-key")




# Load documents (supports PDF, Word, TXT, etc.)


documents = SimpleDirectoryReader("./docs").load_data()




# Build index (automatic chunking, vectorization)


index = VectorStoreIndex.from_documents(documents)




#Create query engine


query_engine = index.as_query_engine()




#Ask a question


response = query_engine.query("What is the company's core product?")


print(response)


print("\nSource:", response.source_nodes[0].text[:200])

import os
from llama_index.core import (
    VectorStoreIndex, SimpleDirectoryReader,
    StorageContext, load_index_from_storage
)

PERSIST_DIR = "./storage"

if not os.path.exists(PERSIST_DIR):
    # Build and save for the first time
    documents = SimpleDirectoryReader("./docs").load_data()
    index = VectorStoreIndex.from_documents(documents)
    index.storage_context.persist(persist_dir=PERSIST_DIR)
    print("Index construction completed and saved")
else:
    # Directly load existing indexes
    storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
    index = load_index_from_storage(storage_context)
    print("Load index from cache")

query_engine = index.as_query_engine()
response = query_engine.query("your question")

from llama_index.core.node_parser import SentenceWindowNodeParser
from llama_index.core.postprocessor import MetadataReplacementPostProcessor

# Sentence window: Retrieve in sentences, but return a larger context window
node_parser = SentenceWindowNodeParser.from_defaults(
    window_size=3, # Return the context of 3 sentences before and after
    window_metadata_key="window",
    original_text_metadata_key="original_text"
)

# Build index
index = VectorStoreIndex.from_documents(
    documents,
    transformations=[node_parser]
)

#Replace with full window when querying
query_engine = index.as_query_engine(
    node_postprocessors=[
        MetadataReplacementPostProcessor(target_metadata_key="window")
    ]
)

from llama_index.core import SQLDatabase
from llama_index.core.query_engine import NLSQLTableQueryEngine
from sqlalchemy import create_engine

# Connect to database
engine = create_engine("sqlite:///sales.db")
sql_database = SQLDatabase(engine, include_tables=["orders", "customers"])

# Create a natural language query engine
query_engine = NLSQLTableQueryEngine(
    sql_database=sql_database,
    tables=["orders", "customers"]
)

# Query using natural language
response = query_engine.query(
    "Which customer had the highest order value in the past 30 days?"
)
print(response)
print("Executed SQL:", response.metadata["sql_query"])