from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.llms.openai import OpenAI
Settings.llm = OpenAI(model="gpt-4o-mini")
Settings.embed_model = OpenAIEmbedding(model="text-embedding-3-small")
docs = SimpleDirectoryReader("./docs").load_data
index = VectorStoreIndex.from_documents(docs)
query_engine = index.as_query_engine(similarity_top_k=3)
response = query_engine.query("What are the key findings in the Q3 report?")
print(response)

from llama_index.core.node_parser import SentenceSplitter
from llama_index.postprocessor.flag_embedding_reranker import FlagEmbeddingReranker
splitter = SentenceSplitter(chunk_size=512, chunk_overlap=100)
# attach metadata like source, page, section during ingest
reranker = FlagEmbeddingReranker(top_n=5)
query_engine = index.as_query_engine(
similarity_top_k=15,
node_postprocessors=[reranker]
)

from pydantic import BaseModel
from llama_index.core.tools import FunctionTool
class Ticket(BaseModel):
title: str
severity: str
def create_ticket(title: str, severity: str) -> str:
# write to your system
return f"Ticket created: {title} ({severity})"
tool = FunctionTool.from_defaults(fn=create_ticket)
agent = index.as_chat_engine(tools=[tool], chat_mode="react")
print(agent.chat("Create a P1 ticket for database latency spikes."))

from llama_index.core.query_engine import SubQuestionQueryEngine
from llama_index.core.tools import QueryEngineTool, ToolMetadata
# suppose you have multiple indices
engine_a = index_a.as_query_engine
engine_b = index_b.as_query_engine
sqe = SubQuestionQueryEngine.from_defaults(
query_engine_tools=[
QueryEngineTool(engine=engine_a, metadata=ToolMetadata(name="finance")),
QueryEngineTool(engine=engine_b, metadata=ToolMetadata(name="product")),
]
)
print(sqe.query("How did product churn affect Q4 revenue?"))