pip install llama-index-core>=0.10.0 llama-index-llms-openai llama-index-embeddings-openai arize-phoenix

from llama_index.core import SimpleDirectoryReader
from llama_index.core.node_parser import SemanticSplitterNodeParser
from llama_index.embeddings.openai import OpenAIEmbedding

embed_model = OpenAIEmbedding(model_name="text-embedding-3-small")
splitter = SemanticSplitterNodeParser(
    buffer_size=1,
    breakpoint_percentile_threshold=95,
    embed_model=embed_model
)

docs = SimpleDirectoryReader(input_files=["data.pdf"]).load_data()
nodes = splitter.get_nodes_from_documents(docs)

from llama_index.core import VectorStoreIndex

index = VectorStoreIndex(nodes, embed_model=embed_model)
index.storage_context.persist(persist_dir="./storage")

# Confirm index built correctly
print(f"Indexed {len(index.docstore.docs)} document chunks")

# Preview a sample node
sample = list(index.docstore.docs.values())[0]
print(f"Sample chunk: {sample.text[:200]}...")

query_engine = index.as_query_engine(similarity_top_k=5)
response = query_engine.query("What are the key concepts?")
print(response)

import phoenix as px
import llama_index.core

px.launch_app()
llama_index.core.set_global_handler("arize_phoenix")
# All subsequent queries are now traced

Is the content source code?
├─ Yes → CodeSplitter
│        language="python" (or typescript, javascript, java, go)
│        chunk_lines=40, chunk_lines_overlap=15
│        → See: references/ingestion.md#codesplitter
│
└─ No, it's documents:
    ├─ Need semantic coherence (legal, technical docs)?
    │   └─ Yes → SemanticSplitterNodeParser
    │            buffer_size=1 (sensitive), 3 (stable)
    │            breakpoint_percentile_threshold=95 (fewer), 70 (more)
    │            → See: references/ingestion.md#semanticsplitternodeparser
    │
    ├─ Prioritize speed → SentenceSplitter
    │        chunk_size=1024, chunk_overlap=20
    │        → See: references/ingestion.md#sentencesplitter
    │
    └─ Need fine-grained retrieval → SentenceWindowNodeParser
             window_size=3 (surrounding sentences in metadata)
             → See: references/ingestion.md#sentencewindownodeparser

Query contains exact terms (function names, error codes, IDs)?
├─ Yes, exact match critical → BM25
│        retriever = BM25Retriever.from_defaults(nodes=nodes)
│        → See: references/retrieval-strategies.md#bm25retriever
│
├─ Conceptual/semantic query → Vector
│        retriever = index.as_retriever(similarity_top_k=5)
│        → See: references/context-rag.md
│
└─ Mixed or unknown query type → Hybrid (recommended default)
         alpha=0.5 (equal weight), 0.3 (favor BM25), 0.7 (favor vector)
         → See: references/retrieval-strategies.md#hybrid-search

Need document navigation only (prev/next/parent)?
├─ Yes → ImplicitPathExtractor (no LLM, zero cost)
│        → See: references/property-graphs.md#implicitpathextractor
│
└─ No, need semantic relationships:
    ├─ Fixed ontology required (regulated domain)?
    │   └─ Yes → SchemaLLMPathExtractor
    │            Pass schema: {"PERSON": ["WORKS_AT"], "COMPANY": ["LOCATED_IN"]}
    │            → See: references/property-graphs.md#schemallmpathextractor
    │
    └─ No, discovery/exploration:
        └─ SimpleLLMPathExtractor
           max_paths_per_chunk=10 (control noise)
           → See: references/property-graphs.md#simplellmpathextractor

Need SQL-like aggregations (COUNT, SUM)?
├─ Yes, trusted environment → TextToCypherRetriever
│        Risk: LLM syntax errors, injection
│        → See: references/property-graphs.md#texttocypherretriever
│
├─ Yes, need safety → CypherTemplateRetriever
│        Pre-define: MATCH (p:Person {name: $name}) RETURN p
│        LLM only extracts parameters
│        → See: references/property-graphs.md#cyphertemplateretriever
│
└─ No, robustness priority → VectorContextRetriever
         Vector search → graph traversal (path_depth=2)
         Most reliable, no code generation
         → See: references/property-graphs.md#vectorcontextretriever

Simple tool loop sufficient?
├─ Yes → ReAct Agent (FunctionCallingAgent)
│        Tools via FunctionTool or ToolSpec
│        → See: references/orchestration.md#react-agent-pattern
│
└─ No, need:
    ├─ Branching/cycles → Workflow
    │   → See: references/orchestration.md#branching
    ├─ Human-in-the-loop → Workflow (suspend/resume)
    │   → See: references/orchestration.md#human-in-the-loop
    ├─ Multi-agent handoff → Workflow + Concierge pattern
    │   → See: references/orchestration.md#concierge-multi-agent
    └─ Parallel execution → Workflow with multiple event emissions
        → See: references/orchestration.md#workflows

from llama_index.core.extractors import TitleExtractor, SummaryExtractor, KeywordExtractor
from llama_index.core.ingestion import IngestionPipeline

pipeline = IngestionPipeline(
    transformations=[
        splitter,
        TitleExtractor(),
        SummaryExtractor(),
        KeywordExtractor(keywords=5),
        embed_model,
    ]
)
nodes = pipeline.run(documents=docs)

from llama_index.core import PropertyGraphIndex
from llama_index.core.indices.property_graph import SimpleLLMPathExtractor

index = PropertyGraphIndex.from_documents(
    docs,
    embed_model=embed_model,
    kg_extractors=[SimpleLLMPathExtractor(max_paths_per_chunk=10)],
)

# Hybrid: vector search + graph traversal
retriever = index.as_retriever(include_text=True)

from llama_index.core.query_engine import RouterQueryEngine
from llama_index.core.selectors import LLMSingleSelector
from llama_index.core.tools import QueryEngineTool

tools = [
    QueryEngineTool.from_defaults(
        query_engine=summary_engine,
        description="High-level summaries and overviews"
    ),
    QueryEngineTool.from_defaults(
        query_engine=detail_engine,
        description="Specific facts, numbers, and details"
    ),
]

router = RouterQueryEngine(
    selector=LLMSingleSelector.from_defaults(),
    query_engine_tools=tools,
)

from llama_index.core.workflow import Workflow, step, StartEvent, StopEvent, Event

class QueryEvent(Event):
    query: str

class MyAgent(Workflow):
    @step
    async def classify(self, ev: StartEvent) -> QueryEvent:
        return QueryEvent(query=ev.get("query"))

    @step
    async def respond(self, ev: QueryEvent) -> StopEvent:
        result = self.query_engine.query(ev.query)
        return StopEvent(result=str(result))

# Run
agent = MyAgent(timeout=60)
result = await agent.run(query="What is X?")

from llama_index.core.postprocessor import SimilarityPostprocessor, LLMRerank

query_engine = index.as_query_engine(
    similarity_top_k=10,  # Retrieve more
    node_postprocessors=[
        SimilarityPostprocessor(similarity_cutoff=0.7),
        LLMRerank(top_n=3),  # Rerank to top 3
    ]
)

# Open Phoenix UI at http://localhost:6006
# Navigate to Traces → Select query → Retrieval span → Retrieved Nodes

# 1. Increase retrieval candidates
query_engine = index.as_query_engine(similarity_top_k=10)  # was 5

# 2. Add reranking to improve precision
from llama_index.core.postprocessor import LLMRerank
query_engine = index.as_query_engine(
    similarity_top_k=10,
    node_postprocessors=[LLMRerank(top_n=3)]
)

# Time the ingestion
import time
start = time.time()
nodes = splitter.get_nodes_from_documents(docs)
print(f"Chunking took {time.time() - start:.1f}s for {len(docs)} docs")

# Option 1: Use local embeddings (no API calls)
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")

# Option 2: Hybrid strategy for large corpora
bulk_nodes = SentenceSplitter().get_nodes_from_documents(bulk_docs)
critical_nodes = SemanticSplitterNodeParser(...).get_nodes_from_documents(critical_docs)

# Check extracted triples
for node in index.property_graph_store.get_triplets():
    print(node)  # Look for irrelevant or duplicate relationships

# Option 1: Reduce paths per chunk
SimpleLLMPathExtractor(max_paths_per_chunk=5)  # was 10

# Option 2: Use strict schema
SchemaLLMPathExtractor(
    possible_entities=["PERSON", "COMPANY"],
    possible_relations=["WORKS_AT", "FOUNDED"],
    strict=True
)

# Enable verbose mode
agent = MyWorkflow(timeout=60, verbose=True)
result = await agent.run(query="test")
# Check console for: [Step Name] Received event: EventType

# Verify type hints match exactly
class MyEvent(Event):
    query: str

@step
async def my_step(self, ev: MyEvent) -> StopEvent:  # Type hint must be MyEvent
    ...

import phoenix as px
session = px.launch_app()
print(f"Phoenix URL: {session.url}")  # Should print http://localhost:6006

# MUST call BEFORE any LlamaIndex imports/operations
import phoenix as px
px.launch_app()

import llama_index.core
llama_index.core.set_global_handler("arize_phoenix")

# Now import and use LlamaIndex
from llama_index.core import VectorStoreIndex