PristrenLlamaIndex handles document loading, chunking, embedding, indexing, and retrieval in a composable pipeline - from a local PDF to a full multi-source RAG app.
Mahmudul Haque Qudrati
CEO & ML Engineer
// tags
OpenAI Codex issue #2847 about excluding sensitive files from context is still unresolved. This post covers the problem, current workarounds, and why it's a critical missing feature for production use.
LlamaIndex is a data framework for LLM applications. Its core abstraction is the index: a structure that ingests documents, chunks and embeds them, and exposes a query interface. Building RAG from scratch requires 500+ lines of glue code; LlamaIndex compresses this to a few dozen lines while remaining highly configurable.
pip install llama-index llama-index-llms-openai llama-index-embeddings-openai
Team workspace
Ship faster with chat, meetings, and projects in one place — Zlyqor.
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.llms.openai import OpenAI
from llama_index.core import Settings
# Configure models
Settings.llm = OpenAI(model="gpt-4o-mini", temperature=0.1)
Settings.embed_model = "local" # uses sentence-transformers locally
# Load documents from a directory
documents = SimpleDirectoryReader("./docs/").load_data()
# Build index (chunks, embeds, stores in-memory)
index = VectorStoreIndex.from_documents(documents)
# Query
query_engine = index.as_query_engine()
response = query_engine.query("What is PagedAttention?")
print(response)
LlamaIndex ships 100+ loaders for common data sources:
from llama_index.readers.web import SimpleWebPageReader
from llama_index.readers.github import GithubRepositoryReader
from llama_index.readers.notion import NotionPageReader
web_docs = SimpleWebPageReader().load_data(["https://docs.vllm.ai/"])
github_docs = GithubRepositoryReader(owner="vllm-project", repo="vllm").load_data()
Control chunking strategy:
from llama_index.core.node_parser import SentenceSplitter, SemanticSplitterNodeParser
# Fixed-size with overlap
parser = SentenceSplitter(chunk_size=512, chunk_overlap=64)
# Semantic chunking (groups semantically similar sentences)
semantic_parser = SemanticSplitterNodeParser(embed_model=Settings.embed_model)
nodes = semantic_parser.get_nodes_from_documents(documents)
from llama_index.core import get_response_synthesizer
# compact: default, fits context into fewest LLM calls
# refine: iterative, updates answer as it reads each chunk
# tree_summarize: builds summary tree bottom-up
synthesizer = get_response_synthesizer(response_mode="tree_summarize")
query_engine = index.as_query_engine(response_synthesizer=synthesizer)
Break complex questions into sub-questions answered by different indices:
from llama_index.core.query_engine import SubQuestionQueryEngine
from llama_index.core.tools import QueryEngineTool
tools = [
QueryEngineTool.from_defaults(query_engine=vllm_index.as_query_engine(), name="vllm_docs", description="vLLM documentation"),
QueryEngineTool.from_defaults(query_engine=ollama_index.as_query_engine(), name="ollama_docs", description="Ollama documentation"),
]
engine = SubQuestionQueryEngine.from_defaults(query_engine_tools=tools)
response = engine.query("Compare vLLM and Ollama for production serving")
query_engine = index.as_query_engine(streaming=True)
streaming_response = query_engine.query("Explain HNSW indexing")
for text_chunk in streaming_response.response_gen:
print(text_chunk, end="", flush=True)
from llama_index.core.vector_stores import MetadataFilter, MetadataFilters
filters = MetadataFilters(filters=[MetadataFilter(key="source", value="technical-docs")])
query_engine = index.as_query_engine(filters=filters)
Full documentation at docs.llamaindex.ai.
Chat, meetings, project management, and time tracking — all wired together with AI. Stop context-switching between five tools.
Try Zlyqor freePractical deep-dives on LLMs, developer tools, and AI engineering. No filler. Unsubscribe any time.
CEO & ML Engineer
CEO and ML Engineer at Pristren. Builds AI-powered software for teams and writes about machine learning, LLMs, developer tools, and practical AI applications.
Alibaba is reportedly banning Claude Code from its workplace due to alleged backdoor risks. This post explains the incident, the technical concerns, and the broader implications for AI coding assistants in regulated environments.
