Python / Python Modern Generative AI and Agents Interview Questions

What embedding models should you use for production RAG systems, and how do you choose between OpenAI and open-source options?

The embedding model is one of the most consequential choices in a RAG system — it determines retrieval quality, cost, latency, and whether data leaves your infrastructure. The right choice depends on your data volume, sensitivity, quality requirements, and deployment environment.

Embedding Model Comparison
Model	Provider	Dimension	Speed	Cost	Best for
text-embedding-3-small	OpenAI API	1536	Fast (API)	$0.02/1M tokens	Balanced quality/cost; most RAG apps
text-embedding-3-large	OpenAI API	3072	Fast (API)	$0.13/1M tokens	Highest quality; small corpora
BAAI/bge-large-en-v1.5	HuggingFace (local)	1024	Fast GPU	Free	Private data; high-quality open-source
sentence-transformers/all-MiniLM-L6-v2	HuggingFace (local)	384	Very fast CPU	Free	Low latency; smaller corpora
nomic-ai/nomic-embed-text-v1.5	HuggingFace / API	768	Fast	Free/API	Long documents (8192 tokens)

# ââ OpenAI embeddings (best quality, external API)
from langchain_openai import OpenAIEmbeddings

oai_embed = OpenAIEmbeddings(
    model='text-embedding-3-small',
    dimensions=512,  # can reduce from 1536 for speed/cost (Matryoshka)
)

# ââ Local HuggingFace embeddings (private, free)
from langchain_huggingface import HuggingFaceEmbeddings

hf_embed = HuggingFaceEmbeddings(
    model_name='BAAI/bge-large-en-v1.5',
    model_kwargs={'device': 'cuda'},
    encode_kwargs={'normalize_embeddings': True},
)

# ââ Direct sentence-transformers usage
from sentence_transformers import SentenceTransformer

model = SentenceTransformer('BAAI/bge-small-en-v1.5', device='cuda')
texts = ['Hello world', 'Machine learning']
embeds = model.encode(texts, batch_size=64, normalize_embeddings=True)
print(embeds.shape)  # (2, 384)

# ââ Benchmark retrieval quality on your own data before committing
# BEIR benchmark: standardised RAG retrieval evaluation
# https://huggingface.co/spaces/mteb/leaderboard â MTEB leaderboard

# Quick retrieval quality check
query   = 'What is machine learning?'
corpus  = ['ML is a type of AI', 'The sky is blue', 'Neural networks learn from data']
q_embed = model.encode(query, normalize_embeddings=True)
c_embed = model.encode(corpus, normalize_embeddings=True)
scores  = c_embed @ q_embed
ranked  = sorted(zip(scores, corpus), reverse=True)
print(ranked)

Take quiz

What is the Matryoshka property of OpenAI's text-embedding-3 models?They support multiple languages simultaneously

✗ Try again.

They can be truncated to a smaller number of dimensions (e.g. 512 instead of 1536) without significant quality loss — allowing you to trade embedding size for speed and storage cost depending on your retrieval requirements

✓ Correct! Well done.

They embed both images and text in the same vector space

✗ Try again.

Each dimension of the embedding is independently interpretable

✗ Try again.

When should you choose local open-source embeddings over the OpenAI API?When you need the highest possible retrieval quality regardless of cost

✗ Try again.

When your data is sensitive or proprietary (cannot be sent to external APIs), when cost at scale is prohibitive, or when you need low-latency batch embedding of millions of documents without API rate limits

✓ Correct! Well done.

Local models always produce better embeddings than cloud APIs

✗ Try again.

When you need to embed more than 100 tokens per document

✗ Try again.

More Related questions...

What are Large Language Models (LLMs) and how do they generate text? What is the Hugging Face Transformers pipeline API and how do you use it for common NLP and vision tasks? How does tokenisation work in Hugging Face and what are the key tokenizer concepts? What is the Auto-class pattern in Hugging Face and how do you run inference with a raw model? What is prompt engineering and what are the most effective techniques for getting better outputs from LLMs? What is Retrieval-Augmented Generation (RAG) and why is it preferred over full fine-tuning for knowledge-intensive tasks? What are vector databases and how do they enable semantic search in RAG pipelines? How do you build a complete RAG pipeline using LangChain? What are the most important text splitting strategies in RAG, and how do chunk size and overlap affect retrieval quality? What are LangChain's core abstractions — Chains, Runnables, and the LangChain Expression Language? How do you add conversation memory to an LLM application with LangChain? What is an AI agent and how does function calling / tool use work in LLM-based agents? What is the ReAct agent pattern and how does LangChain implement it? How do you efficiently load large Hugging Face models for inference, including quantization and device placement? How do you use Hugging Face's text-generation pipeline with open-source chat models like Mistral or Llama? How do you use the Hugging Face Inference API and the InferenceClient for production deployments? What is LoRA and how does the Hugging Face PEFT library simplify fine-tuning large models? How do you use the Hugging Face Datasets library for training and evaluation? How do you fine-tune a model using the Hugging Face Trainer API? How do you evaluate LLM outputs for quality, factual accuracy, and hallucination? How do you stream LLM responses token by token for a better user experience? How do you use multimodal models (vision-language) with Hugging Face for image understanding tasks? How do you reliably get structured JSON output from LLMs, and what tools does LangChain provide? How do you compute semantic similarity between texts using Hugging Face and OpenAI embeddings? What document loaders does LangChain provide, and how do you handle different file types in a RAG pipeline? What is the OpenAI Assistants API and how does it differ from the Chat Completions API? What is the Parent Document Retriever pattern and when does it improve RAG performance? How do you manage, version, and reuse prompts in production LLM applications? How do you generate and manipulate images using Hugging Face's Diffusers library? How do you handle documents or conversations that exceed an LLM's context window? What is LangGraph and how does it differ from LangChain's AgentExecutor for building agents? What embedding models should you use for production RAG systems, and how do you choose between OpenAI and open-source options? How do you add safety guardrails and input/output validation to LLM applications? How do you manage LLM API costs and implement caching to reduce redundant calls? What is LlamaIndex and how does it compare to LangChain for RAG use cases? What is the Hugging Face Hub and how do you push a trained model to share it? How do you build a demo web interface for an LLM application using Gradio? How do you monitor and debug LLM applications in production using LangSmith?

Show more question and Answers...

FastAPI Basics Interview Questions

	Interviews Questions Java Spring Hibernate DevOps Testing API BigData Web Erlang AI Database Integration Cloud Python Scala Tools Golang SAP	About Javapedia.net Javapedia.net is for Java and J2EE developers, technologist and college students who prepare of interview. Also this site includes many practical examples. This site is developed using J2EE technologies by Steve Antony, a senior Developer/lead at one of the logistics based company. Follow Javapedia updates
	contact: javatutorials2016[at]gmail[dot]com
Kindly consider donating for maintaining this website. Thanks.
	Copyright © 2026, javapedia.net, all rights reserved. Privacy Policy · Terms of Service.

Python / Python Modern Generative AI and Agents Interview Questions

What embedding models should you use for production RAG systems, and how do you choose between OpenAI and open-source options?

Comments & Discussions

Recently added questions