LlamaIndex

Use AJ STUDIOZ Cloud Infra with LlamaIndex for RAG, agents, and knowledge bases

Overview

LlamaIndex integrates with AJ STUDIOZ Cloud Infra through the OpenAI-compatible API. All models are cloud-hosted — no GPU or local Ollama instance required. Use any model for chat, completions, and embeddings in your LlamaIndex pipelines.

Installation

pip install llama-index llama-index-llms-openai llama-index-embeddings-openai

LLM Setup

Setup

from llama_index.llms.openai import OpenAI
from llama_index.core import Settings

llm = OpenAI(
    model="gemma3:27b",
    api_base="https://api.ajstudioz.co.in/v1",
    api_key="YOUR_API_KEY",
    temperature=0.7
)

# Set as global default
Settings.llm = llm

---

Embeddings Setup

Embeddings Setup

from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.core import Settings

embed_model = OpenAIEmbedding(
    model="gemma3:4b",
    api_base="https://api.ajstudioz.co.in/v1",
    api_key="YOUR_API_KEY"
)

Settings.embed_model = embed_model

---

Simple Q&A

Q&A

from llama_index.llms.openai import OpenAI
from llama_index.core.llms import ChatMessage

llm = OpenAI(
    model="deepseek-v3.2",
    api_base="https://api.ajstudioz.co.in/v1",
    api_key="YOUR_API_KEY"
)

messages = [
    ChatMessage(role="system", content="You are a helpful assistant."),
    ChatMessage(role="user", content="Summarize the benefits of AI in education."),
]

response = llm.chat(messages)
print(response.message.content)

---

Document Index + RAG

Models and embeddings run entirely in AJ STUDIOZ cloud — no local GPU needed.

RAG with Documents

from llama_index.core import VectorStoreIndex, Document, Settings
from llama_index.llms.openai import OpenAI
from llama_index.embeddings.openai import OpenAIEmbedding

Settings.llm = OpenAI(
    model="gemma3:27b",
    api_base="https://api.ajstudioz.co.in/v1",
    api_key="YOUR_API_KEY"
)
Settings.embed_model = OpenAIEmbedding(
    model="gemma3:4b",
    api_base="https://api.ajstudioz.co.in/v1",
    api_key="YOUR_API_KEY"
)

documents = [
    Document(text="AJ STUDIOZ Cloud Infra provides cloud-hosted AI inference with Ollama and OpenAI compatible APIs."),
    Document(text="32+ models available: Gemma 3, Qwen 3 VL, Kimi K2, DeepSeek V3, GLM-4, MiniMax, Mistral, and more."),
    Document(text="Authentication uses Bearer tokens. Get your key at cloud.ajstudioz.com."),
    Document(text="Ollama base URL: https://api.ajstudioz.co.in | OpenAI base URL: https://api.ajstudioz.co.in/v1"),
]

index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
response = query_engine.query("How do I authenticate with AJ STUDIOZ?")
print(response)

---

Streaming

Streaming

from llama_index.llms.openai import OpenAI
from llama_index.core.llms import ChatMessage

llm = OpenAI(
    model="gemma3:27b",
    api_base="https://api.ajstudioz.co.in/v1",
    api_key="YOUR_API_KEY"
)

messages = [ChatMessage(role="user", content="Write a brief history of the internet.")]

for delta in llm.stream_chat(messages):
    print(delta.delta, end="", flush=True)

---

Next Steps

LangChain Integration

Use LangChain with AJ STUDIOZ

Embeddings Guide

RAG pipelines and embeddings tips