LlamaIndex Llms Integration: Openai

Installation

To install the required package, run:

%pip install llama-index-llms-openai

Setup

Set your OpenAI API key as an environment variable. You can replace "sk-..." with your actual API key:

import os

os.environ["OPENAI_API_KEY"] = "sk-..."

Basic Usage

Generate Completions

To generate a completion for a prompt, use the complete method:

from llama_index.llms.openai import OpenAI

resp = OpenAI().complete("Paul Graham is ")
print(resp)

Chat Responses

To send a chat message and receive a response, create a list of ChatMessage instances and use the chat method:

from llama_index.core.llms import ChatMessage

messages = [
    ChatMessage(
        role="system", content="You are a pirate with a colorful personality."
    ),
    ChatMessage(role="user", content="What is your name?"),
]
resp = OpenAI().chat(messages)
print(resp)

Streaming Responses

Stream Complete

To stream responses for a prompt, use the stream_complete method:

from llama_index.llms.openai import OpenAI

llm = OpenAI()
resp = llm.stream_complete("Paul Graham is ")
for r in resp:
    print(r.delta, end="")

Stream Chat

To stream chat responses, use the stream_chat method:

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

llm = OpenAI()
messages = [
    ChatMessage(
        role="system", content="You are a pirate with a colorful personality."
    ),
    ChatMessage(role="user", content="What is your name?"),
]
resp = llm.stream_chat(messages)
for r in resp:
    print(r.delta, end="")

Configure Model

You can specify a particular model when creating the OpenAI instance:

llm = OpenAI(model="gpt-3.5-turbo")
resp = llm.complete("Paul Graham is ")
print(resp)

messages = [
    ChatMessage(
        role="system", content="You are a pirate with a colorful personality."
    ),
    ChatMessage(role="user", content="What is your name?"),
]
resp = llm.chat(messages)
print(resp)

Asynchronous Usage

You can also use asynchronous methods for completion:

from llama_index.llms.openai import OpenAI

llm = OpenAI(model="gpt-3.5-turbo")
resp = await llm.acomplete("Paul Graham is ")
print(resp)

Set API Key at a Per-Instance Level

If desired, you can have separate LLM instances use different API keys:

from llama_index.llms.openai import OpenAI

llm = OpenAI(model="gpt-3.5-turbo", api_key="BAD_KEY")
resp = OpenAI().complete("Paul Graham is ")
print(resp)

LLM Implementation example

https://docs.llamaindex.ai/en/stable/examples/llm/openai/

Metadata

Release files for llama-index-llms-openai 0.8.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for llama-index-llms-openai 0.8.3
File	Size	Uploaded
llama_index_llms_openai-0.8.3.tar.gz	28.0 kB	Oct 12, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for llama-index-llms-openai 0.8.3
File	Interpreter	ABI	Platform	Reset
llama_index_llms_openai-0.8.3-py3-none-any.whl 29.0 kB Oct 12, 2026	Python 3	none	any	Details

Total release size: 57.0 kB

Release files / llama_index_llms_openai-0.8.3.tar.gz

Download URL	llama_index_llms_openai-0.8.3.tar.gz
Size	28.0 kB
Tags	Source
SHA-256 checksum How to use checksums	`a27c174fb8670209581513cb592291508043f10b5afea5198454501921808ba6`
BLAKE2b-256 checksum How to use checksums	`4ef332798fca5abd745bdce5bc43246eb3ce8346c2a2f905c90ad19ed51b49e9`
Upload date	Oct 12, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.13.0 {"installer":{"name":"uv","version":"0.13.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}`

Release files / llama_index_llms_openai-0.8.3-py3-none-any.whl

Download URL	llama_index_llms_openai-0.8.3-py3-none-any.whl
Size	29.0 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`b86deb1a9d296ca8a66cd2fa1e039e8752a529232cebaf0c7c1d0626c039a29a`
BLAKE2b-256 checksum How to use checksums	`0791149b84210eb39e205bfbe01d85a3e76495fe0c536f4aa9167eb6d80b61a3`
Upload date	Oct 12, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.13.0 {"installer":{"name":"uv","version":"0.13.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}`