LlamaIndex

LlamaIndex is a framework for building LLM-powered agents over your data with LLMs and workflows.

Installation

To make use of the LlamaIndex framework, install the custom Featherless AI integration

pip install llama-index llama-index-llms-featherlessai

Basic example

Below you see a basic completion call using the LlamaIndex Featherless LLM integration

Basic chat completion example
from llama_index.llms.featherlessai import FeatherlessLLM

llm = FeatherlessLLM(model="Qwen/Qwen3-32B", api_key="your api key")
resp = llm.complete("Is 9.9 or 9.11 bigger?")
print(resp)

LlamaIndex also supports calling chat with a list of messages

List of messages
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 = llm.chat(messages)

Streaming the response

Stream response
from llama_index.llms.featherlessai import FeatherlessLLM

llm = FeatherlessLLM(model="Qwen/Qwen3-32B", api_key="your api key")
response = llm.stream_complete("Who is Paul Graham?")
for r in response:
    print(r.delta, end="")

Resources

Last edited: Jun 16, 2025