llama-index-llms-bedrock

What it is and what it does

This package bridges AWS Bedrock LLMs into the LlamaIndex ecosystem, letting you use Bedrock-hosted models (like Amazon Titan) as the language model backend for LlamaIndex applications. It wraps boto3 calls and exposes Bedrock models through LlamaIndex's standard LLM interface, supporting text completion, chat with message history, and streaming variants of both.

You instantiate a Bedrock object with a model name and AWS credentials (profile, access keys, or session token), then call complete(), chat(), stream_complete(), or stream_chat() just as you would with any other LlamaIndex LLM. The package handles authentication and request marshaling to Bedrock, making it straightforward to swap Bedrock into existing LlamaIndex pipelines or build new ones around Bedrock models.

Use it for:

• Build LlamaIndex RAG pipelines using Bedrock models as the generation backend instead of OpenAI or other providers.
• Stream long-form completions from Bedrock models in real-time within LlamaIndex chat or agentic workflows.
• Use Bedrock's managed LLM infrastructure with LlamaIndex's retrieval and indexing tools for cost-optimized deployments.
• Integrate multi-turn conversations with Bedrock models while leveraging LlamaIndex's message history and context management.
• Deploy LlamaIndex applications on AWS without external LLM API dependencies by using Bedrock as the sole LLM provider.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Integrates AWS Bedrock LLMs into LlamaIndex, enabling you to use Bedrock-hosted language models for text completion, chat, and streaming operations within LlamaIndex workflows.

Yes, if you are already using LlamaIndex and need to route requests through AWS Bedrock. The package has low install friction, active maintenance, MIT licensing, no known vulnerabilities, and clear integration points. Install it only if you have AWS Bedrock access and want to use it as your LlamaIndex LLM backend; otherwise it adds no value.

Install

llama-index-llms-bedrock on PyPI

pip install llama-index-llms-bedrock

uv add llama-index-llms-bedrock

poetry add llama-index-llms-bedrock

Installing llama-index-llms-bedrock

Before you install

Low friction: pure Python wheel with three runtime dependencies (boto3, llama-index-core, llama-index-llms-anthropic). Package is actively maintained with recent releases.

License in practice

MIT license permits commercial and private use with minimal restrictions; you may use, modify, and distribute this package freely provided you retain the license notice.

Quickstart

pip install llama-index-llms-bedrock

from llama_index.llms.bedrock import Bedrock

llm = Bedrock(model="amazon.titan-text-express-v1", profile_name="your-aws-profile")
response = llm.complete("Paul Graham is ")
print(response)

Requires AWS credentials (via profile_name, access keys, or environment) and access to Bedrock models in your AWS account; Python 3.10 or later.

Verify before relying

• Which Bedrock model endpoints are supported beyond amazon.titan-text-express-v1
• Whether streaming operations have latency or throughput guarantees
• Support for model-specific parameters or inference configuration options

Package facts

Evidence: llama_index_llms_bedrock-0.5.0-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading