LlamaIndex Llms Integration: Bedrock

Installation

%pip install llama-index-llms-bedrock
!pip install llama-index

Basic Usage

from llama_index.llms.bedrock import Bedrock

# Set your AWS profile name
profile_name = "Your aws profile name"

# Simple completion call
resp = Bedrock(
    model="amazon.titan-text-express-v1", profile_name=profile_name
).complete("Paul Graham is ")
print(resp)

# Expected output:
# Paul Graham is a computer scientist and entrepreneur, best known for co-founding
# the Silicon Valley startup incubator Y Combinator. He is also a prominent writer
# and speaker on technology and business topics...

Call chat with a list of messages

from llama_index.core.llms import ChatMessage
from llama_index.llms.bedrock import Bedrock

messages = [
    ChatMessage(
        role="system", content="You are a pirate with a colorful personality"
    ),
    ChatMessage(role="user", content="Tell me a story"),
]

resp = Bedrock(
    model="amazon.titan-text-express-v1", profile_name=profile_name
).chat(messages)
print(resp)

# Expected output:
# assistant: Alright, matey! Here's a story for you: Once upon a time, there was a pirate
# named Captain Jack Sparrow who sailed the seas in search of his next adventure...

Streaming

Using stream_complete endpoint

from llama_index.llms.bedrock import Bedrock

llm = Bedrock(model="amazon.titan-text-express-v1", profile_name=profile_name)
resp = llm.stream_complete("Paul Graham is ")
for r in resp:
    print(r.delta, end="")

# Expected Output (Stream):
# Paul Graham is a computer programmer, entrepreneur, investor, and writer, best known
# for co-founding the internet firm Y Combinator...

Streaming chat

from llama_index.llms.bedrock import Bedrock

llm = Bedrock(model="amazon.titan-text-express-v1", profile_name=profile_name)
messages = [
    ChatMessage(
        role="system", content="You are a pirate with a colorful personality"
    ),
    ChatMessage(role="user", content="Tell me a story"),
]
resp = llm.stream_chat(messages)
for r in resp:
    print(r.delta, end="")

# Expected Output (Stream):
# Once upon a time, there was a pirate with a colorful personality who sailed the
# high seas in search of adventure...

Configure Model

from llama_index.llms.bedrock import Bedrock

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

# Expected Output:
# Paul Graham is a computer scientist, entrepreneur, investor, and writer. He co-founded
# Viaweb, the first commercial web browser...

Connect to Bedrock with Access Keys

from llama_index.llms.bedrock import Bedrock

llm = Bedrock(
    model="amazon.titan-text-express-v1",
    aws_access_key_id="AWS Access Key ID to use",
    aws_secret_access_key="AWS Secret Access Key to use",
    aws_session_token="AWS Session Token to use",
    region_name="AWS Region to use, e.g. us-east-1",
)

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

# Expected Output:
# Paul Graham is an American computer scientist, entrepreneur, investor, and author,
# best known for co-founding Viaweb, the first commercial web browser...

LLM Implementation example

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

Release files for llama-index-llms-bedrock 0.6.0

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-bedrock 0.6.0
File	Size	Uploaded
llama_index_llms_bedrock-0.6.0.tar.gz	10.9 kB	Aug 31, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for llama-index-llms-bedrock 0.6.0
File	Interpreter	ABI	Platform	Reset
llama_index_llms_bedrock-0.6.0-py3-none-any.whl 11.5 kB Aug 31, 2026	Python 3	none	any	Details

Total release size: 22.4 kB

Release files / llama_index_llms_bedrock-0.6.0.tar.gz

Download URL	llama_index_llms_bedrock-0.6.0.tar.gz
Size	10.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`ef9113c21f8b496e73803fca36ebffa4fe46490d7f9cb50b3718776f6fde0e96`
BLAKE2b-256 checksum How to use checksums	`bece95eedd2662c3b06aef9e1c2d29c7a7d00c3ac68ef0753fbd04a65d7ff2d3`
Upload date	Aug 31, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","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_bedrock-0.6.0-py3-none-any.whl

Download URL	llama_index_llms_bedrock-0.6.0-py3-none-any.whl
Size	11.5 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`c70aeb0295e76badc450bc87cc61e7f66210f5935aacda251ff376f71e033443`
BLAKE2b-256 checksum How to use checksums	`7bf9984c96a1d77d98ccaf3247428f09899ca67a369af52a762a56dcaef008a2`
Upload date	Aug 31, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","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}`