Skip to main content

LLM plugin for Amazon Titan on AWS Bedrock

Project description

llm-bedrock-amazon

PyPI License

Plugin for LLM adding support for Amazon Titan Express model.

Installation

Install as LLM plugin:

$ llm install llm-bedrock-amazon

Install from the GitHub repository:

$ git clone https://github.com/avoidik/llm-bedrock-amazon
$ llm install -e llm-bedrock-amazon

Or, from the local directory:

$ llm install -e .

Configuration

You will need to specify AWS Configuration with the normal boto3 and environment variables.

For example, to use the region us-west-2 and AWS credentials under the personal profile, set the environment variables

export AWS_DEFAULT_REGION="us-west-2"
export AWS_PROFILE="personal"

The model must be enabled in your AWS account.

Usage

This plugin adds the following new model:

amazon.titan-text-express-v1 (aliases: bedrock-titan-express, bte)

You can query them like this:

$ llm -m bte "Give me 10 random names so that I can name my unnamed cat"

Options

  • max_token_count, default 4096 -- The maximum number of tokens to generate in the response.

  • temperature, default 0.7 -- Use a lower value to decrease randomness in the response.

  • diversity, default 0.9 -- Use a lower value to ignore less probable options and decrease the diversity of responses.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llm_bedrock_amazon-1.0.1.tar.gz (7.2 kB view details)

Uploaded Source

Built Distribution

llm_bedrock_amazon-1.0.1-py3-none-any.whl (7.9 kB view details)

Uploaded Python 3

File details

Details for the file llm_bedrock_amazon-1.0.1.tar.gz.

File metadata

  • Download URL: llm_bedrock_amazon-1.0.1.tar.gz
  • Upload date:
  • Size: 7.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.9.19

File hashes

Hashes for llm_bedrock_amazon-1.0.1.tar.gz
Algorithm Hash digest
SHA256 cb346393458346b0ede95d3e8ab3c38d89a518d3ce642e9f69a8d868e0af9be8
MD5 b5e012c5b07f39c268f8c27ae5cf7de8
BLAKE2b-256 27b94560b5fbfef93cd816bfe74d7b046151d588402f0eedfb5b3a58c01a20bc

See more details on using hashes here.

File details

Details for the file llm_bedrock_amazon-1.0.1-py3-none-any.whl.

File metadata

File hashes

Hashes for llm_bedrock_amazon-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 4f8c4d2f31f6d0f582e2889f8a1f77e379e6ce7cd561413ef4963e16a16ba8e9
MD5 dc5f34b89083530ea7b65a5c1975b32f
BLAKE2b-256 860e706af915ab9fa2ee801c26027fd4c5d6ab9ec45e2af3279b06fe0673ace6

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page