Skip to main content

No project description provided

Project description

Bedrock Bot

This project is a basic CLI-based chat bot that uses Bedrock to resolve questions. It can take input from stdin, CLI arguments or interactively when no parameters have been passed.

Installation

  1. pip install bedrock-bot
  2. You will also need some AWS credentials available in your shell (any usual way works - CLI configured IAM user access key/secret keys, environment variables, etc)
  3. Bedrock requires you to opt in to models in order to use them

Usage

bedrock --help
Usage: bedrock [OPTIONS] [ARGS]...

Options:
  -r, --region TEXT               The AWS region to use for requests
  -m, --model [Claude-3-Haiku|Claude-3-Sonnet]
                                  The model to use for requests
  --help                          Show this message and exit.

Directly as a chat bot:

$ bedrock

Hello! I am an AI assistant powered by Amazon Bedrock and using the model Claude-3-Haiku. Enter 'quit' or 'exit' at any time to exit. How may I help you today?
(You can clear existing context by starting a query with 'new>' or 'reset>')

> Hi, what is your name?
My name is Claude.

Using CLI arguments:

$ bedrock "Hi, what is your name?"

Hello! I am an AI assistant powered by Amazon Bedrock and using the model Claude-3-Haiku. Enter 'quit' or 'exit' at any time to exit. How may I help you today?
(You can clear existing context by starting a query with 'new>' or 'reset>')

> Hi, what is your name?
My name is Claude. It's nice to meet you!

Using stdin (Note that you can only use this for one-shot questions as input is reserved by your pipe to stdin and is not an interactive TTY any more):

$ echo "Hi, what is your name?" > input-file

$ cat input-file | bedrock
Hello! I am an AI assistant powered by Amazon Bedrock and using the model Claude-3-Haiku. Enter 'quit' or 'exit' at any time to exit. How may I help you today?
(You can clear existing context by starting a query with 'new>' or 'reset>')

> Hi, what is your name?

My name is Claude. I'm an AI created by Anthropic. It's nice to meet you!                                                         


Note that you can only do one-shot requests when providing input via stdin

Shell auto-complete

Shell auto-complete is also supported.

ZSH

  1. _BEDROCK_COMPLETE=zsh_source bedrock > ~/.bedrock-completion.zsh
  2. Add the following to your ~/.zshrc: source ~/.bedrock-completion.zsh

Bash

  1. _BEDROCK_COMPLETE=bash_source bedrock > ~/.bedrock-completion.bash
  2. Add the following to your ~/.bashrc: source ~/.bedrock-completion.bash

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

bedrock_bot-1.1.0.tar.gz (5.0 kB view details)

Uploaded Source

Built Distribution

bedrock_bot-1.1.0-py3-none-any.whl (6.6 kB view details)

Uploaded Python 3

File details

Details for the file bedrock_bot-1.1.0.tar.gz.

File metadata

  • Download URL: bedrock_bot-1.1.0.tar.gz
  • Upload date:
  • Size: 5.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.2 CPython/3.10.14 Linux/6.5.0-1018-azure

File hashes

Hashes for bedrock_bot-1.1.0.tar.gz
Algorithm Hash digest
SHA256 33a96945e9b969e73f5b4353cec37b08d8d49a37f30d973ca27650159040a6fe
MD5 b33f123ee59b19d96947b3664ab92585
BLAKE2b-256 ef6f8e393619ef639893052d03241504bf2516a817a4a40764f8926f4f0a0de7

See more details on using hashes here.

File details

Details for the file bedrock_bot-1.1.0-py3-none-any.whl.

File metadata

  • Download URL: bedrock_bot-1.1.0-py3-none-any.whl
  • Upload date:
  • Size: 6.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.2 CPython/3.10.14 Linux/6.5.0-1018-azure

File hashes

Hashes for bedrock_bot-1.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 fdca579a3af42929cda46728870f6492086cadbd1e38e395e4d579ac00753277
MD5 103c07b2a6f02c9825ba51976f002648
BLAKE2b-256 0e6548c3138602939a5d6942640e58dc946551b0081a069bce29c9517a872f35

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