Skip to content

Commit

Permalink
Add Amazon Bedrock integration (#111)
Browse files Browse the repository at this point in the history
* Add Amazon Bedrock integration

* add logo

* Rename amazon-bedrock to amazon-bedrock.md

* Update amazon-bedrock.md

* Remove mention of embed models
  • Loading branch information
julian-risch authored Jan 10, 2024
1 parent a15e09d commit 61a6881
Show file tree
Hide file tree
Showing 2 changed files with 67 additions and 0 deletions.
67 changes: 67 additions & 0 deletions integrations/amazon-bedrock.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,67 @@
---
layout: integration
name: Amazon Bedrock
description: Use Models from AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon via Amazon Bedrock with Haystack
authors:
- name: deepset
socials:
github: deepset-ai
twitter: deepset_ai
linkedin: deepset-ai
pypi: https://pypi.org/project/amazon-bedrock-haystack
repo: https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/amazon_bedrock
type: Model Provider
report_issue: https://github.com/deepset-ai/haystack-core-integrations/issues
logo: /logos/aws.png
version: Haystack 2.0
toc: true
---

### Table of Contents

- [Overview](#overview)
- [Installation](#installation)
- [Usage](#usage)
- [AmazonBedrockGenerator](#AmazonBedrockGenerator)

## Overview

[Amazon Bedrock](https://aws.amazon.com/bedrock/) is a fully managed service that makes high-performing foundation models from leading AI startups and Amazon available for your use through a unified API. You can choose from various foundation models to find the one best suited for your use case. More information can be found on the [documentation page](https://docs.haystack.deepset.ai/v2.0/docs/amazonbedrockgenerator).

## Installation

Install the Amazon Bedrock integration:
```bash
pip install amazon-bedrock-haystack
```

## Usage

Once installed, you will have access to an AmazonBedrockGenerator that supports models from various providers:
- Anthropic's Claude
- AI21 Labs' Jurassic-2
- Stability AI's Stable Diffusion
- Cohere's Command
- Meta's Llama 2
- Amazon Titan language models

### AmazonBedrockGenerator

To use this integration for text generation, initialize a `AmazonBedrockGenerator` with the model name and aws credentials:

```python
from amazon_bedrock_haystack import AmazonBedrockGenerator

aws_access_key_id="..."
aws_secret_access_key="..."
aws_region_name="eu-central-1"

generator = AmazonBedrockGenerator(model_name="anthropic.claude-v2", aws_access_key_id=aws_access_key_id, aws_secret_access_key=aws_secret_access_key, aws_region_name=aws_region_name)
result = generator.run("Who is the best American actor?")
for reply in result["replies"]:
print(reply)
```
Output:
```shell
'There is no definitive "best" American actor, as acting skill and talent a# re subjective. However, some of the most acclaimed and influential American act# ors include Tom Hanks, Daniel Day-Lewis, Denzel Washington, Meryl Streep, Rober# t De Niro, Al Pacino, Marlon Brando, Jack Nicholson, Leonardo DiCaprio and John# ny Depp. Choosing a single "best" actor comes down to personal preference.'
```
Binary file added logos/aws.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit 61a6881

Please sign in to comment.