Integrate LangChain Bedrock LLM and Elasticsearch

This workbook demonstrates how to work with Langchain Amazon Bedrock. Amazon Bedrock is a managed service that makes foundation models from leading AI startup and Amazon's own Titan models available through APIs.

Install packages and import modules

Note: boto3 is part of AWS SDK for Python and is required to use Bedrock LLM

Init Bedrock client

To authorize in AWS service we can use ~/.aws/config file with configuring credentials or pass AWS_ACCESS_KEY, AWS_SECRET_KEY, AWS_REGION to boto3 module.

We're using second approach for our example.

Connect to Elasticsearch

ℹ️ We're using an Elastic Cloud deployment of Elasticsearch for this notebook. If you don't have an Elastic Cloud deployment, sign up here for a free trial.

We'll use the Cloud ID to identify our deployment, because we are using Elastic Cloud deployment. To find the Cloud ID for your deployment, go to https://cloud.elastic.co/deployments and select your deployment.

We will use ElasticsearchStore to connect to our elastic cloud deployment. This would help create and index data easily. In the ElasticsearchStore instance, will set embedding to BedrockEmbeddings to embed the texts and elasticsearch index name that will be used in this example.

Download the dataset

Let's download the sample dataset and deserialize the document.

Split Documents into Passages

We’ll chunk documents into passages in order to improve the retrieval specificity and to ensure that we can provide multiple passages within the context window of the final question answering prompt.

Here we are chunking documents into 500 token passages with an overlap of 0 tokens.

Here we are using a simple splitter but Langchain offers more advanced splitters to reduce the chance of context being lost.

Index data into elasticsearch

Next, we will index data to elasticsearch using ElasticsearchStore.from_documents. We will use Cloud ID, Password and Index name values set in the Create cloud deployment step.

Init Bedrock LLM

Next, we will initialize Bedrock LLM. In the Bedrock instance, will pass bedrock_client and specific model_id: amazon.titan-text-express-v1, ai21.j2-ultra-v1, anthropic.claude-v2, cohere.command-text-v14 or etc. You can see list of available base models on Amazon Bedrock User Guide

Asking a question

Now that we have the passages stored in Elasticsearch and llm is initialized, we can now ask a question to get the relevant passages.

Question: What is our work from home policy? [92m ---- Answer ---- [0m We have a full-time work from home policy that provides guidelines and support for employees to work remotely, ensuring the continuity and productivity of business operations during the COVID-19 pandemic and beyond. [94m ---- Sources ---- [0m Name: Work From Home Policy Content: Effective: March 2020 Purpose The purpose of this full-time work-from-home policy is to provide guidelines and support for employees to conduct their work remotely, ensuring the continuity and productivity of business operations during the COVID-19 pandemic and beyond. Scope This policy applies to all employees who are eligible for remote work as determined by their role and responsibilities. It is designed to allow employees to work from home full time while maintaining the same level of performance and collaboration as they would in the office. Eligibility Employees who can perform their work duties remotely and have received approval from their direct supervisor and the HR department are eligible for this work-from-home arrangement. Equipment and Resources ------- Name: Work From Home Policy Content: The company encourages employees to prioritize their health and well-being while working from home. This includes taking regular breaks, maintaining a work-life balance, and seeking support from supervisors and colleagues when needed. Policy Review and Updates This work-from-home policy will be reviewed periodically and updated as necessary, taking into account changes in public health guidance, business needs, and employee feedback. Questions and Concerns Employees are encouraged to direct any questions or concerns about this policy to their supervisor or the HR department. ------- Name: Work From Home Policy Content: Employees are required to accurately track their work hours using the company's time tracking system. Non-exempt employees must obtain approval from their supervisor before working overtime. Confidentiality and Data Security Employees must adhere to the company's confidentiality and data security policies while working from home. This includes safeguarding sensitive information, securing personal devices and internet connections, and reporting any security breaches to the IT department. Health and Well-being The company encourages employees to prioritize their health and well-being while working from home. This includes taking regular breaks, maintaining a work-life balance, and seeking support from supervisors and colleagues when needed. Policy Review and Updates ------- Name: Work From Home Policy Content: Employees who can perform their work duties remotely and have received approval from their direct supervisor and the HR department are eligible for this work-from-home arrangement. Equipment and Resources The necessary equipment and resources will be provided to employees for remote work, including a company-issued laptop, software licenses, and access to secure communication tools. Employees are responsible for maintaining and protecting the company's equipment and data. Workspace Employees working from home are responsible for creating a comfortable and safe workspace that is conducive to productivity. This includes ensuring that their home office is ergonomically designed, well-lit, and free from distractions. Communication -------