Conversational Search for Financial Services
Utilize Amazon Kendra and Generative AI to search & generate content
Overview
Conversational Search for Financial Services Demo is powered by Amazon Kendra and Generative AI. This demo shows a Generative Search and Discovery experience for a user (e.g financial analyst or advisor) to go through large volumes of financial data and reports and discover specific information about a company. This solution empowers the analyst to make quick data-driven decisions using a conversational experience saving time and effort. This demo is applicable to Financial organizations (e.g. Banking and Insurance), Any Financial information providers (e.g. Ratings companies, Financial news) and/or enterprise financial department executives.
Conversational Search across multiple data sources.
This demo uses SEC financial reports. Kendra can ingest million of documents using its pre-built connectors and allow customers to build fast and accurate conversational experience quickly.Amazon Kendra has pre-built connectors for popular data sources such as Amazon Simple Storage Service (Amazon S3), SharePoint, Confluence, and websites, and supports common document formats such as HTML, Word, PowerPoint, PDF, and pure text files.
Get reliable answers with source attribution
This chatbot provides answers along with source links. It uses the RAG(Retrieval Augmented Generation) approach to retrieve information most relevant to the user’s request from the enterprise knowledge base or content, bundles it as context along with the user’s request as a prompt, and then sends it to the LLM to get a GenAI response.
Leverage conversational memory
This chatbot has the ability to remember few of the previous conversation during a chat session. Users do not have to provide all the context in a question
Generate summaries and emails on enterprise data
Users will be able to generate summaries and emails based on the information present in enterprise data sources
Build and deploy similar bots using steps in the blog
Sample questions: Flow 1
- What was the unearned revenue for Amazon as of December 2022?
- Draft a concise email about above unearned revenue to jane@example.com.
- What are amazons long term lease liabilities ?
- Redraft above email by including a paragraph about lease liabilities
- Draft it in Spanish.
Sample questions: Flow 2
- How much interest income did Amazon have in 2022?
- How much interest income did Amazon have in 2021?
- What is the difference in interest income between 2022 and 2021?
- Can you summarize this development in an email to Pascal?
- What are amazons long term lease liabilities ?
- Redraft above email by adding a paragraph about long term lease liabilities.
- I want it in French
Architecture
The Workflow includes the following steps:
- 1000s of financial documents are injested into Amazon Kendra index using the S3 data source connector.
- The LLM is hosted on a SageMaker endpoint.
- An Amazon Lex chatbot is used to interact with the user via the Amazon Lex web UI.
- The solution uses an AWS Lambda function with LangChain to orchestrate between Amazon Kendra, Amazon Lex, and the LLM.
- When users ask the Amazon Lex chatbot for answers from a clinical trails, Amazon Lex calls the Lambda orchestrator to fulfill the request.
- Based on the query, the Lambda orchestrator pulls the relevant records and paragraphs from Amazon Kendra.
- The Lambda orchestrator provides these relevant records to the LLM along with the query and relevant prompt to carry out the required activity.
- The LLM processes the request from the Lambda orchestrator and returns the result.
- The Lambda orchestrator gets the result from the LLM and sends it to the end-user through the Amazon Lex chatbot.
Sustainability
Innovation for Tomorrow
Our AI services prioritize sustainability, delivering innovative solutions that harmonize technological progress with environmental responsibility for a brighter future
We Follow Best Practices
We do AI right by using the best methods, making sure our solutions work well and are ethical.
- Sustainablility
- Project On Time
- Modern Technology
- Latest Designs
About Founders
We Are Leading International Company In The World
Whar Our Clients Say
Testimonials
Engineering Manager
Alice Howard
AIGreenSolutions is a trailblazer in the realm of emerging solutions and AI use cases. As a forward-thinking professional constantly seeking innovative approaches to enhance efficiency and productivity.
Interior Designer
Nathan Marshall
From the very onset, AIGreenSolutions distinguished themselves with their commitment to staying on the cutting edge of technology. Our team of experts exhibited a profound understanding of emerging solutions and artificial intelligence, seamlessly integrating these advancements into practical use cases that addressed your unique business challenges.
Architect
Ema Romero
Equally commendable is AIGreensolution's emphasis on transparency and collaboration. Throughout our engagement, we maintained open lines of communication, keeping you informed at every stage of the process. This collaborative spirit instilled trust and confidence in our capabilities, making the entire journey smooth and enjoyable.
Manager
Ann Smith
What sets AIGreenSolution apart is its unwavering commitment to ongoing innovation. In an ever-evolving technological landscape, we remain at the forefront, continuously exploring new possibilities and refining solutions to stay ahead of the curve. This proactive approach instills confidence and assures clients that we are not just investing in today's solutions but in the promise of tomorrow's advancements.
Request a Quote
Learn More From
Frequently Asked Questions
we offer comprehensive, custom services across the artificial intelligence spectrum.
We employ cutting-edge technologies, ensuring state-of-the-art solutions tailored to meet diverse and evolving demands
Our pricing model is flexible, transparent, and designed to accommodate your specific requirements and budget constraints.