Skip to content

DOCSP-49594 -- Migration of financial services docs #193

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 117 commits into from
May 28, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
117 commits
Select commit Hold shift + click to select a range
6d5ed3a
DOCSP-49594 -- First draft of credit-card-application-with-generative…
xargom Apr 29, 2025
97044dd
DOCSP-49594 -- Fixed link
xargom Apr 29, 2025
e72d542
DOCSP-49594 -- Test with inter-repo links
xargom Apr 29, 2025
53a2520
Second try with inter-repo links
xargom Apr 29, 2025
692a5d7
DOCSP-49597 -- Formatted entire document. Metadata and rendering deta…
xargom Apr 30, 2025
b1bc732
Merge branch 'mongodb:solutions-poc' into solutions-poc
xargom May 2, 2025
843db0d
DOCSP-49597 -- Added card. Fixed links.
xargom May 2, 2025
5046561
DOCSP-49597 -- added snooty variables
xargom May 2, 2025
4460ab0
DOCSP-49597 -- fixed errors
xargom May 2, 2025
f1f1362
DOCSP-49597 - Fixed errors
xargom May 2, 2025
fb7442c
DOCSP-49597 - Embedded video
xargom May 2, 2025
b062551
DOCSP-49597 - Embedded video 2nd try
xargom May 2, 2025
e4274b0
DOCSP-49597 - Removed video alt option
xargom May 2, 2025
fe0a046
DOCSP-49597 - Fixed link in new card in /solutions-library.txt
xargom May 5, 2025
e83c797
DOCSP-49597 - Fixed link again
xargom May 5, 2025
174f7fa
DOCSP-49598 -- First draft of /assessing-business-loan-risks-with-gen…
xargom May 5, 2025
d827d6f
DOCSP-49598 -- Added caption
xargom May 5, 2025
6a41524
DOCSP-49598 -- Removed caption
xargom May 5, 2025
56e1a89
DOCSP-49598 -- Added images
xargom May 6, 2025
46ea0f6
DOCSP-49598 -- Added card in landing page
xargom May 6, 2025
af61bba
DOCSP-49598 -- Added loan risk assessment doc to toctree
xargom May 6, 2025
2abefa6
DOCSP-49598 -- Added snooty constants and replacements
xargom May 6, 2025
8c8a4aa
DOCSP-49598 -- Fixed render errors
xargom May 6, 2025
784c666
DOCSP-49598 -- Fixed errors
xargom May 6, 2025
2138562
DOCSP-49598 -- Fixed incorrect image
xargom May 6, 2025
bf479d1
DOCSP-49599 -- First draft for source/solutions-library/ai-driven-int…
xargom May 6, 2025
e110d21
DOCSP-49599 -- Added interactive banking doc to toctree and correspon…
xargom May 7, 2025
bf35143
DOCSP-49599 -- Fixed typo. 2nd try with video
xargom May 7, 2025
6a7976d
DOCSP-49599 -- 3rd try with local video
xargom May 7, 2025
714d903
DOCSP-49599 -- 4th try with local video
xargom May 7, 2025
54c99cc
DOCSP-49599 -- Fixed indentation
xargom May 7, 2025
4b4db26
DOCSP-49599 -- Another try with .svg image
xargom May 7, 2025
f7bca5e
DOCSP-49599 -- Changed mp4 to gif file
xargom May 7, 2025
abd4e3b
DOCSP-49600 -- Added source/solutions-library/fraud-prevention.txt
xargom May 7, 2025
c089151
DOCSP-49600 -- Added card for fraud-prevention.txt in solutions library
xargom May 7, 2025
83e91c2
DOCSP-49600 -- Fixed indentation in solutions library
xargom May 7, 2025
e1aa2b3
DOCSP-49600 -- Fixed errors
xargom May 7, 2025
3959ccc
DOCSP-49600 -- Fixed spacing
xargom May 7, 2025
efc4084
DOCSP-49600 -- Added snooty items
xargom May 7, 2025
37a658c
DOCSP-49600 -- Changed doctree files
xargom May 8, 2025
9a5155f
DOCSP-49600 -- Added title case
xargom May 8, 2025
f538c6d
DOCSP-49600 -- Added title case x2
xargom May 8, 2025
b71bf76
DOCSP-49600 -- First draft for source/solutions-library/card-fraud-so…
xargom May 8, 2025
f8b4a67
DOCSP-49600 -- Added snooty substitutions and constants
xargom May 8, 2025
5c986b9
DOCSP-49600 -- Fixed errors
xargom May 8, 2025
b9a1574
DOCSP-49600 -- Fixed errors 2
xargom May 8, 2025
9a1c2c8
DOCSP-49600 -- Fixed errors 3
xargom May 8, 2025
41240b5
DOCSP-49600 -- Fixed link
xargom May 8, 2025
36e1a01
DOCSP-49600 -- Fixed link 2
xargom May 8, 2025
75feee9
DOCSP-49601 -- First draft for source/includes/images/industry-soluti…
xargom May 8, 2025
a4851c9
DOCSP-49601 -- Corrected file location
xargom May 8, 2025
ac5d770
DOCSP-49601 -- Fixed errors
xargom May 9, 2025
d2816d2
DOCSP-49601 -- Added snooty variables
xargom May 9, 2025
b9d3103
DOCSP-49601 -- Added snooty variables 2
xargom May 9, 2025
2a77481
DOCSP-49603 -- First draft for source/solutions-library/open-finance-…
xargom May 9, 2025
2aa138e
DOCSP-49603 -- Fixed errors
xargom May 9, 2025
5afb7d5
DOCSP-49603 -- Fixed errors 2
xargom May 9, 2025
c084713
DOCSP-49603 -- 2nd draft of source/solutions-library/open-finance-dat…
xargom May 12, 2025
dcabf30
DOCSP-49604 -- First draft source/solutions-library/hasura-fintech-se…
xargom May 13, 2025
9b3ae9a
DOCSP-49604 -- Added card to lansing page. Snooty replacements, corre…
xargom May 13, 2025
d9089f9
DOCSP-49605 -- first draft for source/solutions-library/payments-solu…
xargom May 13, 2025
14c2e1c
DOCSP-49605 -- fixed bug. changed icons in cards
xargom May 13, 2025
2806b66
DOCSP-49605 -- fixed bug x2
xargom May 13, 2025
38bc619
Merge branch 'mongodb:solutions-poc' into solutions-poc
xargom May 20, 2025
1c2128d
DOCSP-45597 -- Fixed errors and warnings in log
xargom May 20, 2025
a39078f
DOCSP-45597 -- Fixed errors and warnings in log 2
xargom May 22, 2025
a791063
DOCSP-45597 -- Fixed errors and warnings in log 3
xargom May 22, 2025
b237e42
Update source/solutions-library/ai-driven-interactive-banking.txt
xargom May 23, 2025
579ed2a
Update source/solutions-library/open-finance-data-store.txt
xargom May 23, 2025
c8148c9
Update source/solutions-library/credit-card-application-with-generati…
xargom May 23, 2025
1eb7ac8
Update source/solutions-library/credit-card-application-with-generati…
xargom May 23, 2025
ca9ea69
Update source/solutions-library/open-finance-data-store.txt
xargom May 23, 2025
712a3fd
Update source/solutions-library/credit-card-application-with-generati…
xargom May 23, 2025
694e69a
Update source/solutions-library/credit-card-application-with-generati…
xargom May 23, 2025
0db629a
Update source/solutions-library/credit-card-application-with-generati…
xargom May 23, 2025
3ce97c2
DOCSP-49597 -- Fixed substitutions mistakes and corrected numbered li…
xargom May 23, 2025
2c7c6e4
DOCSP-49597 -- Further changes to bulleted list
xargom May 23, 2025
096854d
Update source/solutions-library/assessing-business-loan-risks-with-ge…
xargom May 26, 2025
38267ac
Merge branch 'mongodb:solutions-poc' into solutions-poc
xargom May 26, 2025
f0d0b87
DOCSP-49597, 49598, 49599, and 49600 -- Fixed errors based on feedback.
xargom May 26, 2025
a9d1def
DOCSP-49601 -- Fixed errors based on feedback
xargom May 26, 2025
d3d282e
DOCSP-49602 -- Fixed errors based on feedback
xargom May 26, 2025
68c005b
DOCSP-49603 -- Fixed errors based on feedback
xargom May 26, 2025
1d62591
DOCSP-49603 -- Added json defintion to codeblocks
xargom May 26, 2025
0bb5289
DOCSP-49604 -- Fixed errors based on feedback
xargom May 26, 2025
427f195
DOCSP-49605 -- Fixed errors based on feedback
xargom May 26, 2025
7182f50
Fixed indentation to avoid warning in log
xargom May 26, 2025
65fb516
DOCSP-49599 -- Warning in log persists. Small change in /ai-driven-in…
xargom May 27, 2025
a7ea369
DOCSP-49599 -- Warning in log persists. 2nd change in /ai-driven-int…
xargom May 27, 2025
5244a4e
DOCSP-49605 -- Corrected capitalization in heading to match other hea…
xargom May 27, 2025
afc1fa6
DOCSP-49603 -- Corrected indenting and spacing in a list
xargom May 27, 2025
29e0de5
DOCSP-49603 -- Corrected indenting on list again. Original version ha…
xargom May 27, 2025
a86997c
DOCSP-49603 -- Added blank lines in list
xargom May 27, 2025
0e44da8
Merged changes from collaborator branch to avoid conflicts
xargom May 27, 2025
7f350fd
DOCSP-49602 -- Corrected line in last section
xargom May 27, 2025
2edb029
DOCSP-49600 -- Fixed spacing in Technologies and Products section
xargom May 27, 2025
8603d57
DOCSP-49600 -- Fixed spacing in Technologies and Products section x2
xargom May 27, 2025
5bc9a02
DOCSP-49597 -- corrected incorrect title
xargom May 27, 2025
c504426
DOCSP-49597 -- Matched capitalization to other headings in the doc
xargom May 27, 2025
68c3847
Update leafy-bank-in-aws.svg
xargom May 27, 2025
0123f0a
Update open-finance-architecture.svg. Added width and height
xargom May 27, 2025
ceb866a
Update leafy-bank-in-aws.svg. Modified width and height values
xargom May 27, 2025
360f8a8
Update leafy-bank-in-aws.svg. Modified width and height values.
xargom May 27, 2025
7efc290
Update leafy-bank-in-aws.svg. Modified values again.
xargom May 27, 2025
500bdbb
Update open-finance-architecture.svg Modified height and values. Eras…
xargom May 27, 2025
fc97117
Update open-finance-architecture.svg. Modified values again.
xargom May 27, 2025
150d499
Update open-finance-architecture.svg. Removed previously added height…
xargom May 27, 2025
20bffd8
Update source/solutions-library/assessing-business-loan-risks-with-ge…
xargom May 28, 2025
62c89dc
Merge branch 'mongodb:solutions-poc' into solutions-poc
xargom May 28, 2025
81a56f2
DOCSP-49598 -- Further changes based on feedback.
xargom May 28, 2025
e24f760
DOCSP-49599 -- Further changes based on feedback.
xargom May 28, 2025
d6301c8
DOCSP-49600 -- Changed link in app services to doc that indicates the…
xargom May 28, 2025
bf956cc
DOCSP-49600 -- Added newline
xargom May 28, 2025
8eb7ee6
DOCSP-49602 -- Fixed spacing and line breaks based on feedback
xargom May 28, 2025
0adf2da
DOCSP-49603 -- Added missing newline
xargom May 28, 2025
aa3fa3c
DOCSP-49604 -- Added missing paragraph and corrected indentation prob…
xargom May 28, 2025
c67167f
DOCSP-49605 -- Added missing line and deleted unnecesary constant
xargom May 28, 2025
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file added .DS_Store
Binary file not shown.
Binary file added source/.DS_Store
Binary file not shown.
Binary file added source/includes/.DS_Store
Binary file not shown.
Binary file modified source/includes/images/.DS_Store
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
1 change: 1 addition & 0 deletions source/includes/images/industry-solutions/sol_lib_doc.svg

Large diffs are not rendered by default.

113 changes: 106 additions & 7 deletions source/solutions-library.txt
Original file line number Diff line number Diff line change
Expand Up @@ -40,16 +40,115 @@ kick-start their projects.

Use native stream processing and Vector Search in MongoDB Atlas to
continuously update, store, and search embeddings through a unified
interface.
interface.

.. Fraud Prevention
.. ----------------
.. card::
:headline: Credit Card Application with Generative AI
:url: /solutions-library/credit-card-application-with-generative-ai/
:icon: industry_credit_card
:icon-alt: Atlas industry_credit_card icon

Learn how the convergence of alternative data, artificial intelligence, and
generative AI is reshaping the foundations of credit scoring.

.. card::
:headline: Assessing Business Loan Risks with Generative AI
:url: /solutions-library/assessing-business-loan-risks-with-generative-ai/
:icon: industry_finance
:icon-alt: Atlas industry_finance icon

Learn how generative AI can generate detailed risk assessments and how
MongoDB’s multimodal features enable comprehensive and multidimensional loan risk
analysis.

.. card::
:headline: AI-Driven Interactive Banking
:url: /solutions-library/ai-driven-interactive-banking/
:icon: industry_enterprise
:icon-alt: Atlas industry_enterprise icon

Build an application using MongoDB Atlas Vector Search and large language
models to improve the interactivity of banking applications.

Fraud Prevention
----------------

.. card-group::
:columns: 2
:style: extra-compact

.. card::
:headline: Fraud Detection Accelerator Using AWS SageMaker
:url: /solutions-library/fraud-detection-accelerator/
:icon: general_security
:icon-alt: Atlas general_security icon

Revolutionize fraud detection in finance with MongoDB Atlas and Amazon
SageMaker Canvas. Leverage real-time data and AI for stronger defenses against
cybercrime.

.. card::
:headline: Card Fraud Solution Accelerator
:url: /solutions-library/card-fraud-solution/
:icon: industry_credit_card
:icon-alt: Atlas industry_credit_card icon

Real-time AI/ML fraud detection for Financial Services using MongoDB and
Databricks. Ensure data completeness and instant fraud analysis.

.. card::
:headline: Vector Search Fraud Prevention Accelerator
:url: /solutions-library/vector-search-fraud-prevention/
:icon: mdb_vector_search
:icon-alt: Atlas mdb_vector_search icon

Combine real-time analytics with semantic search by integrating MongoDB Atlas
Vector Search with OpenAI-generated embeddings to detect fraud that
traditional methods miss.

App-Driven Analytics
--------------------

.. card-group::
:columns: 2
:style: extra-compact

.. card::
:headline: MongoDB as the Open Finance Data Store
:url: /solutions-library/open-finance-data-store/
:icon: industry_finance
:icon-alt: Atlas industry_finance icon

MongoDB powers open finance with flexible data integration, built-in security,
and scalability—enabling seamless, compliant, and personalized financial
services.

.. card::
:headline: MongoDB and Hasura for Modern Fintech Services
:url: /solutions-library/hasura-fintech-services/
:icon: industry_ai
:icon-alt: Atlas industry_ai icon

Leverage agentic RAG using MongoDB and Dataworkz to enhance customers’
shopping experiences with a personalized chatbot.

Modernization
-------------

.. card-group::
:columns: 2
:style: extra-compact

.. card::
:headline: Payments Modernization Solution Accelerator
:url: /solutions-library/payments-solution/
:icon: industry_credit_card
:icon-alt: Atlas industry_credit_card icon

Learn how to build an operational data layer (ODL) to unlock siloed payment
data and power modern applications.

.. App-Driven Analytics
.. --------------------

.. Modernization
.. -------------

.. tab:: Manufacturing & Motion
:tabid: manufacturing
Expand Down
179 changes: 179 additions & 0 deletions source/solutions-library/ai-driven-interactive-banking.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,179 @@
.. _arch-center-is-interactive-banking:

==========================================
AI-Driven Interactive Banking
==========================================

.. meta::
:keywords: AI, Generative AI, Interactive Banking, Chatbots, MongoDB Atlas, Vector Search, Large Language Models, Financial Services, Personalization.
:description: Build an application using MongoDB Atlas Vector Search and large language models to improve the interactivity of banking applications.

.. contents:: On this page
:local:
:backlinks: none
:depth: 1
:class: singlecol

- **Use cases**: `Gen AI <https://www.mongodb.com/solutions/use-cases/artificial-intelligence>`_,
`Personalization <https://www.mongodb.com/solutions/use-cases/personalization>`_
- **Industries**: `Financial Services <https://www.mongodb.com/solutions/industries/financial-services>`_
- **Partners**: `Amazon Bedrock <https://aws.amazon.com/bedrock>`_



Solution Overview
-----------------

Interactive banking represents a new era in financial services where customers engage with
digital platforms that anticipate, understand, and meet their needs in real time.

This approach uses generative artificial intelligence (gen AI) technologies like chatbots
and virtual assistants to enhance basic day-to-day banking operations. By leveraging gen
AI, banks can enable self-service digital channels while simultaneously elevating the
customer experience through tailored, context-aware interactions. From AI-powered chatbots
that resolve queries instantly to predictive analytics that offer tailored financial
advice, interactive banking is no longer just about convenience—it’s about creating a
smarter, more engaging and more intuitive banking journey for every user.

By integrating AI-driven advisors into the digital banking experience, banks can provide a
seamless, in-app solution that delivers instant, relevant answers. This removes the need
for customers to leave the app to sift through pages of bank documentation in search of
answers, or worse, endure the inconvenience of calling customer service. The result is a
smoother and more user-friendly interaction, where customers feel supported in their
self-service journey, free from the frustration of navigating traditional, cumbersome
information sources. The entire experience remains within the digital space, enhancing
convenience and efficiency.

.. video:: https://www.youtube.com/watch?v=Pn0IOrn3TKI

Reference Architecture
-----------------------

The problem with traditional terms and conditions is that they are dense, unstructured,
and not easily usable within digital banking environments. To remedy this MongoDB and its
partner propose the following reference architecture:


.. figure:: /includes/images/industry-solutions/leafy-bank-in-aws.svg
:width: 750px
:alt: Reference architecture for AI-driven interactive banking proposal.

MongoDB is positioned as an operational data store (ODS) acting as a medium layer between
the AI technologies and the application layer, which allows organizations to operate with
a more unified dataset. This unification streamlines data management, ensuring that
structured, semi-structured, and unstructured data can coexist, enabling faster
development cycles and more accurate AI-driven insights. By breaking down data silos,
businesses can deliver richer, more consistent customer experiences across their digital
platforms.

Data Model Approach
-------------------

We store both the text chunks from the PDF and their embeddings directly within the same
document in our MongoDB collection. This streamlined approach, illustrated in the image
below, enables efficient and unified data access.

By using MongoDB’s flexible and scalable document model, we can store text and vector
embeddings together, simplifying queries and ensuring high performance without bolting on
additional solutions. This approach allows companies to build AI-enriched applications on
MongoDB’s modern, multi-cloud database platform, unifying real-time, operational,
unstructured, and AI-driven data. With this foundation, businesses can efficiently adapt,
extend, and iterate their applications to seize emerging technological opportunities.

.. figure:: /includes/images/industry-solutions/sol_lib_doc.svg
:width: 750px
:alt: View of chunk and embedding structure in MongoDB

Building the Solution
---------------------

1. Document Preprocessing and Chunking
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

The initial step involves processing and transforming the text-based unstructured data
(such as the Terms & Conditions PDF), that will serve as the source for answering customer
queries.

The document is divided into `N chunks
<https://www.mongodb.com/developer/products/atlas/choosing-chunking-strategy-rag/>`_,
which are stored in |service-fullname|. A custom script scans the document, creates the chunks,
and vectorizes them (as illustrated in the figure below). The chunking process uses a
sliding window technique, ensuring that transitional data between chunks is preserved
while maintaining continuity and context.

Once the document has been transformed into vectorized chunks, they are passed through an
embedding model to generate vector embeddings. The embedding model can be selected
according to the user's requirements. For illustration purposes, we are using Cohere
'cohere.embed-english-v3' on AWS Bedrock for the embedding creation.

Both the chunks and their corresponding vectors are stored in |service-fullname|. In this
sample scenario, we are using `SuperDuper <https://superduper.io/>`_ (an open-source
Python framework that integrates AI models and workflows directly with MongoDB) as the
process orchestrator, enabling more flexible and scalable custom enterprise AI solutions.

2. Vector Search and Querying
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

After we’ve stored both the chunks and their embeddings in MongoDB, we can begin
leveraging `MongoDB Atlas Vector Search
<https://www.mongodb.com/products/platform/atlas-vector-search#query>`_ for semantic
querying.

3. Building the Chatbot UI
~~~~~~~~~~~~~~~~~~~~~~~~~~~

The next step involves building an application—in our case, an interactive chatbot. This
chatbot is powered by MongoDB Atlas Vector Search and a pre-trained |llm|. When a user
inputs a question, that question is first vectorized, and MongoDB Atlas Vector Search is
used to find documents with similar embeddings.

Once relevant documents are retrieved, the next step is to send this data to an LLM. In
this case, we use Amazon Bedrock as the `LLM
<https://www.mongodb.com/resources/basics/artificial-intelligence/large-language-models>`_
container. For this specific use case, we are leveraging Claude from Anthropic. The LLM
receives both the question and the retrieved documents, using the documents as context to
generate a more comprehensive and accurate response. This framework is known as
`retrieval-augmented generation
<https://www.mongodb.com/resources/basics/artificial-intelligence/retrieval-augmented-generation>`_
(|rag|) architecture. RAG enhances the chatbot’s ability to provide accurate answers by
combining semantic search with powerful language model generation.

.. figure:: /includes/images/industry-solutions/chatbot.gif
:width: 750px
:alt: Leafy Bank mock-up chatbot in action

Key Learnings
-------------

- AI-driven technologies like chatbots simplify customer interactions by providing
instant, context-aware responses, allowing users to navigate banking operations
independently without wading through complex terms and conditions.
- By `using Atlas Vector Search
<https://www.mongodb.com/products/platform/atlas-vector-search>`_
and document chunking, MongoDB enables efficient querying of dense legal documents,
ensuring customers receive accurate, context-rich answers.
- MongoDB's integration with vector search, LLMs, and dedicated search infrastructure
allows financial institutions to scale AI solutions, improving performance and
responsiveness as customer demands grow.

Technologies and Products Used
------------------------------

MongoDB Developer Data Platform:
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

- `Atlas Database <https://www.mongodb.com/products/platform/atlas-database>`_
- `Atlas Vector Search <https://www.mongodb.com/products/platform/atlas-vector-search>`_

Partner Technologies:
~~~~~~~~~~~~~~~~~~~~~

- `Amazon Bedrock <https://aws.amazon.com/bedrock>`_

Authors
-------

- Luis Pazmino Diaz, FSI Principal EMEA, MongoDB
- Ainhoa Múgica, Senior Specialist, Industry Solutions, MongoDB
- Pedro Bereilh, Specialist, Industry Solutions, MongoDB
- Andrea Alaman Calderon, Senior Specialist, Industry Solutions, MongoDB
Loading