Document AI with Apache Airflow

Summary

In this post, I cover an approach to a document AI problem using a task flow implemented in Apache Airflow.  The particular problem is around the de-duplication of invoices.  This comes up in payment provider space.  I use Azure AI Document Intelligence for OCR, Azure OpenAI for vector embeddings, and Redis Enterprise for vector search.

Architecture

Code Snippets

File Sensor DAG

OCR DAG

OCR Client (Azure AI Doc Intelligence)

Embedding DAG

Embedding Client (Azure OpenAI)

Vector Search DAG

Vector Search Client (Redis Enterprise)

Source

https://github.com/Redislabs-Solution-Architects/docai_pipeline

Copyright ©1993-2024 Joey E Whelan, All rights reserved.

HAProxy with Redis Enterprise

Summary

This is Part 2 of a two-part series on the implementation of a contact center ACD using Redis data structures.  This part is focused on the network configuration.  In particular, I explain the configuration of HAProxy load balancing with VRRP redundancy in a Redis Enterprise environment.  To boot, I explain some of the complexities of doing this inside a Docker container environment.

• Part 1:  Basic ACD with Redis Enterprise
• Part 2:  HAProxy with Redis Enterprise

Network Architecture

Load Balancing Configuration

HAProxy w/Keepalived

Docker Container

Dockerfile and associated Docker compose script below for two instances of HAProxy w/keepalived.  Note the default start-up for the HAProxy container is overridden with a CMD to start keepalived and haproxy.

Keepalived Config

VRRP redundancy of the two HAProxy instances is implemented with keepalived.  Below is the config for the Master instance.  The Backup instance is identical except for the priority.

Web Servers

I'll start with the simplest load-balancing scenario - web farm.

Docker Container

Below is the Dockerfile and associated Docker compose scripting for a 2-server deployment of Python FastAPI.  Note that no IP addresses are assigned and multiple instances are deployed via Docker compose 'replicas'.

HAProxy Config

Below are the front and backend configurations.  Note the use of Docker's DNS server to enable dynamic mapping of the web servers via a HAProxy server template.

Redis Enterprise Components

Redis Enterprise can provide its own load balancing via internal DNS servers.  For those that do not want to use DNS, external load balancing is also supported.  Official Redis documentation on the general configuration of external load balancing is here.  I'm going to go into detail on the specifics of setting this up with the HAProxy load balancer in a Docker environment.

Docker Containers

A three-node cluster is provisioned below.  Note the ports that are opened:

• 8443 - Redis Enterprise Admin Console
• 9443 - Redis Enterprise REST API
• 12000 - The client port configured for the database.

RE Database Configuration

Below is a JSON config that can be used via the RE REST API to create a Redis database.  Note the proxy policy.  "all-nodes" enables a database client connection point on all the Redis nodes.

RE Cluster Configuration

In the start.sh script, this command below is added to configure redirects in the Cluster (per the Redis documentation).

HAProxy Config - RE Admin Console

Redis Enterprise has a web interface for configuration and monitoring (TLS, port 8443).  I configure back-to-back TLS sessions below with a local SSL cert for the front end.  Additionally, I configure 'sticky' sessions via cookies.

HAProxy Config - RE REST API

Redis Enterprise provides a REST API for programmatic configuration and provisioning (TLS, port 9443).  For this scenario, I simply pass the TLS sessions through HAProxy via TCP.

HAProxy Config - RE Database

A Redis Enterprise database can have a configurable client connection port.  In this case, I've configured it to 12000 (TCP).  Note in the backend configuration I've set up a Layer 7 health check that will attempt to create an authenticated Redis client connection, send a Redis PING, and then close that connection.

Source

https://github.com/redis-developer/basic-acd

Copyright ©1993-2024 Joey E Whelan, All rights reserved.

Basic ACD with Redis Enterprise

Summary

This post covers a contact ACD implementation I've done utilizing Redis data structures.  The applications are written in Python.  The client interface is implemented as REST API via FastAPI.  An internal Python app (Dispatcher) is used to monitor and administer the ACD data structures in Redis.  Docker containers are used for architectural components.

• Part 1:  Basic ACD with Redis Enterprise
• Part 2:  HAProxy with Redis Enterprise

Application Architecture

Data Structures

Contact, Queue

Contacts are implemented as Redis JSON objects.  Each contact has an associated array of skills necessary to service that contact.  Example:  English language proficiency.

A single queue for all contacts is implemented as a Redis Sorted Set.  The members of the set are the Redis key names of the contacts.  The associated scores are millisecond timestamps of the time the contact entered the queue.  This allows for FIFO queue management  

Agent

Agents are implemented as Redis JSON objects.  Agent meta-data is stored as simple properties.  Agent skills are maintained as arrays.  The redis-py implementation of Redlock is used to ensure mutual exclusion to agent objects.

Agent Availability

Redis Sorted Sets are also used to track Agent availability.  A sorted set is created per skill.  The members of that set are the Redis keys for the agents that are available with the associated skill.  The associated scores are millisecond timestamps of the time the agent became available.  This use of sorted sets allows for multi-skill routing to the longest available agent (LAA).

Operations

Agent Targeting 

Routing of contacts to agents is performed by multiple Dispatcher processes.  Each Dispatcher is running an infinite loop that does the following:

• Pop the oldest contact from the queue
• Perform an intersection of the availability sets for the skills necessary for that contact
• If there are agent(s) available, assign that agent to this contact and set the agent to unavailable.
• If there are no agents available with the necessary skills, put the contact back in the queue

Source

https://github.com/Redislabs-Solution-Architects/basic-acd

DICOM Image Caching with Redis

 Summary

This post covers a demonstration of the usage of Redis for caching DICOM imagery.  I use a Jupyter Notebook to step through loading and searching DICOM images in a Redis Enterprise environment.

Architecture

Redis Enterprise Environment

Screen-shot below of the resulting environment in Docker.

Sample DICOM Image

I use a portion of sample images included with the Pydicom lib.  Below is an example:

Code Snippets

Data Load

The code below loops through the Pydicom-included DICOM files.  Those that contain the meta-data that is going to be subsequently used for some search scenarios are broken up into 5 KB chunks and stored as Redis Strings.  Those chunks and the meta-data are then saved to a Redis JSON object.  The chunks' Redis key names are stored as an array in that JSON object.

Search Scenario 1

This code retrieves all the byte chunks for a DICOM image where the Redis key is known.  Strictly, speaking this isn't a 'search'.  I'm simply performing a JSON GET for a key name.

Search Scenario 2

The code below demonstrates how to put together a Redis Search on the image meta-data.  In this case, we're looking for a DICOM image with a protocolName of 194 and studyDate in 2019.

Source

https://github.com/Redislabs-Solution-Architects/redis-dicom

Copyright ©1993-2024 Joey E Whelan, All rights reserved.

Redis Vector Database Sizing Tool

Summary

In this post, I cover a utility I wrote for observing Redis vector data and index sizes with varying data types and index parameters.  The tool creates a single-node, single-shard Redis Enterprise database with the Search and JSON modules enabled.

Code Snippets

Constants and Enums

Redis Index Build and Data Load

Sample Results

Source

https://github.com/Redislabs-Solution-Architects/vss-sizer

Copyright ©1993-2024 Joey E Whelan, All rights reserved.

Redis Search - Rental Availability

Summary

This post covers a very specific use case of Redis in the short-term rental domain.  Specifically, Redis is used to find property availability in a given geographic area and date/time slot.

Architecture

Code Snippets

Data Load

The code below loads rental properties as Redis JSON objects and US Postal ZIP codes with their associated lat/longs as Redis strings.

Property Search

The code below represents an Expressjs route for performing searches on the Redis properties.  The search is performed on rental property type and geographic distance from a given location.

Source

https://github.com/Redislabs-Solution-Architects/rental-availability

Copyright ©1993-2024 Joey E Whelan, All rights reserved.

OpenAI Q&A using Redis VSS for Context

Summary

I'll be covering the use case of providing supplemental context to OpenAI in a question/answer scenario (ChatGPT).  Various news articles will be vectorized and stored in Redis.  For a given question that lies outside of ChatGPT's knowledge, additional context will be fetched from Redis via Vector Similarity Search (VSS).   That context will aid ChatGPT in providing a more accurate answer.

Architecture

Code Snippets

OpenAI Prompt/Collect Helper Function

The code below is a simple function for sending a prompt into ChatGPT and then extracting the resulting response.

OpenAI QnA Example 1

The prompt below is on a topic (FTX meltdown) that is outside of ChatGPT's training cut-off date. As a result, the response is of poor quality (wrong).

Redis Context Index Build

The code below uses Redis-py client lib to build an index for business article content in Redis. The index has two fields in its schema: the text content itself and a vector representing the embedding of that text content.

Context Storage as Redis JSON

The code below loads up a dozen different business articles into Redis as JSON objects.

RedisInsight

Redis Vector Search (KNN)

A vector search in Redis is depicted below. This particular query picks the #1 article as far as vector distance to a given question (prompt).

Reprompt ChatGPT with Redis-fetched Context

The context fetched in the previous step is now added as supplemental info to ChatGPT for the same FTX-related question. The response is now in line with expectations.

Source

https://github.com/openai/openai-cookbook/tree/main/examples/vector_databases/redis/redisqna

Copyright ©1993-2024 Joey E Whelan, All rights reserved.