Integrated Chat-Bot Based on NLP and GPT
INDUSTRY
Communication
SERVICE
Messenger
A smart, adaptable chat-bot for any messenger
"By combining NLP and GPT capabilities, Waverley created a chat-bot that understands users naturally, works with any data source, and can be integrated into any messenger platform."
Waverley developed a generic AI-powered chat-bot that can be integrated into any messenger application and adapted to specific business needs.
Using GoLang and Python microservices, the system collects and processes information from various data sources — turning it into searchable vector embeddings for fast, accurate responses — all while maintaining privacy and cost efficiency.
Messenger
The product is a generic chat-bot that can be integrated into any messenger application and adapted to specific business needs. Its main function is to provide answers to users’ questions, recognising their intention and reaction to the provided answers.
The bot can work with any data storage, websites, or documents as its source of information. For example, it can be connected to an online shop’s database to assist buyers, or to a company’s file drive to answer employees’ questions about internal policies and guidelines.
Waverley Solution (Architecture)
Waverley designed a modular, scalable architecture for the chat-bot, enabling it to work with any data source and any messenger interface.
The system combines GoLang and Python microservices with OpenAI and open-source ML models (Llama, Llama 2, GPT4All), balancing cloud AI capabilities with locally-run models for privacy-sensitive deployments.
Data Collection & Embeddings
The chat-bot consists of data collectors and pipelines — microservices in GoLang and Python — that collect information from databases, files, and websites, then process it into a required format.
Large documents are split into digestible chunks using ML techniques. Each chunk is transformed into embeddings — numeric vectors stored in a vector database (Redis) — enabling fast Vector Similarity Search.
Chat-Bot Engine
Defining the Context — When a user interacts with the chat-bot, their input is processed by the ML model and transformed into a numeric vector. Vector similarity search finds the most relevant documents, defining the context for OpenAI's natural language response.
Caching — A cache vector database stores prior responses. Similar user queries are matched without sending new requests to OpenAI, reducing costs.
Interface — A GoLang API Gateway provides WebSocket (messengers), REST (web), and gRPC (mobile) interfaces with local cache and audit logs.
Intent classification understands what users want; sentiment analysis detects satisfaction and redirects to operators when needed.
ML Models & Hosting
The product combines OpenAI's algorithms with open-source models (Llama, Llama 2, GPT4All) for scraping, processing, and classification before feeding to OpenAI.
Cuts costs on OpenAI resource usage
Keeps private data on local servers, ensuring compliance
Enables operation in regions where ChatGPT is blocked
Due to ML compute requirements, the system requires cloud hosting or a powerful local server.
Feature Development
The chat-bot provides the following functionality:
Recognise the intention of a user
Identify the context of interaction
Answer specific questions from available data sources
Summarise requested documents, webpages, etc.
Provide a reference to the source of information
Translate text
Generate text (emails, posts, etc.) following user instructions
Integrate with third-party systems (e.g. Jira) for business automation
Privacy Protection
The mechanism allows manual classification of information as confidential or non-confidential — filtering out business-critical data before it reaches OpenAI.
For internal deployments, responses are also filtered based on user roles and access levels. Waverley’s solution provides a significant advantage for businesses restricted from using OpenAI’s ChatGPT due to privacy regulations.
A cost-efficient, privacy-first AI system
Waverley delivered a generic chat-bot system that relies on OpenAI’s resources while also functioning autonomously using locally run ML models. This provides additional information security to business owners and allows them to meet rigid privacy regulations.
The system can be adapted to a variety of business needs and, compared to OpenAI’s solution, offers more control over confidentiality settings and is more cost-efficient.
Let's Build Something Great.
Tell us about your project — we'll find the right path forward.