Your client writes via Viber — a standard scenario for e-commerce in the CIS. Manual support of 1000+ dialogues a day eats the budget and reduces conversion: the average operator response time is 4 minutes, while a bot processes a request in 2 seconds. Developing an AI chatbot with NLP and integration through the Viber API turns the messenger into an automated sales and support channel 24/7. We use a production-ready stack: from GPT-4o to locally deployed models via vLLM with INT8 quantization to reduce latency p99 to 1.5 seconds. In one project, the conversion to order increased by 18% after implementing a product carousel — Rich Media allows selecting products right in the chat.
What tasks an AI bot for Viber solves
Inbound processing with NLP. The bot understands natural language, distinguishes a complaint from a delivery question, and switches to an operator on escalation. With few-shot prompts, classification accuracy reaches 92–95% within the first weeks of operation. Additionally, we configure intent detection with a threshold of 0.85 — if confidence is lower, the dialogue is handed over to a human.
Rich Media and catalogs. Viber supports cards with buttons and images. For online stores, this means: the user selects a product right in the chat — without going to the website. We implement dynamic rich_media responses based on data from your CRM.
How the AI model processes dialogues in real time?
After registering the bot through the Viber Partner Program, we configure a webhook to an HTTPS endpoint. All incoming messages go into a queue (via Redis), then are passed to a LangChain agent with dialogue history. A model router decides: answer from FAQ (RAG) or pass to the LLM. The average response delay is 1.5–3 seconds, which fits within messenger UX expectations. For critical scenarios, we use chain-of-thought prompts with 5-shot examples.
LangChain is more efficient than pure REST requests: it provides calls to external tools (database search, order status check) and context management. In our tests, this approach reduces false positives by 30% compared to direct API calls to the model.
How to choose an LLM for a Viber bot?
Choosing a model is a trade-off between quality and speed. The table compares popular options.
| Model | Latency (p99) | Quality (GPT-4 benchmark) | Token Cost | Deployment |
|---|---|---|---|---|
| GPT-4o | 1.2 sec | Baseline | High | OpenAI API |
| LLaMA 3 70B (INT8) | 2.0 sec | 92% | Medium | Local via vLLM |
| Mistral 7B | 0.8 sec | 85% | Low | Local via TGI |
| Gemini 1.5 Pro | 1.5 sec | 90% | Medium | Vertex AI |
For simple FAQs, Mistral 7B is enough. If you need RAG with deep reasoning, LLaMA 3 70B in INT8 provides balance. For maximum quality, we stick with GPT-4o, but with caching of frequent requests.
Comparison of RAG and fine-tuning
| Approach | When to use | Complexity | Updateability |
|---|---|---|---|
| RAG | Knowledge base changes frequently, large volume of documents | Low (no retraining) | Instant upon index update |
| Fine-tuning | Fixed response style, specialized terminology | High (requires labeled data) | Requires model retraining |
Development process: from analysis to deployment
- Analysis. We collect typical scenarios, define metrics (CSAT, FCR, conversion to order). We analyze 2–3 months of support logs.
- Design. We choose the LLM, vector DB (Qdrant), design dialogue graphs. We define the fallback strategy to a human operator.
- Implementation. We write a webhook handler in Python (FastAPI), integrate the Viber API, connect the RAG pipeline with chunk size 512 tokens.
- NLP testing. We run 200+ test dialogues, measure accuracy, latency p99, hallucination rate. We tune temperature (0.1–0.3) and top-p.
- Deployment and monitoring. We deploy on Kubernetes (SageMaker or Vertex AI), set up logging via MLflow and alerts in Grafana. We establish an SLA of 99.9%.
Typical mistakes when integrating an AI bot for Viber
- Ignoring the Viber message length limit (1000 characters for text).
- Missing webhook error handling (timeout, retries).
- Incorrect session variable setup for long dialogues.
- Using too small a context window (recommend at least 4096 tokens).
What is included in the result
- Documentation on the architecture and API of all components.
- Access to the admin panel for managing scenarios and viewing dialogue logs.
- Operation manual for the business customer.
- 2 weeks of post-launch support (bug fixes, prompt adjustments).
- Certified ML engineers ensure monitoring and model fine-tuning on your data.
Why trust the integration to our team
7+ years of experience developing AI solutions for messengers and web channels. 50+ successful integrations with Viber, Telegram, and WhatsApp. We guarantee migration to your model (LLaMA, Mistral) without quality loss. Every project undergoes MLOps audit — we don't deploy black boxes into production.
Contact us for a consultation — we will select the architecture for your budget and timeline. Get a project estimate: an engineer will analyze your scenarios and propose the optimal solution. Order a prototype of an AI bot for Viber today — just write to us.