Build a RAG chatbot
Use case: Build a RAG chatbot that cites your own documentation
Retrieval-augmented generation lets a chat model answer questions from your documentation instead of guessing from whatever it happened to see during training. Webanto's inference API gives you both halves of the pipeline: POST /api/v1/embeddings (model nomic-embed-text) turns your docs into vectors for retrieval, and POST /api/v1/chat (model qwen, a self-hosted 35B multimodal model) turns the retrieved passages into a grounded answer with a citation back to the source page. Webanto does not store or index the vectors for you — you keep them in pgvector, Pinecone, or whatever store you already run, and re-embed the user's question at query time to find the nearest chunks. Answer quality tracks your chunking and retrieval choices far more than the chat model itself, so budget real time for both instead of assuming the model alone determines quality.
What to expect
Answers grounded in your own documentation, with the source page cited alongside each response.
Consistent answers to the same underlying question regardless of how it's phrased, because retrieval matches on meaning rather than exact keywords.
A support team that can point users at a doc update instead of manually rewriting the same answer every time a question repeats.
A visible audit trail — which chunks were retrieved for a given answer — that makes wrong answers debuggable instead of treating the whole system as a black box.
How to set this up
- 1
Split your documentation into chunks — roughly 300-800 tokens each with some overlap, splitting on headings or sections so every chunk stays self-contained.
- 2
Call POST /api/v1/embeddings with model "nomic-embed-text" for every chunk. 20,000 chunks ÷ 100 per credit = 200 credits, comfortably inside a Growth plan's 50,000 monthly credits.
- 3
Store each returned vector alongside its chunk text and source URL in your own vector store (pgvector, Pinecone, etc.) — Webanto returns vectors only, it does not host an index for you.
- 4
At query time, embed the visitor's question with the same nomic-embed-text call and run a nearest-neighbour search against your store to pull the top 5-8 matching chunks.
- 5
Assemble a prompt with the retrieved chunks plus the question and send it to POST /api/v1/chat with model "qwen", instructing it to answer only from the supplied context and cite the source URL for each claim.
- 6
Chat billing runs on tokens: a typical RAG turn (context plus question plus answer) lands around 800-1,500 tokens, so roughly 1.5-3 turns per credit at 2,000 tokens per credit.
- 7
Test with questions you already know the answer to, check the cited sources actually match the claim, and tighten the 'answer only from context' instruction if the model starts drifting into unsupported claims.
Products that power this use case
Frequently asked questions
Can the chatbot hallucinate even with retrieval in place?
Yes — RAG reduces hallucination but does not eliminate it. If retrieval pulls an irrelevant chunk, or the question has no good match in your docs, Qwen can still generate a fluent but wrong answer. Explicitly instruct it to say 'not found in the documentation' when the retrieved context doesn't cover the question, and test that instruction under adversarial phrasing before trusting it in production.
Does Webanto store or index my documentation?
No. POST /api/v1/embeddings returns a vector for whatever text you send, and Webanto does not retain a queryable copy of it. You're responsible for storing the vectors and running similarity search yourself, in pgvector, Pinecone, Weaviate, or any store you prefer.
How much does chunking strategy actually matter?
More than most people expect. Chunks that are too large dilute the embedding with unrelated content and retrieval gets fuzzy; chunks that are too small lose context and the chat model can't answer fully from them. Splitting on natural document boundaries and keeping overlap between adjacent chunks usually beats fixed-length splitting.
Can Qwen handle screenshots or diagrams from the docs?
Yes, Qwen is multimodal and accepts images directly in the chat call, so you can pass a relevant diagram alongside the retrieved text chunks when it's likely to help the answer. That doesn't replace embedding the text itself, though — image content still needs to be described or embedded separately before retrieval can find it.
How many credits does re-embedding cost every time content changes?
The same rate as the first pass — 100 chunks per credit — but you only need to re-embed the chunks that actually changed, not the whole set, if you track a content hash per chunk and skip the ones that are unchanged.
Other use cases
Let shoppers search your catalogue with a photo
Shoppers who spot a product in the wild, on someone else's feed, or on a competitor's site rarely know the right keywords to find it in your catalogue. Visual search closes that gap: a shopper uploads
Find near-duplicate images in a large media library
Large media libraries accumulate redundancy fast — the same product shot re-exported at a different crop, a stock photo uploaded twice under different filenames, a banner re-saved at a lower compressi
Reverse image search against your own image library
Reverse image search answers a narrower question than catalogue browsing: given one photo someone just handed you — a screenshot, a competitor's product shot, a customer's snapshot of a damaged item —
Related resources
Data Synchronization
ServiceWebanto vs HubSpot: which marketing platform fits your business?
ComparisonHubSpot is the dominant all-in-one CRM and marketing platform — sales, marketing, service, CMS, operations — built for mid-market and enterprise B2B teams. Webanto is a focused multi-channel marketing platform — email, social, content — without CRM, sales, or service modules, priced for small and mid-sized teams. HubSpot is the better choice if you need integrated sales and service alongside marketing and have a budget for it. Webanto is the better choice if you want best-in-class email, social, and content tools without paying for an enterprise CRM you do not use.
AI-Powered Web Design: Transforming Digital Experiences
Blog🚀 Transform your website with AI-powered design! Elevate digital experiences effortlessly! 🌐✨
Creating a Comprehensive Web Design Strategy
BlogA solid web design strategy stands as the backbone of any successful online presence. It encompasses more than just aesthetics, focusing on functionality, user experience, SEO integration, and alignment with a brand’s goals. A comprehensive approach ensures that a website not only attracts visitors but also holds their attention, guiding them toward taking desired actions such as making purchases, signing up for newsletters, or requesting services.
Webanto for real estate: lead nurture, listings, and local presence
IndustryReal estate businesses live on lead nurture cycles measured in months, listing pages that must rank locally, and a content engine that keeps agents visible to past clients. Webanto pulls long-cycle drip sequences for buyers and sellers, multi-location office pages, agent bio pages with structured data, and listing-promotion social calendars under one platform — without forcing real estate operators into the CRM-bundled marketing tools whose features sit behind paywalls or feature gates.
Webanto vs ActiveCampaign: which marketing automation platform fits you?
ComparisonWebanto and ActiveCampaign both center on marketing automation, but they solve different problems. ActiveCampaign is an automation-and-CRM heavyweight — its visual automation builder, lead scoring, and sales pipelines are among the deepest in the category, and it integrates with over 900 apps. That depth comes with contact-tiered pricing that climbs as your list grows and a learning curve most small teams feel. Webanto takes a flatter path: one predictable per-plan price, unlimited sends on every paid plan, native Shopify and WooCommerce sync in the base plan, and a shared contact, automation, and analytics model spanning email, social, and content. ActiveCampaign is the stronger choice if automation sophistication and a built-in CRM are your priority. Webanto is the better choice if you want dependable automation, native store data, and unified marketing without contact-based price jumps.
Ready to try it?
Start a 14-day free trial on any paid plan. Cancel before it ends and you won't be charged.

