Frequently asked business questions
Prepare questions and answers about opening hours, services or policies. Active FAQs form part of the context available to the assistant.
Knowledge base for context-aware answers
WhatsApp RAG chatbot: answer with your business knowledge
Prepare FAQs, documents and web pages for your assistant. Organise them into collections and define which knowledge each automation profile can use. ChatCol combines the available FAQs with related document passages before generating an answer.
- Frequently asked questions
- PDF and TXT files
- Web pages and sitemaps
- Knowledge collections
Answers connected to your business information
FAQs provide the answers you prepare for your business. RAG retrieves passages from your documents and pages, while collections organise which sources are available to each profile.
Documents and web pages
Upload PDF or TXT files, index a public HTTPS page or use a compatible sitemap to bring in several sources.
Knowledge organised into collections
Group FAQs and documents by topic, service or department. You can choose which collections each automation profile uses.
Related information retrieval
When a question arrives, RAG searches the available documents for relevant passages and adds them to the answer context.
Step-by-step preparation
How to prepare a RAG knowledge base for your chatbot
Answer quality depends on clear, current and consistent sources. Start with a small set and test real questions before expanding it.
Prepare questions and sources
Gather FAQs, policies, product sheets and instructions that are current and do not contradict one another.
Add and index the content
Create FAQs and add files or URLs from Intelligence. Wait for document indexing to finish before testing them.
Organise the collections
Group related FAQs and documents, then select the knowledge available to each automation profile.
Test real questions
Try common cases, review whether retrieved information is sufficient and adjust sources or instructions when necessary.
Prepare clear sources and keep them current
Start with information you can review and maintain. These limits help you choose the files and pages that will become part of the knowledge base.
- Accepts one PDF or TXT file up to 10 MB per upload and rejects empty or incompatible files.
- Can index one public HTTPS page or attempt the first 15 entries in an XML sitemap; each URL must pass HTTPS validation.
- Finds related passages in documents from the collections available to the conversation.
- Combines FAQs and document context with your instructions. Review answers and update sources when your business changes.
Business information that fits a RAG knowledge base
Choose content with concrete answers that can be kept current. Sensitive or ambiguous questions should retain a route to a person.
Policies and customer service
Answer questions about exchanges, conditions, coverage or processes using the policies you have indexed.
Product catalogue and documentation
Help people find features, compatibility details or instructions from technical sheets and help pages.
Procedures and frequently asked questions
Reuse approved guides and answers to help contacts and hand over to the team when the content is insufficient.
WhatsApp RAG chatbot questions
Answers about sources, retrieval and the limits of a knowledge base connected to AI.
What does RAG mean in a chatbot?
RAG combines retrieval and generation. Before drafting an answer, the system searches indexed content for related passages and adds them to the context given to the AI model.
Which files can I add to the knowledge base?
ChatCol's current implementation accepts PDF and TXT files up to 10 MB. You can also index public HTTPS pages and compatible XML sitemaps.
What are knowledge collections for?
They group FAQs and documents by topic, service or department. You can configure automation profiles to use global knowledge or selected collections, defining which sources are available when preparing an answer.
Do documents update automatically when a source changes?
Not currently. The knowledge base reflects content captured during indexing. If a policy, file or page changes, delete the old source and index its current version again.
Does RAG guarantee that AI will never be wrong?
No. RAG supplies relevant context and reduces reliance on general knowledge, but it does not guarantee perfect answers. Test real questions, keep sources current and route sensitive or insufficient cases to a person.
What do I need to use these answers on WhatsApp?
You need to connect a compatible WhatsApp Business Platform channel and meet Meta's applicable requirements. Conversation windows and approved-template requirements still apply when relevant.