### Answer For a 1,000 SKU product catalog in a single knowledge base, you have three main options for adding content [(1) ]() [(2) ]() : 1. Upload Documents Upload your catalog as files (PDF, TXT, DOCX supported) [(2) ]() . You can upload up to 25 files, where each file is limited to 50MB [(1) ]() . 2. Add via API with knowledge_base_texts Use the Create Knowledge Base API with the

knowledge_base_texts

parameter :

javascript
const knowledgeBaseResponse = await client.knowledgeBase.create({
  knowledge_base_name: "Sample KB",
  knowledge_base_texts: [
    {
      text: "Hello, how are you?",
      title: "Sample Question",
    },
  ],
}) ;

3. Scrape from Webpages If your catalog is online, provide URLs and Retell will scrape the content [(1) ]() [(2) ]() . Important considerations: - The knowledge base uses chunking with configurable

max_chunk_size

(default 2000, range 600-6000) and

min_chunk_size

(default 400, range 200-2000) [(1) ]() - Knowledge Base 2.0 provides up to 50% improvement in answer accuracy with better ranking and precision for key details [(3) ]() - Pricing is $0.005 per minute for using Knowledge Base, with 10 free knowledge bases per workspace [(4) ]() For a large catalog, consider structuring your data clearly with titles for each SKU to help the AI retrieve accurate information [(1) ]() [(2) ]() .

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.

​ To learn more, see the sources I considered: [[1] Create Knowledge Base](https://docs.retellai.com/api-references/create-knowledge-base) [[2] Empower AI with Dynamic Knowledge Bases | Retell AI](https://www.retellai.com/features/knowledge-base) [[3] Major Platform Upgrades: Knowledge base, warm transfer, Voice & Analytics](https://www.retellai.com/changelog/major-platform-upgrades-knowledge-base-warm-transfer-voice-analytics) [[4] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) ​

### Answer For structuring your product catalog, here are the best practices [(1) ]() : Recommended Format: Markdown Prefer

.md

(Markdown) files over

.txt

. Well-structured Markdown is chunked and retrieved more accurately . Structure Guidelines: - Use clear, descriptive headings and keep each section focused and reasonably short - If a section becomes long, split it into multiple subsections - Write short paragraphs and lists to separate concepts; avoid walls of text - Group related information within the same section so chunks remain cohesive and relevant - Avoid ambiguity and use specificity in references . Include names, dates, units, and avoid ambiguous pronouns like

it

or

this

, because prior chunks may not be present Character Limit Information: The knowledge base uses chunking with configurable limits [(2) ]() : - `max_chunk_size`: Maximum number of characters per chunk when splitting knowledge base content (default 2000, range 600-6000) - `min_chunk_size`: Minimum number of characters per chunk (default 400, range 200-2000) . Chunks smaller than this are merged with adjacent chunks Additional Limits: Each knowledge base has these limits [(1) ]() : - Text: at max 50 text snippets - File: at max 25 files, with each file at max 50MB - For CSV, TSV, XLS, and XLSX, the row limit is 1000 rows and the column limit is 50 columns For a 1,000 SKU catalog, structure each product with clear headings in Markdown format, keeping product details concise and well-organized to optimize retrieval accuracy .

​ To learn more, see the sources I considered: [[1] Knowledge Base](https://docs.retellai.com/build/knowledge-base) [[2] Create Knowledge Base](https://docs.retellai.com/api-references/create-knowledge-base) ​

Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.