Knowledge Base
Upload docs, FAQs, and policies — your AI clients search them instead of guessing
Knowledge Base
Your assistant gets asked about your refund policy. Without a knowledge base, it guesses — and guesses wrong. With one, it pulls the exact paragraph from your actual policy and quotes it.
Protobox's knowledge base is a fully managed RAG pipeline. You upload documents; Protobox chunks them, generates embeddings, and stores them for semantic search. Connected MCP clients search your knowledge and get relevant passages in milliseconds.
Building a RAG pipeline from scratch — chunking, embedding, vector storage, retrieval, reranking — is typically a multi-week project. Protobox does it in minutes.
How It Works
Quick Start
Go to Build → Knowledge in the dashboard, or use the CLI / API. Choose a source:
- Text — paste FAQ answers, policy snippets, product descriptions (indexed immediately)
- URL — point to a help article or web page (Protobox crawls and indexes it)
- File — upload a PDF, TXT, HTML, or Markdown file
protobox kb add "Refunds within 30 days of purchase." --title "Refund Policy"
protobox kb add https://docs.example.com --title "Docs"
protobox kb add ./guide.pdf --title "User Guide"kb add takes one argument — a file path, a URL, or quoted text — and infers the source type.
curl -X POST "https://platform.protobox.ai/api/v1/knowledge" \
-H "X-API-Key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"source": "text",
"title": "Refund Policy",
"content": "Refunds are available within 30 days of purchase."
}'Text entries index immediately. URLs and files process asynchronously — protobox kb add polls the ingestion task to completion by default, and the REST response includes a taskId you can poll:
# skip the polling and return immediately
protobox kb add ./guide.pdf --title "User Guide" --no-wait
# inspect an entry later
protobox kb get <id>Processing runs content extraction → chunking → embedding → vector indexing. Most documents finish in under a minute.
Once indexed, search from the CLI, the REST API, or any connected MCP client:
protobox kb --search "what is the refund policy?"Source Types
| Source | Input | Processing | Best For |
|---|---|---|---|
text | content field | Sync (immediate) | FAQ entries, policies, short content |
url | url field | Async (returns taskId) | Web pages, help articles |
file | File upload | Async (returns taskId) | PDFs, manuals, docs |
Search Modes
| Mode | What it does | Best for |
|---|---|---|
hybrid (default) | Combines vector + text search | Most queries — balances meaning and exact matches |
vector | Pure semantic search | Conceptual questions where exact words differ |
text | Full-text keyword search | Specific terms, product names, codes |
protobox kb --search "money back guarantee"The CLI's --search runs the default hybrid retrieval. To pick a mode explicitly — or set minScore and limit — use the search API or the SDK.
Organizing with Folders
Group related entries into folders and filter searches and listings by folder. Pass a folderId when creating an entry via the API, and scope listings by folder in the dashboard.
MCP Integration
Once you've uploaded content, it's searchable from any client connected to your workspace's MCP endpoint — no extra configuration needed. The client receives relevant passages and uses them to ground its answers.
You don't configure anything extra for MCP. Upload documents and they're immediately available to connected clients.
Keeping Content Fresh
URL sync — re-crawl and re-index a URL-sourced entry on a schedule or on demand (configure in the dashboard or via the sync API).
Manual update — the CLI has no in-place edit; replace the entry (remove it, then add the new content), or update it through the SDK:
protobox kb remove <id>
protobox kb add "Updated refund policy: 60-day window." --title "Refund Policy"