The knowledge base is what makes your chatbot smart. It contains all the content your chatbot can reference when answering questions. Without a knowledge base, your chatbot only has the AI model’s general knowledge.Documentation Index
Fetch the complete documentation index at: https://docs.fife.bot/llms.txt
Use this file to discover all available pages before exploring further.
How It Works
FIFE.BOT processes it
Content is split into chunks, converted to vector embeddings (using OpenAI’s text-embedding-3-large), and stored in a PostgreSQL database with pgvector.
User asks a question
The question is analyzed, decomposed into sub-queries if needed, and searched against the knowledge base using hybrid search — combining vector similarity and full-text search.
Best chunks are retrieved
Results are fused, deduplicated, diversified by source, reranked by the LLM, and checked for coverage. If coverage is insufficient, additional retrieval rounds run automatically.
Source Types
| Source | Description | Auto-Sync |
|---|---|---|
| Websites | Crawl and index web pages via Firecrawl | Yes (scheduled) |
| Documents | Upload PDF, DOCX, TXT files | No (manual re-upload) |
| Texts | Write or paste content in a rich text editor | No (manual edit) |
| Q&A Tables | Structured question-answer pairs | No (manual edit) |
| Notion | Sync pages from Notion workspaces | Yes (scheduled) |
| Confluence | Sync pages from Confluence spaces | Yes (scheduled) |
| Google Drive | Sync files from Google Drive folders | Yes (scheduled) |
| SharePoint / OneDrive | Sync documents from Microsoft 365 | Yes (scheduled) |
The Knowledge Base Tab
Open any chatbot and click the Knowledge Base tab to see:- Add Source dropdown — pick a source type to add
- Filter bar — filter by source type (All, Websites, Documents, Texts, Table, Notion, Confluence, Google Drive, SharePoint)
- Source list — all added sources with status indicators
- Processing stats — total sources, ready count, processing count
Source Status Indicators
| Status | Meaning |
|---|---|
| Ready | Content is indexed and searchable |
| Processing | Content is being chunked and embedded |
| Error | Processing failed — click to see error details and retry |
Per-Source Actions
| Action | Description |
|---|---|
| Delete | Remove the source and all its chunks |
| Resync | Re-fetch and re-process content (integrations only) |
| Edit | Modify content (texts and Q&A tables only) |
| Rename | Change the display name |
Routing Instructions
Each knowledge base source can have optional routing instructions — extra context that tells the AI how to use content from that specific source. Example: A website source for your pricing page might have routing instructions like:“When answering pricing questions from this source, always mention the 14-day free trial and the annual discount.”Routing instructions are combined with the system prompt at query time.
Plan Limits
Limits match fife.bot pricing — your plan caps chatbots, monthly credits, and knowledge sources (each website, document set, integration, etc. counts as a source).| Resource | Free | Pro | Business |
|---|---|---|---|
| Chatbots | 1 | 5 | 10 |
| Credits/month | 50 | 2,000 | 5,000 |
| Knowledge sources | 1 | 10 | Unlimited |
Search Technology
FIFE.BOT uses a sophisticated retrieval pipeline:- Query analysis — determines intent, language, and complexity
- Multi-query decomposition — complex questions are split into sub-queries
- Hybrid search — vector cosine similarity + PostgreSQL full-text search with weighted scoring
- Reciprocal Rank Fusion — merges results from multiple search strategies
- Source diversification — ensures results come from multiple sources
- Parent chunk expansion — retrieves surrounding context for better answers
- LLM reranking — the AI re-scores chunks for relevance
- Coverage checking — if the answer isn’t fully covered, additional retrieval rounds run