Advanced Search
ZenSearch provides powerful search capabilities combining semantic understanding with precise filtering. Master these features to find exactly what you need.
Search Architecture
Hybrid Search
ZenSearch uses a hybrid approach combining:
Dense Embeddings
- Semantic understanding: Finds conceptually similar content
- Meaning over keywords: "car" matches "automobile"
- Context awareness: Understands intent behind queries
Sparse Embeddings
- Keyword precision: Exact term matching
- Technical terms: Catches specific jargon
- Names and codes: Finds exact identifiers
Fusion
Results from both methods are combined using sophisticated ranking algorithms to provide the best of both worlds.
Retrieval Pipeline
Query
↓
Intent Classification
↓
Query Expansion (optional)
↓
Permission Filtering
↓
Hybrid Search (Dense + Sparse)
↓
Faceted Filtering
↓
Cross-Encoder Reranking
↓
Context Enrichment
↓
Results
Query Types
Natural Language Questions
Ask questions as you would to a colleague:
"What is our policy on remote work?"
"How do I configure the database connection?"
"Who is responsible for the Q4 budget?"
Keyword Searches
Use specific terms for precision:
"API authentication token"
"error code 5001"
"employee handbook 2024"
Combined Queries
Mix natural language with specific terms:
"How do I fix error ERR_CONNECTION_REFUSED?"
"What are the steps to deploy version 2.3.1?"
Query Expansion
ZenSearch can automatically expand your query to improve results:
How It Works
- Your query is analyzed
- Alternative phrasings are generated
- Multiple searches run in parallel
- Results are merged and deduplicated
Example
Original: "How to fix login issues"
Expanded:
- "login issues troubleshooting"
- "authentication problems resolution"
- "sign in errors fix"
- "login failure solutions"
Faceted Search
Available Facets
| Facet | Description | Example Values |
|---|---|---|
| Topics | Content categories | Technology, Finance, HR |
| Departments | Organizational units | Engineering, Sales, Marketing |
| Languages | Document language | English, Spanish, French |
| Sentiments | Content tone | Positive, Neutral, Negative |
| Date Range | Creation/modification | Last 7/30/90 days, Custom |
Using Facets
- Perform a search
- View facets in the sidebar
- Click to filter by facet values
- Combine multiple facets
- Clear filters to broaden results
Dynamic Facets
Facets update based on current results:
- Counts reflect filtered results
- Unavailable facets are hidden
- Values sorted by relevance
Cross-Encoder Reranking
What Is Reranking?
After initial retrieval, a cross-encoder model reranks results for better precision:
- Initial retrieval: Fast, broad search
- Reranking: Deep analysis of top candidates
- Final order: Most relevant results first
Benefits
- More accurate relevance scores
- Better handling of complex queries
- Improved result ordering
Coverage Information
Understanding Coverage
Search results include coverage metrics showing completeness:
- Full coverage: All relevant content found
- Partial coverage: Some content may be missing
- Warnings: Potential gaps in results
Coverage Indicators
Results: 15 documents found
Coverage: 94% (3 semantic units pending indexing)
⚠️ Some content from GitHub connector is still syncing
Search Modes
Chat Mode
Best for:
- Questions needing synthesized answers
- Multi-turn conversations
- Research and exploration
Features:
- AI-generated responses
- Source citations
- Follow-up capability
Search Mode
Best for:
- Finding specific documents
- Browsing available content
- Detailed filtering
Features:
- Document list results
- Faceted filtering
- Preview snippets
Scope and Collections
Collection Scoping
Control search boundaries:
| Scope | Use Case |
|---|---|
| All Collections | Company-wide search |
| Single Collection | Department-specific search |
| Multiple Collections | Cross-functional research |
Setting Scope
- Click the Scope dropdown
- Select collections to include
- View document counts
- Search within selection
Answer Shape
Query Classification
ZenSearch classifies queries to optimize responses:
| Shape | Description | Example |
|---|---|---|
| Enumerative | List of items | "What tools do we use?" |
| Procedural | Step-by-step | "How do I submit expenses?" |
| Exploratory | Open-ended | "Tell me about our products" |
| Comparative | Comparison | "Compare Plan A vs Plan B" |
Response Formatting
Responses are formatted based on query shape:
- Enumerative: Bulleted lists
- Procedural: Numbered steps
- Exploratory: Comprehensive overview
- Comparative: Tables and comparisons
Meta-Questions
About Your Knowledge Base
Ask meta-questions about your indexed content:
"What topics are covered in our documentation?"
"Give me an overview of the engineering wiki"
"What data sources are connected?"
"Show me statistics about our content"
Meta-Question Indicators
Meta-questions are indicated with badges:
- Overview
- Topics
- Data Sources
- Statistics
- Capabilities
Search Tips
Effective Queries
| Strategy | Example |
|---|---|
| Be specific | "Q4 2024 sales report" vs "sales" |
| Add context | "Python API authentication" vs "authentication" |
| Use timeframes | "last quarter", "2024", "recent" |
| Name specifics | Include project, team, or person names |
Refining Results
- Start broad, then narrow with facets
- Try alternative phrasings
- Use both chat and search modes
- Check suggested related queries
Interpreting Results
| Indicator | Meaning |
|---|---|
| High relevance | Strong match to query |
| Multiple citations | Synthesized from several sources |
| Recent date | Current information |
| Verified source | From authoritative connector |
Permissions and Access
Search-Time Filtering
ZenSearch enforces permissions at search time:
- Query is received
- User's access rights are checked
- Only accessible documents are searched
- Results exclude unauthorized content
Permission Types
| Type | Description |
|---|---|
| User | Individual access rights |
| Group | Team or group membership |
| Team | Workspace access |
| Domain | Organization-wide |
| Public | No restrictions |
Performance
Speed Optimization
ZenSearch optimizes for fast results:
- Cached embeddings
- Indexed metadata
- Parallel searches
- Incremental updates
Large Result Sets
For queries with many results:
- Pagination available
- "Load more" functionality
- Result count displayed
- Coverage information shown
Troubleshooting
No Results
- Check collection scope
- Broaden search terms
- Remove filters
- Verify content is indexed
Irrelevant Results
- Add more specific terms
- Use facet filters
- Try different phrasing
- Check query intent
Slow Searches
- Narrow collection scope
- Simplify complex queries
- Check for large pending syncs
- Use specific filters
Next Steps
- Ask & Chat - Main search interface
- Agents - AI-powered research
- API - Search API reference