Effective Search
Trove uses semantic search, not keyword matching. Write queries as natural language questions or phrases. Trove matches on meaning, not exact words.
Choosing the Right Tool
Section titled “Choosing the Right Tool”| Goal | Use | Example |
|---|---|---|
| Find specific content | search / trove_search | ”papers about attention mechanisms in transformers” |
| Explore a topic broadly | discover / trove_discover | ”AI safety” |
| See what’s new | recent / trove_recent | (no query needed) |
| Read full content | document query / trove_get_document | (pass a document ID from search results) |
Tips for Better Results
Section titled “Tips for Better Results”1. Be Specific
Section titled “1. Be Specific”Describe what you are actually looking for. Specific queries return higher-relevance results.
| Instead of | Try |
|---|---|
| ”AI training" | "how does RLHF work in large language models" |
| "startup advice" | "when should a startup raise a Series A" |
| "programming" | "error handling patterns in Rust async code” |
2. Use Filters
Section titled “2. Use Filters”Narrow results when you know something about the source.
- By connector. “Search my Readwise highlights for…”
- By author. “Find articles by Paul Graham about…”
- By date. “What did I save last week about…”
- By content type. “Search my transcripts for…”
- By tags. “Find everything tagged ‘machine-learning’…“
3. Combine Search and Get Document
Section titled “3. Combine Search and Get Document”Search returns snippets, the most relevant chunk from each document. When a snippet looks promising, use trove_get_document (or the document GraphQL query) to read the full text. This two-step pattern keeps search fast while giving you full content on demand.
4. Try Discover for Brainstorming
Section titled “4. Try Discover for Brainstorming”discover uses a lower similarity threshold than search. Use it when you want:
- Loosely related content across different sources
- A broader view of what you have saved on a topic
- Connections between ideas that a precise search would miss
5. Use Recent for Chronological
Section titled “5. Use Recent for Chronological”recent does no semantic matching. It returns documents sorted by index time, newest first. Good for:
- Checking what was synced today
- Reviewing recently saved content
- Keeping up with active connectors
6. Filter by Date
Section titled “6. Filter by Date”Use after and before to find content from a specific time period. Dates apply to the content’s original creation date, not when it was indexed.
7. Scope to a Connector
Section titled “7. Scope to a Connector”When you know where the content lives, filter by connector name. Searching “within my arXiv papers” is faster and more precise than searching everything.
Understanding Relevance Scores
Section titled “Understanding Relevance Scores”Every search and discover result includes a relevance score from 0.0 to 1.0.
| Score | Interpretation |
|---|---|
| 0.9+ | Strong match. Directly answers your query |
| 0.7 to 0.9 | Good match. Clearly related content |
| 0.5 to 0.7 | Related but tangential |
| Below 0.5 | Weak match. Only loosely connected |
If scores are low across all results, rephrase your query or use discover for broader exploration.