The retrieval settings control how the Knowledge Assistant filters and ranks documents before generating a response. These settings allow you to fine-tune the balance between precision (returning only highly relevant results) and recall (returning more results that might be useful). All settings can be configured in the Admin Console.
This filter removes chunks that are too short to contain meaningful information. Very short chunks often contain headers, footers, or fragmented text that adds noise without providing useful context.
When enabled, chunks shorter than the minimum length are removed from search results before being passed to the language model.
The minimum number of characters a chunk must have to be included in results. Lower values include more content but may introduce noise. Higher values ensure only substantial content is used but may filter out valid short answers.
This feature adjusts how many candidate documents are retrieved based on the complexity of the user's query. Simple, straightforward questions need fewer candidates, while complex questions benefit from a wider search.
When enabled, the system analyzes query complexity and adjusts the number of candidate documents retrieved. Simple queries (e.g., "What is BITB's expense ratio?") retrieve fewer candidates, reducing noise and improving response speed.
Controls how much to reduce the candidate pool for simple queries. A multiplier of 2x means simple queries retrieve half as many candidates as complex queries. Lower values make the filter more aggressive.
The system classifies queries into complexity levels based on:
Different types of questions have different relevance requirements. A factual question about a specific product needs highly relevant results, while an exploratory question about a broad topic can benefit from a wider range of moderately relevant content.
When enabled, the minimum relevance score required for a chunk to be included varies based on the detected intent of the query. This allows the system to be more strict for factual queries and more permissive for exploratory ones.
Questions seeking specific facts, numbers, or definitions. Examples: "What is BITB's expense ratio?" or "When was ETHW launched?"
Behavior: Higher threshold ensures only highly relevant chunks are used, reducing the risk of incorrect information.
Questions comparing multiple items or asking about differences. Examples: "How does BITB compare to GBTC?" or "What's the difference between spot and futures ETFs?"
Behavior: Moderate threshold allows retrieving information about multiple products to enable meaningful comparisons.
Questions about time-based information, trends, or historical data. Examples: "What happened to Bitcoin in 2024?" or "How has BITB performed this year?"
Behavior: Moderate threshold with preference for recent documents.
Broad questions seeking general information or learning about a topic. Examples: "Tell me about crypto ETFs" or "What products does Bitwise offer?"
Behavior: Lower threshold includes a wider range of content to provide comprehensive overviews.
Relevance scores range from 0% to 100%, representing how closely a chunk matches the query:
This filter ensures that when users ask about specific products or assets, the retrieved chunks actually mention those entities. This prevents the model from conflating information about different products.
When enabled and a user asks about a specific product (e.g., "BITB"), chunks that don't mention that product are filtered out. This is only applied to factual queries where precision is critical.
If the entity filter is too aggressive and removes all chunks, the system falls back to keeping the top N chunks by relevance score. This ensures there's always some context for the model to work with.
| Use Case | Recommended Settings |
|---|---|
| High precision (factual queries) | All filters enabled, higher thresholds (25%+ for factual) |
| Broad coverage (exploratory queries) | Lower thresholds (5-10%), entity filter disabled |
| FAQ-style knowledge base | Lower min chunk length (50), all other defaults |
| Document-heavy knowledge base | Higher min chunk length (150), complexity-aware enabled |
| Balanced (default) | All defaults - good balance of precision and recall |
After adjusting settings, monitor the impact using the Analytics Dashboard: