Retrieval
The Retrieval page contains the technical configuration that controls whether — and how — the agent retrieves and learns from your knowledge base. Most settings here do not need to change for general use — but tuning them for your specific content and query patterns can noticeably improve answer quality.
Navigate to Knowledge → Retrieval in the left sidebar.
Reference
These settings control whether the agent draws on your Knowledge base when forming answers.
Enable Reference
When enabled, the agent searches references derived from your uploaded Knowledge content — documents, videos, and websites — before responding. This allows it to give accurate, context-specific answers grounded in your own content rather than relying solely on the base AI model's knowledge.
Disable this if your agent is intended for general-purpose conversation with no proprietary knowledge base.
How content becomes references: Every document, video, and website you add through the Knowledge menu is parsed and broken into text chunks. These chunks are what the agent actually searches — they are the references. Uploading content is a prerequisite for reference-based answers to work.
Restrict Answer
Only available when Enable Reference is turned on.
When enabled, the agent will only answer questions that can be answered using the knowledge base. If no relevant content is found, it declines to answer rather than guessing or using general knowledge.
Use this when accuracy and traceability to your documents is critical (e.g., legal, compliance, or technical support agents).
Content Scope
This section lets you restrict which content types the agent draws from during retrieval. By default, the agent searches across all content types in the knowledge base.
When content types are defined here, the agent only retrieves chunks that match one of the listed types. Leave this list empty to allow all content types.
Use content type filtering when your knowledge base contains a mix of materials (e.g., legal docs, FAQs, product specs) and you want the agent to scope its searches to specific categories.
Search Configuration
These settings directly control how many results the agent considers per query and how strictly it matches against the user's question.
| Setting | Description |
|---|---|
| Reference per-Query | The number of chunks retrieved and fed to the AI per user query. Higher values give the AI more context but increase response latency and token cost. Default: 4. |
| Search Tolerance | A 1–10 scale controlling how closely chunk content must match the query. Lower values (closer to 1) require a tighter match and may return no results for ambiguous queries; higher values cast a wider net but may include loosely relevant chunks. |
| Tolerance Increment | When no results are found at the current tolerance, the search automatically widens by this step size. For example, a value of 2 means the tolerance increases by 2 on each retry until results are found or the maximum tolerance is reached. |
Tuning Guidance
| Scenario | Recommended adjustment |
|---|---|
| Agent often says "I don't know" for questions you expect it to answer | Increase Search Tolerance or Tolerance Increment |
| Agent returns off-topic answers | Decrease Search Tolerance |
| Agent answers are shallow or missing detail | Increase Reference per-Query |
| Response times are too slow | Decrease Reference per-Query |
Reranker Configuration
The reranker adds a second scoring pass after the initial vector search. Vector search is fast but operates on embedding similarity, which can surface chunks that are topically adjacent without being the best answer to the specific question asked. The reranker reads the actual text of each candidate chunk against the query and re-orders them by contextual relevance before the final selection is passed to the AI.
The effect is better answer precision — especially for knowledge bases with many similar-sounding chunks — without needing to lower Search Tolerance or increase Reference per-Query.
How it works
- The vector search retrieves a larger candidate pool — controlled by Documents to Rerank
- The reranker AI model scores every candidate against the query
- The top Reference per-Query chunks (from the Search Configuration section) are selected from that re-ranked pool
- Those chunks are sent to the AI to generate the final answer
Documents to Rerank must be greater than Reference per-Query. The reranker needs a wider pool than the final selection — for example, retrieve 10 candidates, rerank them, then pass the best 4 to the AI.
Settings
| Setting | Description |
|---|---|
| Enable Reranker | Toggle that turns the reranking pass on or off. When disabled, the top chunks from the vector search are used as-is. |
| Reranker AI Model | The AI model used to score candidates. Only available when the reranker is enabled. Default: smart. |
| Documents to Rerank | How many candidates the vector search retrieves for the reranker to score. Must be a positive integer greater than Reference per-Query. Placeholder default: 10. |
When to enable the reranker
Enable it when:
- Your knowledge base has many chunks with similar vocabulary (e.g., a large FAQ or policy library)
- The agent retrieves technically relevant chunks but misses the most directly applicable one
- Answer quality is inconsistent despite adequate Search Tolerance settings
Leave it disabled when:
- Your knowledge base is small and well-structured — vector search alone is sufficient
- Latency is a priority — the reranking pass adds an extra AI model call per query
Training Configuration
| Setting | Description |
|---|---|
| Content Training AI Model | The AI model used during knowledge base training and embedding generation. Changing this affects how new content is indexed — existing indexed content is not automatically re-indexed. |
Saving Changes
Click Save at the bottom right. Changes to Reference and Search Configuration take effect immediately for new conversations. Changes to Training Configuration affect only newly indexed content — existing embeddings are not updated.