> For the complete documentation index, see [llms.txt](https://help.tellius.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.tellius.com/settings/analytics/search-discover-and-predict.md).
# Search, Discover & Predict
Under **Settings → Modules → Analytics → Search, Discover & Predict,** this page lets admins fine-tune how users interact with Tellius's core search, insight generation, and machine learning capabilities.
### **Search**
Customize the behavior of natural language search, guided query experiences, and visualization enhancements.
**Enable personalised search:** When turned on, Tellius uses each user's historical interactions to prioritize and rank query suggestions, making future searches smarter and more relevant. This delivers faster insights for repeat users by learning what matters to them.
**Perform query on Enter key press:** Allows users to trigger a search by pressing **Enter**, without clicking the search icon.
**Enable Guide Me Queries:** Activates Tellius's AI-powered query assistant, which suggests relevant, contextual questions based on the selected Business View. Useful for users unfamiliar with the schema or unsure where to begin.
**Enable Add to Vizpad Buttons (Search & Insights):** Shows an **Add to Vizpad** button next to each search or insight result, so users can build interactive Vizpads quickly from the response.
**Enable In-Memory operations (Segment Driver, ML etc) for Live BV:** Enables Tellius to perform compute-heavy operations such as segmentation analysis, machine learning, and driver insights directly in memory, even for Live Business Views connected to systems like Snowflake or Redshift.
Beyond faster performance for those features, this toggle is required to enable downloads and exports of datasets, Insights, and Business Views when using Live connections.
{% hint style="warning" %}
Enabling this requires sufficient system RAM. If your environment has limited memory, consider keeping it disabled to avoid compute bottlenecks.
{% endhint %}
**Enable data labels by default:** Ensures charts automatically include numeric labels, such as value annotations on bars, lines, or pie slices, making data easier to interpret at a glance.
**Enable editing of Search Guide for Power Users:** Allows users with the Power role to edit the Search Guide.
**Default Aggregation:** Defines how Tellius summarizes numeric fields in Search and Insights by default. The available options are **Sum**, **Avg**, **Min**, **Max**, **Percentage**, **Median**, **Count**, and **Unique Count**.
### **Insights**
The Insights engine generates advanced insights using machine learning algorithms, which need temporary storage for intermediate computation data. Choose where that data is stored:
**Memory:** Best for high-performance computation. Using RAM produces faster insights, especially on small to mid-sized datasets. It requires more memory, which may not suit very large workloads.
**Disk:** Suitable for large datasets or memory-constrained environments. Storing data on disk reduces RAM usage and may slightly slow insight generation, though disk performance is sufficient in most cases.
{% hint style="info" %}
Choose **Memory** for speed; choose **Disk** for scalability.
{% endhint %}
### **Machine Learning**
Configures how Tellius performs predictive analytics and builds machine learning models.
**Configure Compute vs Memory for computation:** The same choice as the Insights section, applied to ML workloads:
* **Memory** - best for speed and iterative modeling, suited to small and medium datasets, but requires more system memory.
* **Disk** - better for larger datasets or shared environments with limited memory. Sufficient in most cases.
**AutoML Hyperparameter optimization:** AutoML tunes the hyperparameters for every algorithm it runs. Turning optimization on produces more accurate models at the cost of additional execution time. Turning it off uses default parameters and reduces computation time.
**Enable time-series models:** Controls whether users can create new time-series regression Point-n-Click Models. When disabled, users cannot create new ones, but existing time-series regression models can still be viewed. Time-series models support forecasting use cases such as demand prediction, sales forecasting, and trend analysis.
#### Saving
Click **Save** to apply your changes, or **Cancel** to discard them. Save stays inactive until something changes.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://help.tellius.com/settings/analytics/search-discover-and-predict.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
