> For the complete documentation index, see [llms.txt](https://docs.altum.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.altum.ai/english/property-valuation-and-market/interactive-reference-api/visual-similarity-search.md).
# Visual similarity search
Not all features of a property are caught in tabular data. For finding reference objects, we now support visual search which can be added as a weight
Visual similar properties
## How to use
* Input "visual\_similarity": 1 to activate the function.
* Add a custom weight from 0.1 to 1 to determine the impact of sorting the results with 0.5 as default: "weight\_visualsimilarity": 0.5.
* Input an image for the target object via example “url”: “.
* Optionally adjust the other weights to improve the sorting of visual similar properties. When only interested in the visual similarity of the reference objects, set the rest of the weights to zero: "weight\_innersurfacearea" : 0, "weight\_buildyear" : 0, "weight\_transactiondate" : 0, "weight\_distance" : 0.
{% hint style="info" %}
* Visual similarity can only be calculated for objects of which a facade image is known in the database.
* The performance of the API when activating “visual\_similarity” is slower because of the activation of the model to parse the images and find visual similar properties.
{% endhint %}
## Results
* The reference objects are sorted based on the calculated weight
* Per reference object, additional information is returned:
* Image: The facade image of the reference objects is added per reference object when known: “Image”: “.
* Visual similarity score: “VisualSimilarityScore”: 82.425.
---
# 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.altum.ai/english/property-valuation-and-market/interactive-reference-api/visual-similarity-search.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
