# Détection de Documents Similaires

{% hint style="info" %}
**Disponible à partir de la version 11.48.0** — Nécessite la licence `OPENSEARCH_ENABLED`.
{% endhint %}

## Que fait ce script ?

Utilise la recherche de similarité vectorielle pour trouver des documents sémantiquement similaires. Si un document avec plus de 95 % de similarité est trouvé, le numéro de facture est signalé comme potentiellement frauduleux ou en double.

## Déclencheur

`AFTER_FORMATTING` sur le type de document **INVOICE**

## Script Complet

```python
doc_id = document_json["doc_id"]
similar = vector_search(doc_id, k=5)

for doc in similar:
    if doc["similarity_percent"] > 95:
        set_field_as_invalid(
            document_data, "invoice_id",
            f"95%+ similaire à : {doc['name']} (Score : {doc['similarity_percent']}%)"
        )
        break
```

## Fonctions Utilisées

* [vector\_search()](/administration-and-setup/settings/global-settings/document-types/script/scripting-in-docbits/fulltext-search-functions.md#vector_search)
* [set\_field\_as\_invalid()](https://github.com/Fellow-Consulting-AG/docbits/blob/fr/readme/administration-and-setup/settings/global-settings/document-types/script/scripting-in-docbits/field-functions.md#set_field_as_invalid)


---

# Agent Instructions: 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:

```
GET https://docs-fr.docbits.com/administration-and-setup/settings/global-settings/document-types/script/scripting-in-docbits/sample-scripts/similar-document-detection.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.
