> ## Documentation Index
> Fetch the complete documentation index at: https://docs.camel-ai.org/llms.txt
> Use this file to discover all available pages before exploring further.

# Camel.retrievers.jina rerank retriever

<a id="camel.retrievers.jina_rerank_retriever" />

<a id="camel.retrievers.jina_rerank_retriever.JinaRerankRetriever" />

## JinaRerankRetriever

```python theme={"system"}
class JinaRerankRetriever(BaseRetriever):
```

An implementation of the `BaseRetriever` using the `Jina AI Reranker`
model.

This retriever uses Jina AI's reranking API to re-order retrieved documents
based on their relevance to the query. It supports multilingual retrieval
across 100+ languages.

**Parameters:**

* **model\_name** (Union\[JinaRerankerModelType, str]): The model name to use for re-ranking.
* **api\_key** (str, optional): The API key for authenticating with the Jina AI service.
* **References**:
* **https**: //jina.ai/reranker/

<a id="camel.retrievers.jina_rerank_retriever.JinaRerankRetriever.__init__" />

### **init**

```python theme={"system"}
def __init__(
    self,
    model_name: Union[JinaRerankerModelType, str] = JinaRerankerModelType.JINA_RERANKER_V2_BASE_MULTILINGUAL,
    api_key: str | None = None
):
```

Initializes an instance of the JinaRerankRetriever. This
constructor sets up the API key for interacting with the Jina AI
Reranker API.

**Parameters:**

* **model\_name** (Union\[JinaRerankerModelType, str]): The name of the model to be used for re-ranking. Can be a JinaRerankerModelType enum value or a string. Defaults to `JinaRerankerModelType.JINA_RERANKER_V2_BASE_MULTILINGUAL`.
* **api\_key** (Optional\[str]): The API key for authenticating requests to the Jina AI API. If not provided, the method will attempt to retrieve the key from the environment variable 'JINA\_API\_KEY'.

<a id="camel.retrievers.jina_rerank_retriever.JinaRerankRetriever.query" />

### query

```python theme={"system"}
def query(
    self,
    query: str,
    retrieved_result: list[dict[str, Any]],
    top_k: int = DEFAULT_TOP_K_RESULTS
):
```

Queries and compiles results using the Jina AI re-ranking model.

**Parameters:**

* **query** (str): Query string for information retriever.
* **retrieved\_result** (List\[Dict\[str, Any]]): The content to be re-ranked, should be the output from `BaseRetriever` like `VectorRetriever`. Each dict should have a 'text' key containing the document text.
* **top\_k** (int, optional): The number of top results to return during retrieval. Must be a positive integer. Defaults to `DEFAULT_TOP_K_RESULTS`.

**Returns:**

List\[Dict\[str, Any]]: Concatenated list of the query results,
each containing the original data plus a 'similarity score'.