1  ---
  2  title: "JinaDocumentEmbedder"
  3  id: jinadocumentembedder
  4  slug: "/jinadocumentembedder"
  5  description: "This component computes the embeddings of a list of documents and stores the obtained vectors in the embedding field of each document. It uses Jina AI Embeddings models.  The vectors computed by this component are necessary to perform embedding retrieval on a collection of documents. At retrieval time, the vector representing the query is compared with those of the documents to find the most similar or relevant documents."
  6  ---
  7  
  8  # JinaDocumentEmbedder
  9  
 10  This component computes the embeddings of a list of documents and stores the obtained vectors in the embedding field of each document. It uses Jina AI Embeddings models.  The vectors computed by this component are necessary to perform embedding retrieval on a collection of documents. At retrieval time, the vector representing the query is compared with those of the documents to find the most similar or relevant documents.
 11  
 12  <div className="key-value-table">
 13  
 14  |  |  |
 15  | --- | --- |
 16  | **Most common position in a pipeline** | Before a [`DocumentWriter`](../writers/documentwriter.mdx)  in an indexing pipeline |
 17  | **Mandatory init variables** | `api_key`: The Jina API key. Can be set with `JINA_API_KEY` env var. |
 18  | **Mandatory run variables** | `documents`: A list of documents |
 19  | **Output variables** | `documents`: A list of documents (enriched with embeddings)  <br /> <br />`meta`: A dictionary of metadata |
 20  | **API reference** | [Jina](/reference/integrations-jina) |
 21  | **GitHub link** | https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/jina |
 22  
 23  </div>
 24  
 25  ## Overview
 26  
 27  `JinaDocumentEmbedder` enriches the metadata of documents with an embedding of their content. To embed a string, you should use the [`JinaTextEmbedder`](jinatextembedder.mdx). To see the list of compatible Jina Embeddings models, head to Jina AI’s [website](https://jina.ai/embeddings/). The default model for `JinaDocumentEmbedder` is `jina-embeddings-v2-base-en`.
 28  
 29  To start using this integration with Haystack, install the package with:
 30  
 31  ```shell
 32  pip install jina-haystack
 33  ```
 34  
 35  The component uses a `JINA_API_KEY` environment variable by default. Otherwise, you can pass an API key at initialization with `api_key`:
 36  
 37  ```python
 38  embedder = JinaDocumentEmbedder(api_key=Secret.from_token("<your-api-key>"))
 39  ```
 40  
 41  To get a Jina Embeddings API key, head to https://jina.ai/embeddings/.
 42  
 43  ### Embedding Metadata
 44  
 45  Text documents often come with a set of metadata. If they are distinctive and semantically meaningful, you can embed them along with the text of the document to improve retrieval.
 46  
 47  You can do this easily by using the Document Embedder:
 48  
 49  ```python
 50  from haystack import Document
 51  from haystack_integrations.components.embedders.jina import JinaDocumentEmbedder
 52  
 53  doc = Document(content="some text", meta={"title": "relevant title", "page number": 18})
 54  
 55  embedder = JinaDocumentEmbedder(
 56      api_key=Secret.from_token("<your-api-key>"),
 57      meta_fields_to_embed=["title"],
 58  )
 59  
 60  docs_w_embeddings = embedder.run(documents=[doc])["documents"]
 61  ```
 62  
 63  ## Usage
 64  
 65  ### On its own
 66  
 67  Here is how you can use the component on its own:
 68  
 69  ```python
 70  from haystack_integrations.components.embedders.jina import JinaDocumentEmbedder
 71  
 72  doc = Document(content="I love pizza!")
 73  
 74  document_embedder = JinaDocumentEmbedder(api_key=Secret.from_token("<your-api-key>"))
 75  
 76  result = document_embedder.run([doc])
 77  print(result["documents"][0].embedding)
 78  
 79  ## [0.017020374536514282, -0.023255806416273117, ...]
 80  ```
 81  
 82  :::info
 83  We recommend setting JINA_API_KEY as an environment variable instead of setting it as a parameter.
 84  :::
 85  
 86  ### In a pipeline
 87  
 88  ```python
 89  from haystack import Pipeline
 90  from haystack.document_stores.in_memory import InMemoryDocumentStore
 91  from haystack_integrations.components.embedders.jina import JinaDocumentEmbedder
 92  from haystack_integrations.components.embedders.jina import JinaTextEmbedder
 93  from haystack.components.writers import DocumentWriter
 94  from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
 95  
 96  document_store = InMemoryDocumentStore(embedding_similarity_function="cosine")
 97  
 98  documents = [
 99      Document(content="My name is Wolfgang and I live in Berlin"),
100      Document(content="I saw a black horse running"),
101      Document(content="Germany has many big cities"),
102  ]
103  
104  indexing_pipeline = Pipeline()
105  indexing_pipeline.add_component(
106      "embedder",
107      JinaDocumentEmbedder(api_key=Secret.from_token("<your-api-key>")),
108  )
109  indexing_pipeline.add_component("writer", DocumentWriter(document_store=document_store))
110  indexing_pipeline.connect("embedder", "writer")
111  
112  indexing_pipeline.run({"embedder": {"documents": documents}})
113  
114  query_pipeline = Pipeline()
115  query_pipeline.add_component(
116      "text_embedder",
117      JinaTextEmbedder(api_key=Secret.from_token("<your-api-key>")),
118  )
119  query_pipeline.add_component(
120      "retriever",
121      InMemoryEmbeddingRetriever(document_store=document_store),
122  )
123  query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
124  
125  query = "Who lives in Berlin?"
126  
127  result = query_pipeline.run({"text_embedder": {"text": query}})
128  
129  print(result["retriever"]["documents"][0])
130  
131  ## Document(id=..., mimetype: 'text/plain',
132  ## text: 'My name is Wolfgang and I live in Berlin')
133  ```
134  
135  ## Additional References
136  
137  🧑‍🍳 Cookbook: [Using the Jina-embeddings-v2-base-en model in a Haystack RAG pipeline for legal document analysis](https://haystack.deepset.ai/cookbook/jina-embeddings-v2-legal-analysis-rag)