From 5f87bddc7f434f9faedfb9c0eae984b2d5e72afa Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Wed, 11 Sep 2024 18:38:29 +0800
Subject: [PATCH 01/25] chore: update Jina Embedder usage for V3 release

---
 .../embedders/jina/document_embedder.py       |  8 ++---
 .../embedders/jina/text_embedder.py           |  6 ++--
 .../jina/tests/test_document_embedder.py      | 32 +++++++++++++++++++
 integrations/jina/tests/test_text_embedder.py | 29 +++++++++++++++++
 4 files changed, 68 insertions(+), 7 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index 6bcd94220..4caf0ebc5 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -131,7 +131,7 @@ def _prepare_texts_to_embed(self, documents: List[Document]) -> List[str]:
             texts_to_embed.append(text_to_embed)
         return texts_to_embed
 
-    def _embed_batch(self, texts_to_embed: List[str], batch_size: int) -> Tuple[List[List[float]], Dict[str, Any]]:
+    def _embed_batch(self, texts_to_embed: List[str], batch_size: int, parameters: Optional[Dict]) -> Tuple[List[List[float]], Dict[str, Any]]:
         """
         Embed a list of texts in batches.
         """
@@ -142,7 +142,7 @@ def _embed_batch(self, texts_to_embed: List[str], batch_size: int) -> Tuple[List
             range(0, len(texts_to_embed), batch_size), disable=not self.progress_bar, desc="Calculating embeddings"
         ):
             batch = texts_to_embed[i : i + batch_size]
-            response = self._session.post(JINA_API_URL, json={"input": batch, "model": self.model_name}).json()
+            response = self._session.post(JINA_API_URL, json={"input": batch, "model": self.model_name, **parameters}).json()
             if "data" not in response:
                 raise RuntimeError(response["detail"])
 
@@ -161,7 +161,7 @@ def _embed_batch(self, texts_to_embed: List[str], batch_size: int) -> Tuple[List
         return all_embeddings, metadata
 
     @component.output_types(documents=List[Document], meta=Dict[str, Any])
-    def run(self, documents: List[Document]):
+    def run(self, documents: List[Document], parameters: Optional[Dict]):
         """
         Compute the embeddings for a list of Documents.
 
@@ -180,7 +180,7 @@ def run(self, documents: List[Document]):
 
         texts_to_embed = self._prepare_texts_to_embed(documents=documents)
 
-        embeddings, metadata = self._embed_batch(texts_to_embed=texts_to_embed, batch_size=self.batch_size)
+        embeddings, metadata = self._embed_batch(texts_to_embed=texts_to_embed, batch_size=self.batch_size, parameters=parameters)
 
         for doc, emb in zip(documents, embeddings):
             doc.embedding = emb
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index 6398122a4..237ec927d 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
 #
 # SPDX-License-Identifier: Apache-2.0
-from typing import Any, Dict, List
+from typing import Any, Dict, List, Optional
 
 import requests
 from haystack import component, default_from_dict, default_to_dict
@@ -95,7 +95,7 @@ def from_dict(cls, data: Dict[str, Any]) -> "JinaTextEmbedder":
         return default_from_dict(cls, data)
 
     @component.output_types(embedding=List[float], meta=Dict[str, Any])
-    def run(self, text: str):
+    def run(self, text: str, parameters: Optional[Dict]):
         """
         Embed a string.
 
@@ -114,7 +114,7 @@ def run(self, text: str):
 
         text_to_embed = self.prefix + text + self.suffix
 
-        resp = self._session.post(JINA_API_URL, json={"input": [text_to_embed], "model": self.model_name}).json()
+        resp = self._session.post(JINA_API_URL, json={"input": [text_to_embed], "model": self.model_name, **parameters}).json()
         if "data" not in resp:
             raise RuntimeError(resp["detail"])
 
diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index 9d63f8302..cd448696d 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -246,3 +246,35 @@ def test_run_on_empty_list(self):
 
         assert result["documents"] is not None
         assert not result["documents"]  # empty list
+    
+    def test_run_with_v3(self):
+        docs = [
+            Document(content="I love cheese", meta={"topic": "Cuisine"}),
+            Document(content="A transformer is a deep learning architecture", meta={"topic": "ML"}),
+        ]
+
+        model = "jina-embeddings-v3-base-en"
+        with patch("requests.sessions.Session.post", side_effect=mock_session_post_response):
+            embedder = JinaDocumentEmbedder(
+                api_key=Secret.from_token("fake-api-key"),
+                model=model,
+                prefix="prefix ",
+                suffix=" suffix",
+                meta_fields_to_embed=["topic"],
+                embedding_separator=" | ",
+                batch_size=1,
+            )
+            result = embedder.run(documents=docs, parameters={"task_type":"retrieval.passage"})
+
+        documents_with_embeddings = result["documents"]
+        metadata = result["meta"]
+
+        assert isinstance(documents_with_embeddings, list)
+        assert len(documents_with_embeddings) == len(docs)
+        for doc in documents_with_embeddings:
+            assert isinstance(doc, Document)
+            assert isinstance(doc.embedding, list)
+            assert len(doc.embedding) == 3
+            assert all(isinstance(x, float) for x in doc.embedding)
+        assert metadata == {"model": model, "usage": {"prompt_tokens": 4, "total_tokens": 4}}
+
diff --git a/integrations/jina/tests/test_text_embedder.py b/integrations/jina/tests/test_text_embedder.py
index 5c0f80d02..4b9ae550e 100644
--- a/integrations/jina/tests/test_text_embedder.py
+++ b/integrations/jina/tests/test_text_embedder.py
@@ -106,3 +106,32 @@ def test_run_wrong_input_format(self):
 
         with pytest.raises(TypeError, match="JinaTextEmbedder expects a string as an input"):
             embedder.run(text=list_integers_input)
+
+    def test_with_v3(self):
+        model = "jina-embeddings-v3"
+        with patch("requests.sessions.Session.post") as mock_post:
+            # Configure the mock to return a specific response
+            mock_response = requests.Response()
+            mock_response.status_code = 200
+            mock_response._content = json.dumps(
+                {
+                    "model": "jina-embeddings-v3",
+                    "object": "list",
+                    "usage": {"total_tokens": 6, "prompt_tokens": 6},
+                    "data": [{"object": "embedding", "index": 0, "embedding": [0.1, 0.2, 0.3]}],
+                }
+            ).encode()
+
+            mock_post.return_value = mock_response
+
+            embedder = JinaTextEmbedder(
+                api_key=Secret.from_token("fake-api-key"), model=model, prefix="prefix ", suffix=" suffix"
+            )
+            result = embedder.run(text="The food was delicious", parameters={"task_type":"retrieval.passage"})
+
+        assert len(result["embedding"]) == 3
+        assert all(isinstance(x, float) for x in result["embedding"])
+        assert result["meta"] == {
+            "model": "jina-embeddings-v3",
+            "usage": {"prompt_tokens": 6, "total_tokens": 6},
+        }

From e0f48cd3a10fc8273242c1c070aa1d77cc0e3b34 Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Wed, 11 Sep 2024 18:48:31 +0800
Subject: [PATCH 02/25] fix: resolve lint issue

---
 .../embedders/jina/document_embedder.py        | 18 +++++++++++++++---
 .../components/embedders/jina/text_embedder.py |  6 +++++-
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index 4caf0ebc5..ef790dd95 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -131,7 +131,12 @@ def _prepare_texts_to_embed(self, documents: List[Document]) -> List[str]:
             texts_to_embed.append(text_to_embed)
         return texts_to_embed
 
-    def _embed_batch(self, texts_to_embed: List[str], batch_size: int, parameters: Optional[Dict]) -> Tuple[List[List[float]], Dict[str, Any]]:
+    def _embed_batch(
+            self,
+            texts_to_embed: List[str],
+            batch_size: int,
+            parameters: Optional[Dict]
+        ) -> Tuple[List[List[float]],Dict[str, Any]]:
         """
         Embed a list of texts in batches.
         """
@@ -142,7 +147,10 @@ def _embed_batch(self, texts_to_embed: List[str], batch_size: int, parameters: O
             range(0, len(texts_to_embed), batch_size), disable=not self.progress_bar, desc="Calculating embeddings"
         ):
             batch = texts_to_embed[i : i + batch_size]
-            response = self._session.post(JINA_API_URL, json={"input": batch, "model": self.model_name, **parameters}).json()
+            response = self._session.post(
+                JINA_API_URL,
+                json={"input": batch, "model": self.model_name, **parameters}
+            ).json()
             if "data" not in response:
                 raise RuntimeError(response["detail"])
 
@@ -180,7 +188,11 @@ def run(self, documents: List[Document], parameters: Optional[Dict]):
 
         texts_to_embed = self._prepare_texts_to_embed(documents=documents)
 
-        embeddings, metadata = self._embed_batch(texts_to_embed=texts_to_embed, batch_size=self.batch_size, parameters=parameters)
+        embeddings, metadata = self._embed_batch(
+            texts_to_embed=texts_to_embed,
+            batch_size=self.batch_size,
+            parameters=parameters
+        )
 
         for doc, emb in zip(documents, embeddings):
             doc.embedding = emb
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index 237ec927d..7510b8628 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -114,7 +114,11 @@ def run(self, text: str, parameters: Optional[Dict]):
 
         text_to_embed = self.prefix + text + self.suffix
 
-        resp = self._session.post(JINA_API_URL, json={"input": [text_to_embed], "model": self.model_name, **parameters}).json()
+        resp = self._session.post(
+            JINA_API_URL,
+            json={"input": [text_to_embed], "model": self.model_name, **parameters}
+        ).json()
+
         if "data" not in resp:
             raise RuntimeError(resp["detail"])
 

From dff73c2260971c331e5d461910dd4c35a48cf8ac Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Wed, 11 Sep 2024 18:53:40 +0800
Subject: [PATCH 03/25] fix: resolve test error

---
 .../components/embedders/jina/document_embedder.py            | 4 ++--
 .../components/embedders/jina/text_embedder.py                | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index ef790dd95..1f88266cb 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -135,7 +135,7 @@ def _embed_batch(
             self,
             texts_to_embed: List[str],
             batch_size: int,
-            parameters: Optional[Dict]
+            parameters: Optional[Dict] = None
         ) -> Tuple[List[List[float]],Dict[str, Any]]:
         """
         Embed a list of texts in batches.
@@ -169,7 +169,7 @@ def _embed_batch(
         return all_embeddings, metadata
 
     @component.output_types(documents=List[Document], meta=Dict[str, Any])
-    def run(self, documents: List[Document], parameters: Optional[Dict]):
+    def run(self, documents: List[Document], parameters: Optional[Dict]=None):
         """
         Compute the embeddings for a list of Documents.
 
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index 7510b8628..47a229f7d 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -95,7 +95,7 @@ def from_dict(cls, data: Dict[str, Any]) -> "JinaTextEmbedder":
         return default_from_dict(cls, data)
 
     @component.output_types(embedding=List[float], meta=Dict[str, Any])
-    def run(self, text: str, parameters: Optional[Dict]):
+    def run(self, text: str, parameters: Optional[Dict]=None):
         """
         Embed a string.
 

From 88f0eba9fa80fe4d75192a0590453661d76b586e Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Wed, 11 Sep 2024 19:00:36 +0800
Subject: [PATCH 04/25] fix: resolve test error

---
 .../components/embedders/jina/document_embedder.py          | 6 +++++-
 .../components/embedders/jina/text_embedder.py              | 6 +++++-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index 1f88266cb..ea0ead972 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -149,7 +149,11 @@ def _embed_batch(
             batch = texts_to_embed[i : i + batch_size]
             response = self._session.post(
                 JINA_API_URL,
-                json={"input": batch, "model": self.model_name, **parameters}
+                json={
+                    "input": batch,
+                    "model": self.model_name,
+                    **(parameters if parameters is not None else {})
+                },
             ).json()
             if "data" not in response:
                 raise RuntimeError(response["detail"])
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index 47a229f7d..c7220b404 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -116,7 +116,11 @@ def run(self, text: str, parameters: Optional[Dict]=None):
 
         resp = self._session.post(
             JINA_API_URL,
-            json={"input": [text_to_embed], "model": self.model_name, **parameters}
+            json={
+                "input": [text_to_embed],
+                "model": self.model_name,
+                **(parameters if parameters is not None else {}),
+            }
         ).json()
 
         if "data" not in resp:

From 0ad3ffe560dbc6a150b30a00b54f1f4a8c0bd78a Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Wed, 11 Sep 2024 19:06:20 +0800
Subject: [PATCH 05/25] fix: resolve lint issues

---
 .../components/embedders/jina/document_embedder.py         | 7 ++-----
 .../components/embedders/jina/text_embedder.py             | 2 +-
 integrations/jina/tests/test_document_embedder.py          | 7 +++----
 integrations/jina/tests/test_text_embedder.py              | 2 +-
 4 files changed, 7 insertions(+), 11 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index ea0ead972..2a9345339 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -132,10 +132,7 @@ def _prepare_texts_to_embed(self, documents: List[Document]) -> List[str]:
         return texts_to_embed
 
     def _embed_batch(
-            self,
-            texts_to_embed: List[str],
-            batch_size: int,
-            parameters: Optional[Dict] = None
+            self, texts_to_embed: List[str], batch_size: int, parameters: Optional[Dict] = None
         ) -> Tuple[List[List[float]],Dict[str, Any]]:
         """
         Embed a list of texts in batches.
@@ -173,7 +170,7 @@ def _embed_batch(
         return all_embeddings, metadata
 
     @component.output_types(documents=List[Document], meta=Dict[str, Any])
-    def run(self, documents: List[Document], parameters: Optional[Dict]=None):
+    def run(self, documents: List[Document], parameters: Optional[Dict] = None):
         """
         Compute the embeddings for a list of Documents.
 
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index c7220b404..fcffa5094 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -95,7 +95,7 @@ def from_dict(cls, data: Dict[str, Any]) -> "JinaTextEmbedder":
         return default_from_dict(cls, data)
 
     @component.output_types(embedding=List[float], meta=Dict[str, Any])
-    def run(self, text: str, parameters: Optional[Dict]=None):
+    def run(self, text: str, parameters: Optional[Dict] = None):
         """
         Embed a string.
 
diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index cd448696d..e5921c52e 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -246,7 +246,7 @@ def test_run_on_empty_list(self):
 
         assert result["documents"] is not None
         assert not result["documents"]  # empty list
-    
+
     def test_run_with_v3(self):
         docs = [
             Document(content="I love cheese", meta={"topic": "Cuisine"}),
@@ -264,7 +264,7 @@ def test_run_with_v3(self):
                 embedding_separator=" | ",
                 batch_size=1,
             )
-            result = embedder.run(documents=docs, parameters={"task_type":"retrieval.passage"})
+            result = embedder.run(documents=docs, parameters={"task_type": "retrieval.passage"})
 
         documents_with_embeddings = result["documents"]
         metadata = result["meta"]
@@ -276,5 +276,4 @@ def test_run_with_v3(self):
             assert isinstance(doc.embedding, list)
             assert len(doc.embedding) == 3
             assert all(isinstance(x, float) for x in doc.embedding)
-        assert metadata == {"model": model, "usage": {"prompt_tokens": 4, "total_tokens": 4}}
-
+        assert metadata == {"model": model, "usage": {"prompt_tokens": 4, "total_tokens": 4}}
\ No newline at end of file
diff --git a/integrations/jina/tests/test_text_embedder.py b/integrations/jina/tests/test_text_embedder.py
index 4b9ae550e..e2f55464b 100644
--- a/integrations/jina/tests/test_text_embedder.py
+++ b/integrations/jina/tests/test_text_embedder.py
@@ -127,7 +127,7 @@ def test_with_v3(self):
             embedder = JinaTextEmbedder(
                 api_key=Secret.from_token("fake-api-key"), model=model, prefix="prefix ", suffix=" suffix"
             )
-            result = embedder.run(text="The food was delicious", parameters={"task_type":"retrieval.passage"})
+            result = embedder.run(text="The food was delicious", parameters={"task_type": "retrieval.passage"})
 
         assert len(result["embedding"]) == 3
         assert all(isinstance(x, float) for x in result["embedding"])

From 3819a18ab630c619ae71e839c785c4a398733b0e Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Wed, 11 Sep 2024 19:11:53 +0800
Subject: [PATCH 06/25] fix: resolve lint issues

---
 .../embedders/jina/document_embedder.py          | 16 ++++------------
 .../components/embedders/jina/text_embedder.py   |  6 +-----
 .../jina/tests/test_document_embedder.py         |  2 +-
 3 files changed, 6 insertions(+), 18 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index 2a9345339..8916116c4 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -132,8 +132,8 @@ def _prepare_texts_to_embed(self, documents: List[Document]) -> List[str]:
         return texts_to_embed
 
     def _embed_batch(
-            self, texts_to_embed: List[str], batch_size: int, parameters: Optional[Dict] = None
-        ) -> Tuple[List[List[float]],Dict[str, Any]]:
+        self, texts_to_embed: List[str], batch_size: int, parameters: Optional[Dict] = None
+    ) -> Tuple[List[List[float]],Dict[str, Any]]:
         """
         Embed a list of texts in batches.
         """
@@ -146,11 +146,7 @@ def _embed_batch(
             batch = texts_to_embed[i : i + batch_size]
             response = self._session.post(
                 JINA_API_URL,
-                json={
-                    "input": batch,
-                    "model": self.model_name,
-                    **(parameters if parameters is not None else {})
-                },
+                json={"input": batch, "model": self.model_name, **(parameters if parameters is not None else {})},
             ).json()
             if "data" not in response:
                 raise RuntimeError(response["detail"])
@@ -189,11 +185,7 @@ def run(self, documents: List[Document], parameters: Optional[Dict] = None):
 
         texts_to_embed = self._prepare_texts_to_embed(documents=documents)
 
-        embeddings, metadata = self._embed_batch(
-            texts_to_embed=texts_to_embed,
-            batch_size=self.batch_size,
-            parameters=parameters
-        )
+        embeddings, metadata = self._embed_batch(texts_to_embed=texts_to_embed, batch_size=self.batch_size, parameters=parameters)
 
         for doc, emb in zip(documents, embeddings):
             doc.embedding = emb
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index fcffa5094..8bdfb40e4 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -116,11 +116,7 @@ def run(self, text: str, parameters: Optional[Dict] = None):
 
         resp = self._session.post(
             JINA_API_URL,
-            json={
-                "input": [text_to_embed],
-                "model": self.model_name,
-                **(parameters if parameters is not None else {}),
-            }
+            json={"input": [text_to_embed], "model": self.model_name, **(parameters if parameters is not None else {})},
         ).json()
 
         if "data" not in resp:
diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index e5921c52e..17bb6b7de 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -276,4 +276,4 @@ def test_run_with_v3(self):
             assert isinstance(doc.embedding, list)
             assert len(doc.embedding) == 3
             assert all(isinstance(x, float) for x in doc.embedding)
-        assert metadata == {"model": model, "usage": {"prompt_tokens": 4, "total_tokens": 4}}
\ No newline at end of file
+        assert metadata == {"model": model, "usage": {"prompt_tokens": 4, "total_tokens": 4}}

From e9fa8534a0c318bd74b6eba167394be25679efd3 Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Wed, 11 Sep 2024 19:13:21 +0800
Subject: [PATCH 07/25] fix: resolve lint issues

---
 .../components/embedders/jina/document_embedder.py            | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index 8916116c4..0b2794e47 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -185,7 +185,9 @@ def run(self, documents: List[Document], parameters: Optional[Dict] = None):
 
         texts_to_embed = self._prepare_texts_to_embed(documents=documents)
 
-        embeddings, metadata = self._embed_batch(texts_to_embed=texts_to_embed, batch_size=self.batch_size, parameters=parameters)
+        embeddings, metadata = self._embed_batch(
+            texts_to_embed=texts_to_embed, batch_size=self.batch_size, parameters=parameters
+        )
 
         for doc, emb in zip(documents, embeddings):
             doc.embedding = emb

From 4c02045f3484ad0ae8db740c1f04eed45d0bbf44 Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Wed, 11 Sep 2024 19:14:54 +0800
Subject: [PATCH 08/25] fix: resolve lint issues

---
 .../components/embedders/jina/document_embedder.py              | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index 0b2794e47..38539c7ea 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -133,7 +133,7 @@ def _prepare_texts_to_embed(self, documents: List[Document]) -> List[str]:
 
     def _embed_batch(
         self, texts_to_embed: List[str], batch_size: int, parameters: Optional[Dict] = None
-    ) -> Tuple[List[List[float]],Dict[str, Any]]:
+    ) -> Tuple[List[List[float]], Dict[str, Any]]:
         """
         Embed a list of texts in batches.
         """

From da2238aa12e5adc9b17cc26f9eeb61d4975e5347 Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Wed, 11 Sep 2024 19:26:38 +0800
Subject: [PATCH 09/25] fix: resolve lint issues

---
 integrations/jina/tests/test_document_embedder.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index 17bb6b7de..477c83586 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -253,7 +253,7 @@ def test_run_with_v3(self):
             Document(content="A transformer is a deep learning architecture", meta={"topic": "ML"}),
         ]
 
-        model = "jina-embeddings-v3-base-en"
+        model = "jina-embeddings-v3"
         with patch("requests.sessions.Session.post", side_effect=mock_session_post_response):
             embedder = JinaDocumentEmbedder(
                 api_key=Secret.from_token("fake-api-key"),
@@ -276,4 +276,4 @@ def test_run_with_v3(self):
             assert isinstance(doc.embedding, list)
             assert len(doc.embedding) == 3
             assert all(isinstance(x, float) for x in doc.embedding)
-        assert metadata == {"model": model, "usage": {"prompt_tokens": 4, "total_tokens": 4}}
+        assert metadata == {"model": model, "usage": {"prompt_tokens": 2 * 4, "total_tokens": 2 * 4}}

From 4fe1ca43bcdc2b8841b7ea2d4ab1fdaf17743597 Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Thu, 12 Sep 2024 15:17:09 +0800
Subject: [PATCH 10/25] chore: update JinaEmbedding for v3 release

---
 .../components/embedders/jina/document_embedder.py          | 4 ++--
 .../components/embedders/jina/text_embedder.py              | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index 38539c7ea..62e746759 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -28,7 +28,7 @@ class JinaDocumentEmbedder:
 
     doc = Document(content="I love pizza!")
 
-    result = document_embedder.run([doc])
+    result = document_embedder.run([doc], parameters={"task_type": "retrieval.query"})
     print(result['documents'][0].embedding)
 
     # [0.017020374536514282, -0.023255806416273117, ...]
@@ -38,7 +38,7 @@ class JinaDocumentEmbedder:
     def __init__(
         self,
         api_key: Secret = Secret.from_env_var("JINA_API_KEY"),  # noqa: B008
-        model: str = "jina-embeddings-v2-base-en",
+        model: str = "jina-embeddings-v3",
         prefix: str = "",
         suffix: str = "",
         batch_size: int = 32,
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index 8bdfb40e4..617086d2f 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -25,10 +25,10 @@ class JinaTextEmbedder:
 
     text_to_embed = "I love pizza!"
 
-    print(text_embedder.run(text_to_embed))
+    print(text_embedder.run(text_to_embed), parameters={"task_type": "retrieval.query"})
 
     # {'embedding': [0.017020374536514282, -0.023255806416273117, ...],
-    # 'meta': {'model': 'jina-embeddings-v2-base-en',
+    # 'meta': {'model': 'jina-embeddings-v3',
     #          'usage': {'prompt_tokens': 4, 'total_tokens': 4}}}
     ```
     """
@@ -36,7 +36,7 @@ class JinaTextEmbedder:
     def __init__(
         self,
         api_key: Secret = Secret.from_env_var("JINA_API_KEY"),  # noqa: B008
-        model: str = "jina-embeddings-v2-base-en",
+        model: str = "jina-embeddings-v3",
         prefix: str = "",
         suffix: str = "",
     ):

From d517aa10f0a461c4eba7a85448dfbd50180b173a Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Thu, 12 Sep 2024 16:28:41 +0800
Subject: [PATCH 11/25] fix: resolve test errors

---
 integrations/jina/tests/test_document_embedder.py | 2 +-
 integrations/jina/tests/test_text_embedder.py     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index 477c83586..27316c7c1 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -31,7 +31,7 @@ def test_init_default(self, monkeypatch):
         embedder = JinaDocumentEmbedder()
 
         assert embedder.api_key == Secret.from_env_var("JINA_API_KEY")
-        assert embedder.model_name == "jina-embeddings-v2-base-en"
+        assert embedder.model_name == "jina-embeddings-v3"
         assert embedder.prefix == ""
         assert embedder.suffix == ""
         assert embedder.batch_size == 32
diff --git a/integrations/jina/tests/test_text_embedder.py b/integrations/jina/tests/test_text_embedder.py
index e2f55464b..82fe0139d 100644
--- a/integrations/jina/tests/test_text_embedder.py
+++ b/integrations/jina/tests/test_text_embedder.py
@@ -17,7 +17,7 @@ def test_init_default(self, monkeypatch):
         embedder = JinaTextEmbedder()
 
         assert embedder.api_key == Secret.from_env_var("JINA_API_KEY")
-        assert embedder.model_name == "jina-embeddings-v2-base-en"
+        assert embedder.model_name == "jina-embeddings-v3"
         assert embedder.prefix == ""
         assert embedder.suffix == ""
 

From 9ef324ef864c2547e44a0069ac04de31cd9bccb2 Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Thu, 12 Sep 2024 16:36:08 +0800
Subject: [PATCH 12/25] fix: resolve test errors

---
 integrations/jina/tests/test_document_embedder.py | 2 +-
 integrations/jina/tests/test_text_embedder.py     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index 27316c7c1..06af3a5a2 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -73,7 +73,7 @@ def test_to_dict(self, monkeypatch):
             "type": "haystack_integrations.components.embedders.jina.document_embedder.JinaDocumentEmbedder",
             "init_parameters": {
                 "api_key": {"env_vars": ["JINA_API_KEY"], "strict": True, "type": "env_var"},
-                "model": "jina-embeddings-v2-base-en",
+                "model": "jina-embeddings-v3",
                 "prefix": "",
                 "suffix": "",
                 "batch_size": 32,
diff --git a/integrations/jina/tests/test_text_embedder.py b/integrations/jina/tests/test_text_embedder.py
index 82fe0139d..6ccf77937 100644
--- a/integrations/jina/tests/test_text_embedder.py
+++ b/integrations/jina/tests/test_text_embedder.py
@@ -46,7 +46,7 @@ def test_to_dict(self, monkeypatch):
             "type": "haystack_integrations.components.embedders.jina.text_embedder.JinaTextEmbedder",
             "init_parameters": {
                 "api_key": {"env_vars": ["JINA_API_KEY"], "strict": True, "type": "env_var"},
-                "model": "jina-embeddings-v2-base-en",
+                "model": "jina-embeddings-v3",
                 "prefix": "",
                 "suffix": "",
             },

From f79fa73e91a28a4e9b9ae198b23b1c443496b8c0 Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Thu, 12 Sep 2024 17:18:03 +0800
Subject: [PATCH 13/25] chore: added test case

---
 .../jina/tests/test_document_embedder.py      | 24 +++++++++++++++++++
 integrations/jina/tests/test_text_embedder.py | 15 ++++++++++++
 2 files changed, 39 insertions(+)

diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index 06af3a5a2..0ef992d1f 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -277,3 +277,27 @@ def test_run_with_v3(self):
             assert len(doc.embedding) == 3
             assert all(isinstance(x, float) for x in doc.embedding)
         assert metadata == {"model": model, "usage": {"prompt_tokens": 2 * 4, "total_tokens": 2 * 4}}
+    
+    @patch('requests.sessions.Session.post')
+    def test_run_without_tasktype(self, mock_post):
+        docs = [
+            Document(content="I love cheese", meta={"topic": "Cuisine"}),
+            Document(content="A transformer is a deep learning architecture", meta={"topic": "ML"}),
+        ]
+
+        # Configure the mock to return a response with an error status code
+        mock_post.return_value.status_code = 400
+        mock_post.return_value.json.return_value = {"detail":"Task type parameter is required for jina-embeddings-v3."}
+
+        with pytest.raises(Exception) as excinfo:
+            embedder = JinaDocumentEmbedder(
+                api_key=Secret.from_token("fake-api-key"),
+                prefix="prefix ",
+                suffix=" suffix",
+                meta_fields_to_embed=["topic"],
+                embedding_separator=" | ",
+                batch_size=1,
+            )
+            embedder.run(documents=docs)
+
+        assert "Task type parameter is required for jina-embeddings-v3." in str(excinfo.value)
diff --git a/integrations/jina/tests/test_text_embedder.py b/integrations/jina/tests/test_text_embedder.py
index 6ccf77937..f59db454f 100644
--- a/integrations/jina/tests/test_text_embedder.py
+++ b/integrations/jina/tests/test_text_embedder.py
@@ -135,3 +135,18 @@ def test_with_v3(self):
             "model": "jina-embeddings-v3",
             "usage": {"prompt_tokens": 6, "total_tokens": 6},
         }
+    
+    @patch('requests.sessions.Session.post')
+    def test_run_without_tasktype(self, mock_post):
+
+        # Configure the mock to return a response with an error status code
+        mock_post.return_value.status_code = 400
+        mock_post.return_value.json.return_value = {"detail":"Task type parameter is required for jina-embeddings-v3."}
+
+        with pytest.raises(Exception) as excinfo:
+            embedder = JinaTextEmbedder(
+                api_key=Secret.from_token("fake-api-key"), prefix="prefix ", suffix=" suffix",
+            )
+            embedder.run(text="The food was delicious")
+
+        assert "Task type parameter is required for jina-embeddings-v3." in str(excinfo.value)

From cfb18eeea92c2942cdbf26f5f8e0bee82f801b0f Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Thu, 12 Sep 2024 17:29:22 +0800
Subject: [PATCH 14/25] fix: resolve lint issues

---
 integrations/jina/tests/test_document_embedder.py | 4 ++--
 integrations/jina/tests/test_text_embedder.py     | 8 +++++---
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index 0ef992d1f..b46a6f4d5 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -277,7 +277,7 @@ def test_run_with_v3(self):
             assert len(doc.embedding) == 3
             assert all(isinstance(x, float) for x in doc.embedding)
         assert metadata == {"model": model, "usage": {"prompt_tokens": 2 * 4, "total_tokens": 2 * 4}}
-    
+
     @patch('requests.sessions.Session.post')
     def test_run_without_tasktype(self, mock_post):
         docs = [
@@ -287,7 +287,7 @@ def test_run_without_tasktype(self, mock_post):
 
         # Configure the mock to return a response with an error status code
         mock_post.return_value.status_code = 400
-        mock_post.return_value.json.return_value = {"detail":"Task type parameter is required for jina-embeddings-v3."}
+        mock_post.return_value.json.return_value = {"detail": "Task type parameter is required for jina-embeddings-v3."}
 
         with pytest.raises(Exception) as excinfo:
             embedder = JinaDocumentEmbedder(
diff --git a/integrations/jina/tests/test_text_embedder.py b/integrations/jina/tests/test_text_embedder.py
index f59db454f..5ab3d6b50 100644
--- a/integrations/jina/tests/test_text_embedder.py
+++ b/integrations/jina/tests/test_text_embedder.py
@@ -135,17 +135,19 @@ def test_with_v3(self):
             "model": "jina-embeddings-v3",
             "usage": {"prompt_tokens": 6, "total_tokens": 6},
         }
-    
+
     @patch('requests.sessions.Session.post')
     def test_run_without_tasktype(self, mock_post):
 
         # Configure the mock to return a response with an error status code
         mock_post.return_value.status_code = 400
-        mock_post.return_value.json.return_value = {"detail":"Task type parameter is required for jina-embeddings-v3."}
+        mock_post.return_value.json.return_value = {"detail": "Task type parameter is required for jina-embeddings-v3."}
 
         with pytest.raises(Exception) as excinfo:
             embedder = JinaTextEmbedder(
-                api_key=Secret.from_token("fake-api-key"), prefix="prefix ", suffix=" suffix",
+                api_key=Secret.from_token("fake-api-key"),
+                prefix="prefix ",
+                suffix=" suffix",
             )
             embedder.run(text="The food was delicious")
 

From 531433f624dab1f02027d18fc7686ce0c2bd7ecf Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Fri, 13 Sep 2024 13:26:40 +0800
Subject: [PATCH 15/25] fix: update function call

---
 .../embedders/jina/document_embedder.py       | 40 +++++++++++++------
 .../embedders/jina/text_embedder.py           | 29 +++++++++++---
 .../jina/tests/test_document_embedder.py      | 11 ++++-
 integrations/jina/tests/test_text_embedder.py | 13 ++++--
 4 files changed, 71 insertions(+), 22 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index 62e746759..f6e922b64 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -45,6 +45,8 @@ def __init__(
         progress_bar: bool = True,
         meta_fields_to_embed: Optional[List[str]] = None,
         embedding_separator: str = "\n",
+        task_type: Optional[str] = None,
+        dimensions: Optional[int] = None,
     ):
         """
         Create a JinaDocumentEmbedder component.
@@ -78,6 +80,8 @@ def __init__(
                 "Content-type": "application/json",
             }
         )
+        self.task_type = task_type
+        self.dimensions = dimensions
 
     def _get_telemetry_data(self) -> Dict[str, Any]:
         """
@@ -91,17 +95,23 @@ def to_dict(self) -> Dict[str, Any]:
         :returns:
             Dictionary with serialized data.
         """
-        return default_to_dict(
-            self,
-            api_key=self.api_key.to_dict(),
-            model=self.model_name,
-            prefix=self.prefix,
-            suffix=self.suffix,
-            batch_size=self.batch_size,
-            progress_bar=self.progress_bar,
-            meta_fields_to_embed=self.meta_fields_to_embed,
-            embedding_separator=self.embedding_separator,
-        )
+        kwargs = {
+            "api_key": self.api_key.to_dict(),
+            "model": self.model_name,
+            "prefix": self.prefix,
+            "suffix": self.suffix,
+            "batch_size": self.batch_size,
+            "progress_bar": self.progress_bar,
+            "meta_fields_to_embed": self.meta_fields_to_embed,
+            "embedding_separator": self.embedding_separator,
+        }
+        # Optional parameters, the following two are only supported by embeddings-v3 for now
+        if self.task_type:
+            kwargs["task_type"] = self.task_type
+        if self.dimensions:
+            kwargs["dimensions"] = self.dimensions
+
+        return default_to_dict(self, **kwargs)
 
     @classmethod
     def from_dict(cls, data: Dict[str, Any]) -> "JinaDocumentEmbedder":
@@ -166,7 +176,7 @@ def _embed_batch(
         return all_embeddings, metadata
 
     @component.output_types(documents=List[Document], meta=Dict[str, Any])
-    def run(self, documents: List[Document], parameters: Optional[Dict] = None):
+    def run(self, documents: List[Document]):
         """
         Compute the embeddings for a list of Documents.
 
@@ -184,7 +194,11 @@ def run(self, documents: List[Document], parameters: Optional[Dict] = None):
             raise TypeError(msg)
 
         texts_to_embed = self._prepare_texts_to_embed(documents=documents)
-
+        parameters = {}
+        if self.task_type:
+            parameters["task_type"] = self.task_type
+        if self.dimensions:
+            parameters["dimensions"] = self.dimensions
         embeddings, metadata = self._embed_batch(
             texts_to_embed=texts_to_embed, batch_size=self.batch_size, parameters=parameters
         )
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index 617086d2f..71ad72a2b 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -39,6 +39,8 @@ def __init__(
         model: str = "jina-embeddings-v3",
         prefix: str = "",
         suffix: str = "",
+        task_type: Optional[str] = None,
+        dimensions: Optional[int] = None,
     ):
         """
         Create a JinaTextEmbedder component.
@@ -65,6 +67,8 @@ def __init__(
                 "Content-type": "application/json",
             }
         )
+        self.task_type = task_type
+        self.dimensions = dimensions
 
     def _get_telemetry_data(self) -> Dict[str, Any]:
         """
@@ -78,9 +82,18 @@ def to_dict(self) -> Dict[str, Any]:
         :returns:
             Dictionary with serialized data.
         """
-        return default_to_dict(
-            self, api_key=self.api_key.to_dict(), model=self.model_name, prefix=self.prefix, suffix=self.suffix
-        )
+        kwargs = {
+            "api_key": self.api_key.to_dict(),
+            "model": self.model_name,
+            "prefix": self.prefix,
+            "suffix": self.suffix,
+        }
+        # Optional parameters, the following two are only supported by embeddings-v3 for now
+        if self.task_type:
+            kwargs["task_type"] = self.task_type
+        if self.dimensions:
+            kwargs["dimensions"] = self.dimensions
+        return default_to_dict(self, **kwargs)
 
     @classmethod
     def from_dict(cls, data: Dict[str, Any]) -> "JinaTextEmbedder":
@@ -95,7 +108,7 @@ def from_dict(cls, data: Dict[str, Any]) -> "JinaTextEmbedder":
         return default_from_dict(cls, data)
 
     @component.output_types(embedding=List[float], meta=Dict[str, Any])
-    def run(self, text: str, parameters: Optional[Dict] = None):
+    def run(self, text: str):
         """
         Embed a string.
 
@@ -114,9 +127,15 @@ def run(self, text: str, parameters: Optional[Dict] = None):
 
         text_to_embed = self.prefix + text + self.suffix
 
+        parameters = {}
+        if self.task_type is not None:
+            parameters["task_type"] = self.task_type
+        if self.dimensions is not None:
+            parameters["dimensions"] = self.dimensions
+
         resp = self._session.post(
             JINA_API_URL,
-            json={"input": [text_to_embed], "model": self.model_name, **(parameters if parameters is not None else {})},
+            json={"input": [text_to_embed], "model": self.model_name, **parameters},
         ).json()
 
         if "data" not in resp:
diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index b46a6f4d5..ff4ad6042 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -49,6 +49,8 @@ def test_init_with_parameters(self):
             progress_bar=False,
             meta_fields_to_embed=["test_field"],
             embedding_separator=" | ",
+            task_type="retrieval.query",
+            dimensions=1024,
         )
 
         assert embedder.api_key == Secret.from_token("fake-api-key")
@@ -59,6 +61,8 @@ def test_init_with_parameters(self):
         assert embedder.progress_bar is False
         assert embedder.meta_fields_to_embed == ["test_field"]
         assert embedder.embedding_separator == " | "
+        assert embedder.task_type == "retrieval.query"
+        assert embedder.dimensions == 1024
 
     def test_init_fail_wo_api_key(self, monkeypatch):
         monkeypatch.delenv("JINA_API_KEY", raising=False)
@@ -93,6 +97,8 @@ def test_to_dict_with_custom_init_parameters(self, monkeypatch):
             progress_bar=False,
             meta_fields_to_embed=["test_field"],
             embedding_separator=" | ",
+            task_type="retrieval.query",
+            dimensions=1024,
         )
         data = component.to_dict()
         assert data == {
@@ -106,6 +112,8 @@ def test_to_dict_with_custom_init_parameters(self, monkeypatch):
                 "progress_bar": False,
                 "meta_fields_to_embed": ["test_field"],
                 "embedding_separator": " | ",
+                "task_type": "retrieval.query",
+                "dimensions": 1024,
             },
         }
 
@@ -263,8 +271,9 @@ def test_run_with_v3(self):
                 meta_fields_to_embed=["topic"],
                 embedding_separator=" | ",
                 batch_size=1,
+                task_type="retrieval.query"
             )
-            result = embedder.run(documents=docs, parameters={"task_type": "retrieval.passage"})
+            result = embedder.run(documents=docs)
 
         documents_with_embeddings = result["documents"]
         metadata = result["meta"]
diff --git a/integrations/jina/tests/test_text_embedder.py b/integrations/jina/tests/test_text_embedder.py
index 5ab3d6b50..10c4185ac 100644
--- a/integrations/jina/tests/test_text_embedder.py
+++ b/integrations/jina/tests/test_text_embedder.py
@@ -10,7 +10,6 @@
 
 from haystack_integrations.components.embedders.jina import JinaTextEmbedder
 
-
 class TestJinaTextEmbedder:
     def test_init_default(self, monkeypatch):
         monkeypatch.setenv("JINA_API_KEY", "fake-api-key")
@@ -58,6 +57,8 @@ def test_to_dict_with_custom_init_parameters(self, monkeypatch):
             model="model",
             prefix="prefix",
             suffix="suffix",
+            task_type="retrieval.query",
+            dimensions=1024,
         )
         data = component.to_dict()
         assert data == {
@@ -67,6 +68,8 @@ def test_to_dict_with_custom_init_parameters(self, monkeypatch):
                 "model": "model",
                 "prefix": "prefix",
                 "suffix": "suffix",
+                "task_type": "retrieval.query",
+                "dimensions": 1024,
             },
         }
 
@@ -125,9 +128,13 @@ def test_with_v3(self):
             mock_post.return_value = mock_response
 
             embedder = JinaTextEmbedder(
-                api_key=Secret.from_token("fake-api-key"), model=model, prefix="prefix ", suffix=" suffix"
+                api_key=Secret.from_token("fake-api-key"),
+                model=model,
+                prefix="prefix ",
+                suffix=" suffix",
+                task_type="retrieval.query"
             )
-            result = embedder.run(text="The food was delicious", parameters={"task_type": "retrieval.passage"})
+            result = embedder.run(text="The food was delicious")
 
         assert len(result["embedding"]) == 3
         assert all(isinstance(x, float) for x in result["embedding"])

From c039af7b696dc49b1112813bb41004d18010da99 Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Fri, 13 Sep 2024 13:33:52 +0800
Subject: [PATCH 16/25] fix: resolve lint issues

---
 integrations/jina/tests/test_document_embedder.py | 2 +-
 integrations/jina/tests/test_text_embedder.py     | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index ff4ad6042..7537d4e3a 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -271,7 +271,7 @@ def test_run_with_v3(self):
                 meta_fields_to_embed=["topic"],
                 embedding_separator=" | ",
                 batch_size=1,
-                task_type="retrieval.query"
+                task_type="retrieval.query",
             )
             result = embedder.run(documents=docs)
 
diff --git a/integrations/jina/tests/test_text_embedder.py b/integrations/jina/tests/test_text_embedder.py
index 10c4185ac..fc89f78ba 100644
--- a/integrations/jina/tests/test_text_embedder.py
+++ b/integrations/jina/tests/test_text_embedder.py
@@ -10,6 +10,7 @@
 
 from haystack_integrations.components.embedders.jina import JinaTextEmbedder
 
+
 class TestJinaTextEmbedder:
     def test_init_default(self, monkeypatch):
         monkeypatch.setenv("JINA_API_KEY", "fake-api-key")
@@ -132,7 +133,7 @@ def test_with_v3(self):
                 model=model,
                 prefix="prefix ",
                 suffix=" suffix",
-                task_type="retrieval.query"
+                task_type="retrieval.query",
             )
             result = embedder.run(text="The food was delicious")
 

From 38781cbd37ada48438ceab41fc61c33221761752 Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Fri, 13 Sep 2024 14:17:46 +0800
Subject: [PATCH 17/25] fix: lint error

---
 .../components/embedders/jina/document_embedder.py              | 2 +-
 .../components/embedders/jina/text_embedder.py                  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index f6e922b64..2dd7765d2 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -194,7 +194,7 @@ def run(self, documents: List[Document]):
             raise TypeError(msg)
 
         texts_to_embed = self._prepare_texts_to_embed(documents=documents)
-        parameters = {}
+        parameters: Dict[str, any] = {}
         if self.task_type:
             parameters["task_type"] = self.task_type
         if self.dimensions:
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index 71ad72a2b..d74f44a4b 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -127,7 +127,7 @@ def run(self, text: str):
 
         text_to_embed = self.prefix + text + self.suffix
 
-        parameters = {}
+        parameters: Dict[str, any] = {}
         if self.task_type is not None:
             parameters["task_type"] = self.task_type
         if self.dimensions is not None:

From c2d80f01717a5a1bd5f6770221cf29fda58762b9 Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Fri, 13 Sep 2024 14:20:46 +0800
Subject: [PATCH 18/25] fix: lint error

---
 .../components/embedders/jina/document_embedder.py              | 2 +-
 .../components/embedders/jina/text_embedder.py                  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index 2dd7765d2..0e5c06459 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -194,7 +194,7 @@ def run(self, documents: List[Document]):
             raise TypeError(msg)
 
         texts_to_embed = self._prepare_texts_to_embed(documents=documents)
-        parameters: Dict[str, any] = {}
+        parameters: Dict[str, Any] = {}
         if self.task_type:
             parameters["task_type"] = self.task_type
         if self.dimensions:
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index d74f44a4b..e51652ecb 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -127,7 +127,7 @@ def run(self, text: str):
 
         text_to_embed = self.prefix + text + self.suffix
 
-        parameters: Dict[str, any] = {}
+        parameters: Dict[str, Any] = {}
         if self.task_type is not None:
             parameters["task_type"] = self.task_type
         if self.dimensions is not None:

From 86cc89251c1bd72ed4aa61063ab40897e7755cf8 Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Fri, 13 Sep 2024 17:09:16 +0800
Subject: [PATCH 19/25] chore: remove unnecessary test cases

---
 .../jina/tests/test_document_embedder.py      | 24 -------------------
 integrations/jina/tests/test_text_embedder.py | 17 -------------
 2 files changed, 41 deletions(-)

diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index 7537d4e3a..19311a1a6 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -286,27 +286,3 @@ def test_run_with_v3(self):
             assert len(doc.embedding) == 3
             assert all(isinstance(x, float) for x in doc.embedding)
         assert metadata == {"model": model, "usage": {"prompt_tokens": 2 * 4, "total_tokens": 2 * 4}}
-
-    @patch('requests.sessions.Session.post')
-    def test_run_without_tasktype(self, mock_post):
-        docs = [
-            Document(content="I love cheese", meta={"topic": "Cuisine"}),
-            Document(content="A transformer is a deep learning architecture", meta={"topic": "ML"}),
-        ]
-
-        # Configure the mock to return a response with an error status code
-        mock_post.return_value.status_code = 400
-        mock_post.return_value.json.return_value = {"detail": "Task type parameter is required for jina-embeddings-v3."}
-
-        with pytest.raises(Exception) as excinfo:
-            embedder = JinaDocumentEmbedder(
-                api_key=Secret.from_token("fake-api-key"),
-                prefix="prefix ",
-                suffix=" suffix",
-                meta_fields_to_embed=["topic"],
-                embedding_separator=" | ",
-                batch_size=1,
-            )
-            embedder.run(documents=docs)
-
-        assert "Task type parameter is required for jina-embeddings-v3." in str(excinfo.value)
diff --git a/integrations/jina/tests/test_text_embedder.py b/integrations/jina/tests/test_text_embedder.py
index fc89f78ba..26280689e 100644
--- a/integrations/jina/tests/test_text_embedder.py
+++ b/integrations/jina/tests/test_text_embedder.py
@@ -143,20 +143,3 @@ def test_with_v3(self):
             "model": "jina-embeddings-v3",
             "usage": {"prompt_tokens": 6, "total_tokens": 6},
         }
-
-    @patch('requests.sessions.Session.post')
-    def test_run_without_tasktype(self, mock_post):
-
-        # Configure the mock to return a response with an error status code
-        mock_post.return_value.status_code = 400
-        mock_post.return_value.json.return_value = {"detail": "Task type parameter is required for jina-embeddings-v3."}
-
-        with pytest.raises(Exception) as excinfo:
-            embedder = JinaTextEmbedder(
-                api_key=Secret.from_token("fake-api-key"),
-                prefix="prefix ",
-                suffix=" suffix",
-            )
-            embedder.run(text="The food was delicious")
-
-        assert "Task type parameter is required for jina-embeddings-v3." in str(excinfo.value)

From 5847efb4508884123e7d86d8027117de43eeded4 Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Wed, 18 Sep 2024 09:14:29 +0800
Subject: [PATCH 20/25] chore: use 'task' instead of 'task_type'

---
 .../embedders/jina/document_embedder.py          | 16 ++++++++--------
 .../components/embedders/jina/text_embedder.py   | 16 ++++++++--------
 .../jina/tests/test_document_embedder.py         | 10 +++++-----
 integrations/jina/tests/test_text_embedder.py    |  6 +++---
 4 files changed, 24 insertions(+), 24 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index 0e5c06459..dc4240f9a 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -24,11 +24,11 @@ class JinaDocumentEmbedder:
 
     # Make sure that the environment variable JINA_API_KEY is set
 
-    document_embedder = JinaDocumentEmbedder()
+    document_embedder = JinaDocumentEmbedder(task="retrieval.query")
 
     doc = Document(content="I love pizza!")
 
-    result = document_embedder.run([doc], parameters={"task_type": "retrieval.query"})
+    result = document_embedder.run([doc])
     print(result['documents'][0].embedding)
 
     # [0.017020374536514282, -0.023255806416273117, ...]
@@ -45,7 +45,7 @@ def __init__(
         progress_bar: bool = True,
         meta_fields_to_embed: Optional[List[str]] = None,
         embedding_separator: str = "\n",
-        task_type: Optional[str] = None,
+        task: Optional[str] = None,
         dimensions: Optional[int] = None,
     ):
         """
@@ -80,7 +80,7 @@ def __init__(
                 "Content-type": "application/json",
             }
         )
-        self.task_type = task_type
+        self.task = task
         self.dimensions = dimensions
 
     def _get_telemetry_data(self) -> Dict[str, Any]:
@@ -106,8 +106,8 @@ def to_dict(self) -> Dict[str, Any]:
             "embedding_separator": self.embedding_separator,
         }
         # Optional parameters, the following two are only supported by embeddings-v3 for now
-        if self.task_type:
-            kwargs["task_type"] = self.task_type
+        if self.task:
+            kwargs["task"] = self.task
         if self.dimensions:
             kwargs["dimensions"] = self.dimensions
 
@@ -195,8 +195,8 @@ def run(self, documents: List[Document]):
 
         texts_to_embed = self._prepare_texts_to_embed(documents=documents)
         parameters: Dict[str, Any] = {}
-        if self.task_type:
-            parameters["task_type"] = self.task_type
+        if self.task:
+            parameters["task"] = self.task
         if self.dimensions:
             parameters["dimensions"] = self.dimensions
         embeddings, metadata = self._embed_batch(
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index e51652ecb..05840220f 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -21,11 +21,11 @@ class JinaTextEmbedder:
 
     # Make sure that the environment variable JINA_API_KEY is set
 
-    text_embedder = JinaTextEmbedder()
+    text_embedder = JinaTextEmbedder(task="retrieval.query")
 
     text_to_embed = "I love pizza!"
 
-    print(text_embedder.run(text_to_embed), parameters={"task_type": "retrieval.query"})
+    print(text_embedder.run(text_to_embed))
 
     # {'embedding': [0.017020374536514282, -0.023255806416273117, ...],
     # 'meta': {'model': 'jina-embeddings-v3',
@@ -39,7 +39,7 @@ def __init__(
         model: str = "jina-embeddings-v3",
         prefix: str = "",
         suffix: str = "",
-        task_type: Optional[str] = None,
+        task: Optional[str] = None,
         dimensions: Optional[int] = None,
     ):
         """
@@ -67,7 +67,7 @@ def __init__(
                 "Content-type": "application/json",
             }
         )
-        self.task_type = task_type
+        self.task = task
         self.dimensions = dimensions
 
     def _get_telemetry_data(self) -> Dict[str, Any]:
@@ -89,8 +89,8 @@ def to_dict(self) -> Dict[str, Any]:
             "suffix": self.suffix,
         }
         # Optional parameters, the following two are only supported by embeddings-v3 for now
-        if self.task_type:
-            kwargs["task_type"] = self.task_type
+        if self.task:
+            kwargs["task"] = self.task
         if self.dimensions:
             kwargs["dimensions"] = self.dimensions
         return default_to_dict(self, **kwargs)
@@ -128,8 +128,8 @@ def run(self, text: str):
         text_to_embed = self.prefix + text + self.suffix
 
         parameters: Dict[str, Any] = {}
-        if self.task_type is not None:
-            parameters["task_type"] = self.task_type
+        if self.task is not None:
+            parameters["task"] = self.task
         if self.dimensions is not None:
             parameters["dimensions"] = self.dimensions
 
diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index 19311a1a6..78339a1c8 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -49,7 +49,7 @@ def test_init_with_parameters(self):
             progress_bar=False,
             meta_fields_to_embed=["test_field"],
             embedding_separator=" | ",
-            task_type="retrieval.query",
+            task="retrieval.query",
             dimensions=1024,
         )
 
@@ -61,7 +61,7 @@ def test_init_with_parameters(self):
         assert embedder.progress_bar is False
         assert embedder.meta_fields_to_embed == ["test_field"]
         assert embedder.embedding_separator == " | "
-        assert embedder.task_type == "retrieval.query"
+        assert embedder.task == "retrieval.query"
         assert embedder.dimensions == 1024
 
     def test_init_fail_wo_api_key(self, monkeypatch):
@@ -97,7 +97,7 @@ def test_to_dict_with_custom_init_parameters(self, monkeypatch):
             progress_bar=False,
             meta_fields_to_embed=["test_field"],
             embedding_separator=" | ",
-            task_type="retrieval.query",
+            task="retrieval.query",
             dimensions=1024,
         )
         data = component.to_dict()
@@ -112,7 +112,7 @@ def test_to_dict_with_custom_init_parameters(self, monkeypatch):
                 "progress_bar": False,
                 "meta_fields_to_embed": ["test_field"],
                 "embedding_separator": " | ",
-                "task_type": "retrieval.query",
+                "task": "retrieval.query",
                 "dimensions": 1024,
             },
         }
@@ -271,7 +271,7 @@ def test_run_with_v3(self):
                 meta_fields_to_embed=["topic"],
                 embedding_separator=" | ",
                 batch_size=1,
-                task_type="retrieval.query",
+                task="retrieval.query",
             )
             result = embedder.run(documents=docs)
 
diff --git a/integrations/jina/tests/test_text_embedder.py b/integrations/jina/tests/test_text_embedder.py
index 26280689e..a4623c698 100644
--- a/integrations/jina/tests/test_text_embedder.py
+++ b/integrations/jina/tests/test_text_embedder.py
@@ -58,7 +58,7 @@ def test_to_dict_with_custom_init_parameters(self, monkeypatch):
             model="model",
             prefix="prefix",
             suffix="suffix",
-            task_type="retrieval.query",
+            task="retrieval.query",
             dimensions=1024,
         )
         data = component.to_dict()
@@ -69,7 +69,7 @@ def test_to_dict_with_custom_init_parameters(self, monkeypatch):
                 "model": "model",
                 "prefix": "prefix",
                 "suffix": "suffix",
-                "task_type": "retrieval.query",
+                "task": "retrieval.query",
                 "dimensions": 1024,
             },
         }
@@ -133,7 +133,7 @@ def test_with_v3(self):
                 model=model,
                 prefix="prefix ",
                 suffix=" suffix",
-                task_type="retrieval.query",
+                task="retrieval.query",
             )
             result = embedder.run(text="The food was delicious")
 

From 9e01dd53496948e31c009ad1cb447f0158387d1d Mon Sep 17 00:00:00 2001
From: Aaron Ji <aaron.hui.ji@outlook.com>
Date: Wed, 18 Sep 2024 10:07:02 +0800
Subject: [PATCH 21/25] chore: add 'late_chunking' for Jina embedders

---
 .../components/embedders/jina/document_embedder.py          | 6 ++++++
 .../components/embedders/jina/text_embedder.py              | 6 ++++++
 integrations/jina/tests/test_document_embedder.py           | 2 ++
 integrations/jina/tests/test_text_embedder.py               | 2 ++
 4 files changed, 16 insertions(+)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index dc4240f9a..be7b98d07 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -47,6 +47,7 @@ def __init__(
         embedding_separator: str = "\n",
         task: Optional[str] = None,
         dimensions: Optional[int] = None,
+        late_chunking: Optional[bool] = None,
     ):
         """
         Create a JinaDocumentEmbedder component.
@@ -82,6 +83,7 @@ def __init__(
         )
         self.task = task
         self.dimensions = dimensions
+        self.late_chunking = late_chunking
 
     def _get_telemetry_data(self) -> Dict[str, Any]:
         """
@@ -110,6 +112,8 @@ def to_dict(self) -> Dict[str, Any]:
             kwargs["task"] = self.task
         if self.dimensions:
             kwargs["dimensions"] = self.dimensions
+        if self.late_chunking is not None:
+            kwargs["late_chunking"] = self.late_chunking
 
         return default_to_dict(self, **kwargs)
 
@@ -199,6 +203,8 @@ def run(self, documents: List[Document]):
             parameters["task"] = self.task
         if self.dimensions:
             parameters["dimensions"] = self.dimensions
+        if self.late_chunking is not None:
+            parameters["late_chunking"] = self.late_chunking
         embeddings, metadata = self._embed_batch(
             texts_to_embed=texts_to_embed, batch_size=self.batch_size, parameters=parameters
         )
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index 05840220f..4bcdbc71c 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -41,6 +41,7 @@ def __init__(
         suffix: str = "",
         task: Optional[str] = None,
         dimensions: Optional[int] = None,
+        late_chunking: Optional[bool] = None,
     ):
         """
         Create a JinaTextEmbedder component.
@@ -69,6 +70,7 @@ def __init__(
         )
         self.task = task
         self.dimensions = dimensions
+        self.late_chunking = late_chunking
 
     def _get_telemetry_data(self) -> Dict[str, Any]:
         """
@@ -93,6 +95,8 @@ def to_dict(self) -> Dict[str, Any]:
             kwargs["task"] = self.task
         if self.dimensions:
             kwargs["dimensions"] = self.dimensions
+        if self.late_chunking is not None:
+            kwargs["late_chunking"] = self.late_chunking
         return default_to_dict(self, **kwargs)
 
     @classmethod
@@ -132,6 +136,8 @@ def run(self, text: str):
             parameters["task"] = self.task
         if self.dimensions is not None:
             parameters["dimensions"] = self.dimensions
+        if self.late_chunking is not None:
+            parameters["late_chunking"] = self.late_chunking
 
         resp = self._session.post(
             JINA_API_URL,
diff --git a/integrations/jina/tests/test_document_embedder.py b/integrations/jina/tests/test_document_embedder.py
index 78339a1c8..247b95eff 100644
--- a/integrations/jina/tests/test_document_embedder.py
+++ b/integrations/jina/tests/test_document_embedder.py
@@ -51,6 +51,7 @@ def test_init_with_parameters(self):
             embedding_separator=" | ",
             task="retrieval.query",
             dimensions=1024,
+            late_chunking=True,
         )
 
         assert embedder.api_key == Secret.from_token("fake-api-key")
@@ -63,6 +64,7 @@ def test_init_with_parameters(self):
         assert embedder.embedding_separator == " | "
         assert embedder.task == "retrieval.query"
         assert embedder.dimensions == 1024
+        assert embedder.late_chunking is True
 
     def test_init_fail_wo_api_key(self, monkeypatch):
         monkeypatch.delenv("JINA_API_KEY", raising=False)
diff --git a/integrations/jina/tests/test_text_embedder.py b/integrations/jina/tests/test_text_embedder.py
index a4623c698..058712a18 100644
--- a/integrations/jina/tests/test_text_embedder.py
+++ b/integrations/jina/tests/test_text_embedder.py
@@ -27,11 +27,13 @@ def test_init_with_parameters(self):
             model="model",
             prefix="prefix",
             suffix="suffix",
+            late_chunking=True,
         )
         assert embedder.api_key == Secret.from_token("fake-api-key")
         assert embedder.model_name == "model"
         assert embedder.prefix == "prefix"
         assert embedder.suffix == "suffix"
+        assert embedder.late_chunking is True
 
     def test_init_fail_wo_api_key(self, monkeypatch):
         monkeypatch.delenv("JINA_API_KEY", raising=False)

From 689586024df58a9aecb700f4bc287e16dfb62664 Mon Sep 17 00:00:00 2001
From: Aaron Ji <127167174+DresAaron@users.noreply.github.com>
Date: Wed, 18 Sep 2024 15:47:49 +0800
Subject: [PATCH 22/25] Update
 integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
---
 .../components/embedders/jina/document_embedder.py            | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index be7b98d07..bcfe88a6a 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -199,9 +199,9 @@ def run(self, documents: List[Document]):
 
         texts_to_embed = self._prepare_texts_to_embed(documents=documents)
         parameters: Dict[str, Any] = {}
-        if self.task:
+        if self.task is not None:
             parameters["task"] = self.task
-        if self.dimensions:
+        if self.dimensions is not None:
             parameters["dimensions"] = self.dimensions
         if self.late_chunking is not None:
             parameters["late_chunking"] = self.late_chunking

From 048f7a66d5eca473ac4d6b1186ac3fa2972f8906 Mon Sep 17 00:00:00 2001
From: Aaron Ji <127167174+DresAaron@users.noreply.github.com>
Date: Wed, 18 Sep 2024 15:47:57 +0800
Subject: [PATCH 23/25] Update
 integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
---
 .../components/embedders/jina/document_embedder.py            | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index bcfe88a6a..50ac77fe8 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -108,9 +108,9 @@ def to_dict(self) -> Dict[str, Any]:
             "embedding_separator": self.embedding_separator,
         }
         # Optional parameters, the following two are only supported by embeddings-v3 for now
-        if self.task:
+        if self.task is not None:
             kwargs["task"] = self.task
-        if self.dimensions:
+        if self.dimensions is not None:
             kwargs["dimensions"] = self.dimensions
         if self.late_chunking is not None:
             kwargs["late_chunking"] = self.late_chunking

From c0bccaa8b76d1667304f7f4ffec7527a201d824b Mon Sep 17 00:00:00 2001
From: Aaron Ji <127167174+DresAaron@users.noreply.github.com>
Date: Wed, 18 Sep 2024 15:51:37 +0800
Subject: [PATCH 24/25] Update
 integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
---
 .../components/embedders/jina/document_embedder.py              | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
index 50ac77fe8..bbac547c3 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -160,7 +160,7 @@ def _embed_batch(
             batch = texts_to_embed[i : i + batch_size]
             response = self._session.post(
                 JINA_API_URL,
-                json={"input": batch, "model": self.model_name, **(parameters if parameters is not None else {})},
+                json={"input": batch, "model": self.model_name, **(parameters or {})},
             ).json()
             if "data" not in response:
                 raise RuntimeError(response["detail"])

From 3d45a2cb78e2785d53528cf7ac7a41d449326a8f Mon Sep 17 00:00:00 2001
From: Aaron Ji <127167174+DresAaron@users.noreply.github.com>
Date: Wed, 18 Sep 2024 15:51:50 +0800
Subject: [PATCH 25/25] Update
 integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py

Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
---
 .../components/embedders/jina/text_embedder.py                | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
index 4bcdbc71c..c22f9ea2c 100644
--- a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
+++ b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -91,9 +91,9 @@ def to_dict(self) -> Dict[str, Any]:
             "suffix": self.suffix,
         }
         # Optional parameters, the following two are only supported by embeddings-v3 for now
-        if self.task:
+        if self.task is not None:
             kwargs["task"] = self.task
-        if self.dimensions:
+        if self.dimensions is not None:
             kwargs["dimensions"] = self.dimensions
         if self.late_chunking is not None:
             kwargs["late_chunking"] = self.late_chunking