fastembed-haystack 0.1.0__tar.gz → 1.0.0__tar.gz

{fastembed_haystack-0.1.0 → fastembed_haystack-1.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: fastembed-haystack
-Version: 0.1.0
+Version: 1.0.0
 Summary: Haystack 2.x component to embed strings and Documents using fastembed embedding model
 Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/fastembed/README.md
@@ -9,6 +9,7 @@ Author-email: deepset GmbH <info@deepset.ai>
 License-Expression: Apache-2.0
 License-File: LICENSE.txt
 Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9

{fastembed_haystack-0.1.0 → fastembed_haystack-1.0.0}/pyproject.toml

@@ -14,6 +14,7 @@ authors = [
   { name = "deepset GmbH", email = "info@deepset.ai" },
 ]
 classifiers = [
+  "License :: OSI Approved :: Apache Software License",
   "Development Status :: 4 - Beta",
   "Programming Language :: Python",
   "Programming Language :: Python :: 3.8",

{fastembed_haystack-0.1.0 → fastembed_haystack-1.0.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_document_embedder.py

@@ -29,14 +29,18 @@ class FastembedDocumentEmbedder:
     # Text taken from PubMed QA Dataset (https://huggingface.co/datasets/pubmed_qa)
     document_list = [
         Document(
-            content="Oxidative stress generated within inflammatory joints can produce autoimmune phenomena and joint destruction. Radical species with oxidative activity, including reactive nitrogen species, represent mediators of inflammation and cartilage damage.",
+            content=("Oxidative stress generated within inflammatory joints can produce autoimmune phenomena and joint "
+                     "destruction. Radical species with oxidative activity, including reactive nitrogen species, "
+                     "represent mediators of inflammation and cartilage damage."),
             meta={
                 "pubid": "25,445,628",
                 "long_answer": "yes",
             },
         ),
         Document(
-            content="Plasma levels of pancreatic polypeptide (PP) rise upon food intake. Although other pancreatic islet hormones, such as insulin and glucagon, have been extensively investigated, PP secretion and actions are still poorly understood.",
+            content=("Plasma levels of pancreatic polypeptide (PP) rise upon food intake. Although other pancreatic "
+                     "islet hormones, such as insulin and glucagon, have been extensively investigated, PP secretion "
+                     "and actions are still poorly understood."),
             meta={
                 "pubid": "25,445,712",
                 "long_answer": "yes",
@@ -49,7 +53,7 @@ class FastembedDocumentEmbedder:
     print(f"Document Embedding: {result['documents'][0].embedding}")
     print(f"Embedding Dimension: {len(result['documents'][0].embedding)}")
     ```
-    """  # noqa: E501
+    """
 
     def __init__(
         self,

{fastembed_haystack-0.1.0 → fastembed_haystack-1.0.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_sparse_document_embedder.py

@@ -12,30 +12,31 @@ class FastembedSparseDocumentEmbedder:
 
     Usage example:
     ```python
-    # To use this component, install the "fastembed-haystack" package.
-    # pip install fastembed-haystack
-
     from haystack_integrations.components.embedders.fastembed import FastembedSparseDocumentEmbedder
     from haystack.dataclasses import Document
 
-    doc_embedder = FastembedSparseDocumentEmbedder(
+    sparse_doc_embedder = FastembedSparseDocumentEmbedder(
         model="prithvida/Splade_PP_en_v1",
         batch_size=32,
     )
 
-    doc_embedder.warm_up()
+    sparse_doc_embedder.warm_up()
 
     # Text taken from PubMed QA Dataset (https://huggingface.co/datasets/pubmed_qa)
     document_list = [
         Document(
-            content="Oxidative stress generated within inflammatory joints can produce autoimmune phenomena and joint destruction. Radical species with oxidative activity, including reactive nitrogen species, represent mediators of inflammation and cartilage damage.",
+            content=("Oxidative stress generated within inflammatory joints can produce autoimmune phenomena and joint "
+                     "destruction. Radical species with oxidative activity, including reactive nitrogen species, "
+                     "represent mediators of inflammation and cartilage damage."),
             meta={
                 "pubid": "25,445,628",
                 "long_answer": "yes",
             },
         ),
         Document(
-            content="Plasma levels of pancreatic polypeptide (PP) rise upon food intake. Although other pancreatic islet hormones, such as insulin and glucagon, have been extensively investigated, PP secretion and actions are still poorly understood.",
+            content=("Plasma levels of pancreatic polypeptide (PP) rise upon food intake. Although other pancreatic "
+                     "islet hormones, such as insulin and glucagon, have been extensively investigated, PP secretion "
+                     "and actions are still poorly understood."),
             meta={
                 "pubid": "25,445,712",
                 "long_answer": "yes",
@@ -43,12 +44,12 @@ class FastembedSparseDocumentEmbedder:
         ),
     ]
 
-    result = doc_embedder.run(document_list)
+    result = sparse_doc_embedder.run(document_list)
     print(f"Document Text: {result['documents'][0].content}")
-    print(f"Document Embedding: {result['documents'][0].sparse_embedding}")
-    print(f"Embedding Dimension: {len(result['documents'][0].sparse_embedding)}")
+    print(f"Document Sparse Embedding: {result['documents'][0].sparse_embedding}")
+    print(f"Sparse Embedding Dimension: {len(result['documents'][0].sparse_embedding)}")
     ```
-    """  # noqa: E501
+    """
 
     def __init__(
         self,

{fastembed_haystack-0.1.0 → fastembed_haystack-1.0.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_sparse_text_embedder.py

@@ -13,28 +13,25 @@ class FastembedSparseTextEmbedder:
 
     Usage example:
     ```python
-    # To use this component, install the "fastembed-haystack" package.
-    # pip install fastembed-haystack
-
     from haystack_integrations.components.embedders.fastembed import FastembedSparseTextEmbedder
 
-    text = "It clearly says online this will work on a Mac OS system. The disk comes and it does not, only Windows. Do Not order this if you have a Mac!!"
+    text = ("It clearly says online this will work on a Mac OS system. "
+            "The disk comes and it does not, only Windows. Do Not order this if you have a Mac!!")
 
-    text_embedder = FastembedSparseTextEmbedder(
+    sparse_text_embedder = FastembedSparseTextEmbedder(
         model="prithvida/Splade_PP_en_v1"
     )
-    text_embedder.warm_up()
+    sparse_text_embedder.warm_up()
 
-    embedding = text_embedder.run(text)["embedding"]
+    sparse_embedding = sparse_text_embedder.run(text)["sparse_embedding"]
     ```
-    """  # noqa: E501
+    """
 
     def __init__(
         self,
         model: str = "prithvida/Splade_PP_en_v1",
         cache_dir: Optional[str] = None,
         threads: Optional[int] = None,
-        batch_size: int = 32,
         progress_bar: bool = True,
         parallel: Optional[int] = None,
     ):
@@ -46,7 +43,6 @@ class FastembedSparseTextEmbedder:
                 Can be set using the `FASTEMBED_CACHE_PATH` env variable.
                 Defaults to `fastembed_cache` in the system's temp directory.
         :param threads: The number of threads single onnxruntime session can use. Defaults to None.
-        :param batch_size: Number of strings to encode at once.
         :param progress_bar: If true, displays progress bar during embedding.
         :param parallel:
                 If > 1, data-parallel encoding will be used, recommended for offline encoding of large datasets.
@@ -57,7 +53,6 @@ class FastembedSparseTextEmbedder:
         self.model_name = model
         self.cache_dir = cache_dir
         self.threads = threads
-        self.batch_size = batch_size
         self.progress_bar = progress_bar
         self.parallel = parallel
 
@@ -73,7 +68,6 @@ class FastembedSparseTextEmbedder:
             model=self.model_name,
             cache_dir=self.cache_dir,
             threads=self.threads,
-            batch_size=self.batch_size,
             progress_bar=self.progress_bar,
             parallel=self.parallel,
         )
@@ -110,7 +104,6 @@ class FastembedSparseTextEmbedder:
 
         embedding = self.embedding_backend.embed(
             [text],
-            batch_size=self.batch_size,
             show_progress_bar=self.progress_bar,
             parallel=self.parallel,
         )[0]

{fastembed_haystack-0.1.0 → fastembed_haystack-1.0.0}/src/haystack_integrations/components/embedders/fastembed/fastembed_text_embedder.py

@@ -12,12 +12,10 @@ class FastembedTextEmbedder:
 
     Usage example:
     ```python
-    # To use this component, install the "fastembed-haystack" package.
-    # pip install fastembed-haystack
-
     from haystack_integrations.components.embedders.fastembed import FastembedTextEmbedder
 
-    text = "It clearly says online this will work on a Mac OS system. The disk comes and it does not, only Windows. Do Not order this if you have a Mac!!"
+    text = ("It clearly says online this will work on a Mac OS system. "
+            "The disk comes and it does not, only Windows. Do Not order this if you have a Mac!!")
 
     text_embedder = FastembedTextEmbedder(
         model="BAAI/bge-small-en-v1.5"
@@ -26,7 +24,7 @@ class FastembedTextEmbedder:
 
     embedding = text_embedder.run(text)["embedding"]
     ```
-    """  # noqa: E501
+    """
 
     def __init__(
         self,

{fastembed_haystack-0.1.0 → fastembed_haystack-1.0.0}/tests/test_fastembed_sparse_text_embedder.py

@@ -18,7 +18,6 @@ class TestFastembedSparseTextEmbedder:
         assert embedder.model_name == "prithvida/Splade_PP_en_v1"
         assert embedder.cache_dir is None
         assert embedder.threads is None
-        assert embedder.batch_size == 32
         assert embedder.progress_bar is True
         assert embedder.parallel is None
 
@@ -30,14 +29,12 @@ class TestFastembedSparseTextEmbedder:
             model="prithvida/Splade_PP_en_v1",
             cache_dir="fake_dir",
             threads=2,
-            batch_size=64,
             progress_bar=False,
             parallel=1,
         )
         assert embedder.model_name == "prithvida/Splade_PP_en_v1"
         assert embedder.cache_dir == "fake_dir"
         assert embedder.threads == 2
-        assert embedder.batch_size == 64
         assert embedder.progress_bar is False
         assert embedder.parallel == 1
 
@@ -53,7 +50,6 @@ class TestFastembedSparseTextEmbedder:
                 "model": "prithvida/Splade_PP_en_v1",
                 "cache_dir": None,
                 "threads": None,
-                "batch_size": 32,
                 "progress_bar": True,
                 "parallel": None,
             },
@@ -67,7 +63,6 @@ class TestFastembedSparseTextEmbedder:
             model="prithvida/Splade_PP_en_v1",
             cache_dir="fake_dir",
             threads=2,
-            batch_size=64,
             progress_bar=False,
             parallel=1,
         )
@@ -78,7 +73,6 @@ class TestFastembedSparseTextEmbedder:
                 "model": "prithvida/Splade_PP_en_v1",
                 "cache_dir": "fake_dir",
                 "threads": 2,
-                "batch_size": 64,
                 "progress_bar": False,
                 "parallel": 1,
             },
@@ -94,7 +88,6 @@ class TestFastembedSparseTextEmbedder:
                 "model": "prithvida/Splade_PP_en_v1",
                 "cache_dir": None,
                 "threads": None,
-                "batch_size": 32,
                 "progress_bar": True,
                 "parallel": None,
             },
@@ -103,7 +96,6 @@ class TestFastembedSparseTextEmbedder:
         assert embedder.model_name == "prithvida/Splade_PP_en_v1"
         assert embedder.cache_dir is None
         assert embedder.threads is None
-        assert embedder.batch_size == 32
         assert embedder.progress_bar is True
         assert embedder.parallel is None
 
@@ -117,7 +109,6 @@ class TestFastembedSparseTextEmbedder:
                 "model": "prithvida/Splade_PP_en_v1",
                 "cache_dir": "fake_dir",
                 "threads": 2,
-                "batch_size": 64,
                 "progress_bar": False,
                 "parallel": 1,
             },
@@ -126,7 +117,6 @@ class TestFastembedSparseTextEmbedder:
         assert embedder.model_name == "prithvida/Splade_PP_en_v1"
         assert embedder.cache_dir == "fake_dir"
         assert embedder.threads == 2
-        assert embedder.batch_size == 64
         assert embedder.progress_bar is False
         assert embedder.parallel == 1