fastembed integration: add example (#401)

* created project

* added parallel param

* updated test

* version 0.0.1

* renamed folder

* removed print

* updated readme

* added fastembed.yml

* fix typos

* python version to 3.9 for lint

* updated file

* force install black

* return to original file

* try to fix workflow

* retry

* add missing info to pyproject

* add hatch-vcs to check version

* Update pyproject.toml

* fixed typos

* removed python 3.9

* Update fastembed.yml

* Update fastembed_document_embedder.py

* Update fastembed_text_embedder.py

* ignore errors for bool arguments

* fix

* try moving noqa

* move noqa

* formatted with black

* added numpy dependency

* removed numpy

* removed numpy

* make mypy happy

* Update fastembed_backend.py

* removed classvar

* fix

* Update pyproject.toml

* added import numpy lint

* skip docs generation for the time being

* Update README.md

* added config.yml

* generate docs

* Update fastembed.yml

* Update config.yml

* rm unnecessary from_dict

* final touch

* updated labeler.yml

* updated library readme

* fix typos

* fix docstrings/README

* added example.py

* formatted with black

* fixed formatting

* fix

---------

Co-authored-by: Stefano Fiorucci <[email protected]>

integrations/fastembed/example/example.py

@@ -0,0 +1,33 @@
+from haystack import Document, Pipeline
+from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
+from haystack.document_stores.in_memory import InMemoryDocumentStore
+from haystack_integrations.components.embedders.fastembed import FastembedDocumentEmbedder, FastembedTextEmbedder
+
+document_store = InMemoryDocumentStore(embedding_similarity_function="cosine")
+
+documents = [
+    Document(content="My name is Wolfgang and I live in Berlin"),
+    Document(content="I saw a black horse running"),
+    Document(content="Germany has many big cities"),
+    Document(content="fastembed is supported by and maintained by Qdrant."),
+]
+
+document_embedder = FastembedDocumentEmbedder()
+document_embedder.warm_up()
+documents_with_embeddings = document_embedder.run(documents)["documents"]
+document_store.write_documents(documents_with_embeddings)
+
+query_pipeline = Pipeline()
+query_pipeline.add_component("text_embedder", FastembedTextEmbedder())
+query_pipeline.add_component("retriever", InMemoryEmbeddingRetriever(document_store=document_store))
+query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
+
+query = "Who supports fastembed?"
+
+result = query_pipeline.run({"text_embedder": {"text": query}})
+
+print(result["retriever"]["documents"][0])  # noqa: T201
+
+# Document(id=...,
+#  content: 'fastembed is supported by and maintained by Qdrant.',
+#  score: 0.758..)