Skip to content

The agent engineering platform.

community: Add docstring for GLiNERLinkExtractor (#26218)

Christophe Bornet56580b5fff81
diff --git a/libs/community/langchain_community/graph_vectorstores/extractors/gliner_link_extractor.py b/libs/community/langchain_community/graph_vectorstores/extractors/gliner_link_extractor.py
index a485f849c7..9d567a1f8d 100644
--- a/libs/community/langchain_community/graph_vectorstores/extractors/gliner_link_extractor.py
+++ b/libs/community/langchain_community/graph_vectorstores/extractors/gliner_link_extractor.py
@@ -14,7 +14,117 @@ GLiNERInput = Union[str, Document]
@beta()
class GLiNERLinkExtractor(LinkExtractor[GLiNERInput]):
- """Link documents with common named entities using GLiNER <https://github.com/urchade/GLiNER>."""
+ """Link documents with common named entities using `GLiNER`_.
+
+ `GLiNER`_ is a Named Entity Recognition (NER) model capable of identifying any
+ entity type using a bidirectional transformer encoder (BERT-like).
+
+ The ``GLiNERLinkExtractor`` uses GLiNER to create links between documents that
+ have named entities in common.
+
+ Example::
+
+ extractor = GLiNERLinkExtractor(
+ labels=["Person", "Award", "Date", "Competitions", "Teams"]
+ )
+ results = extractor.extract_one("some long text...")
+
+ .. _GLiNER: https://github.com/urchade/GLiNER
+
+ .. seealso::
+
+ - :mod:`How to use a graph vector store <langchain_community.graph_vectorstores>`
+ - :class:`How to create links between documents <langchain_core.graph_vectorstores.links.Link>`
+
+ How to link Documents on common named entities
+ ==============================================
+
+ Preliminaries
+ -------------
+
+ Install the ``gliner`` package:
+
+ .. code-block:: bash
+
+ pip install -q langchain_community gliner
+
+ Usage
+ -----
+
+ We load the ``state_of_the_union.txt`` file, chunk it, then for each chunk we
+ extract named entity links and add them to the chunk.
+
+ Using extract_one()
+ ^^^^^^^^^^^^^^^^^^^
+
+ We can use :meth:`extract_one` on a document to get the links and add the links
+ to the document metadata with
+ :meth:`~langchain_core.graph_vectorstores.links.add_links`::
+
+ from langchain_community.document_loaders import TextLoader
+ from langchain_community.graph_vectorstores import CassandraGraphVectorStore
+ from langchain_community.graph_vectorstores.extractors import GLiNERLinkExtractor
+ from langchain_core.graph_vectorstores.links import add_links
+ from langchain_text_splitters import CharacterTextSplitter
+
+ loader = TextLoader("state_of_the_union.txt")
+ raw_documents = loader.load()
+
+ text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+ documents = text_splitter.split_documents(raw_documents)
+
+ ner_extractor = GLiNERLinkExtractor(["Person", "Topic"])
+ for document in documents:
+ links = ner_extractor.extract_one(document)
+ add_links(document, links)
+
+ print(documents[0].metadata)
+
+ .. code-block:: output
+
+ {'source': 'state_of_the_union.txt', 'links': [Link(kind='entity:Person', direction='bidir', tag='President Zelenskyy'), Link(kind='entity:Person', direction='bidir', tag='Vladimir Putin')]}
+
+ Using LinkExtractorTransformer
+ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+ Using the :class:`~langchain_community.graph_vectorstores.extractors.keybert_link_extractor.LinkExtractorTransformer`,
+ we can simplify the link extraction::
+
+ from langchain_community.document_loaders import TextLoader
+ from langchain_community.graph_vectorstores.extractors import (
+ GLiNERLinkExtractor,
+ LinkExtractorTransformer,
+ )
+ from langchain_text_splitters import CharacterTextSplitter
+
+ loader = TextLoader("state_of_the_union.txt")
+ raw_documents = loader.load()
+
+ text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+ documents = text_splitter.split_documents(raw_documents)
+
+ ner_extractor = GLiNERLinkExtractor(["Person", "Topic"])
+ transformer = LinkExtractorTransformer([ner_extractor])
+ documents = transformer.transform_documents(documents)
+
+ print(documents[0].metadata)
+
+ .. code-block:: output
+
+ {'source': 'state_of_the_union.txt', 'links': [Link(kind='entity:Person', direction='bidir', tag='President Zelenskyy'), Link(kind='entity:Person', direction='bidir', tag='Vladimir Putin')]}
+
+ The documents with named entity links can then be added to a :class:`~langchain_core.graph_vectorstores.base.GraphVectorStore`::
+
+ from langchain_community.graph_vectorstores import CassandraGraphVectorStore
+
+ store = CassandraGraphVectorStore.from_documents(documents=documents, embedding=...)
+
+ Args:
+ labels: List of kinds of entities to extract.
+ kind: Kind of links to produce with this extractor.
+ model: GLiNER model to use.
+ extract_kwargs: Keyword arguments to pass to GLiNER.
+ """ # noqa: E501
def __init__(
self,
@@ -24,23 +134,6 @@ class GLiNERLinkExtractor(LinkExtractor[GLiNERInput]):
model: str = "urchade/gliner_mediumv2.1",
extract_kwargs: Optional[Dict[str, Any]] = None,
):
- """Extract keywords using GLiNER.
-
- Example:
-
- .. code-block:: python
-
- extractor = GLiNERLinkExtractor(
- labels=["Person", "Award", "Date", "Competitions", "Teams"]
- )
- results = extractor.extract_one("some long text...")
-
- Args:
- labels: List of kinds of entities to extract.
- kind: Kind of links to produce with this extractor.
- model: GLiNER model to use.
- extract_kwargs: Keyword arguments to pass to GLiNER.
- """
try:
from gliner import GLiNER