The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
community: Fix links in GraphVectorStore pydoc (#25959)
Christophe Bornet58f339a67c2b
diff --git a/libs/community/langchain_community/graph_vectorstores/__init__.py b/libs/community/langchain_community/graph_vectorstores/__init__.pyindex 485123a96b..5773b224dc 100644--- a/libs/community/langchain_community/graph_vectorstores/__init__.py+++ b/libs/community/langchain_community/graph_vectorstores/__init__.py@@ -1,6 +1,9 @@-"""**Graph Vector Store**+""".. title:: Graph Vector Store-Sometimes embedding models don’t capture all the important relationships between+Graph Vector Store+==================++Sometimes embedding models don't capture all the important relationships betweendocuments.Graph Vector Stores are an extension to both vector stores and retrievers that allowdocuments to be explicitly connected to each other.@@ -13,11 +16,10 @@ Each document identifies tags that link to and from it.For example, a paragraph of text may be linked to URLs based on the anchor tags init's content and linked from the URL(s) it is published at.-Link extractors can be used to extract links from documents.--Example:+`Link extractors <langchain_community.graph_vectorstores.extractors.link_extractor.LinkExtractor>`+can be used to extract links from documents.-.. code-block:: python+Example::graph_vector_store = CassandraGraphVectorStore()link_extractor = HtmlLinkExtractor()@@ -25,13 +27,18 @@ Example:add_links(document, links)graph_vector_store.add_document(document)-***********-Get started-***********+.. seealso::-We chunk the State of the Union text and split it into documents.+ - :class:`How to use a graph vector store as a retriever <langchain_community.graph_vectorstores.base.GraphVectorStoreRetriever>`+ - :class:`How to create links between documents <langchain_community.graph_vectorstores.links.Link>`+ - :class:`How to link Documents on hyperlinks in HTML <langchain_community.graph_vectorstores.extractors.html_link_extractor.HtmlLinkExtractor>`+ - :class:`How to link Documents on common keywords (using KeyBERT) <langchain_community.graph_vectorstores.extractors.keybert_link_extractor.KeybertLinkExtractor>`+ - :class:`How to link Documents on common named entities (using GliNER) <langchain_community.graph_vectorstores.extractors.gliner_link_extractor.GLiNERLinkExtractor>`-.. code-block:: python+Get started+-----------++We chunk the State of the Union text and split it into documents::from langchain_community.document_loaders import TextLoaderfrom langchain_text_splitters import CharacterTextSplitter@@ -41,14 +48,12 @@ We chunk the State of the Union text and split it into documents.documents = text_splitter.split_documents(raw_documents)Links can be added to documents manually but it's easier to use a-:class:`~langchain_community.graph_vectorstores.extractors.LinkExtractor`.+:class:`~langchain_community.graph_vectorstores.extractors.link_extractor.LinkExtractor`.Several common link extractors are available and you can build your own.For this guide, we'll use the-:class:`~langchain_community.graph_vectorstores.extractors.KeybertLinkExtractor`+:class:`~langchain_community.graph_vectorstores.extractors.keybert_link_extractor.KeybertLinkExtractor`which uses the KeyBERT model to tag documents with keywords and uses these keywords to-create links between documents.--.. code-block:: python+create links between documents::from langchain_community.graph_vectorstores.extractors import KeybertLinkExtractorfrom langchain_community.graph_vectorstores.links import add_links@@ -58,15 +63,14 @@ create links between documents.for doc in documents:add_links(doc, extractor.extract_one(doc))-***********************************************Create the graph vector store and add documents-***********************************************+-----------------------------------------------We'll use an Apache Cassandra or Astra DB database as an example.-We create a :class:`~langchain_community.graph_vectorstores.CassandraGraphVectorStore`-from the documents and an :class:`~langchain_openai.OpenAIEmbeddings` model.--.. code-block:: python+We create a+:class:`~langchain_community.graph_vectorstores.cassandra.CassandraGraphVectorStore`+from the documents and an :class:`~langchain_openai.embeddings.base.OpenAIEmbeddings`+model::import cassiofrom langchain_community.graph_vectorstores import CassandraGraphVectorStore@@ -80,45 +84,37 @@ from the documents and an :class:`~langchain_openai.OpenAIEmbeddings` model.documents=documents,)-*****************+Similarity search-*****************+-----------------If we don't traverse the graph, a graph vector store behaves like a regular vectorstore.So all methods available in a vector store are also available in a graph vector store.The :meth:`~langchain_community.graph_vectorstores.base.GraphVectorStore.similarity_search`method returns documents similar to a query without considering-the links between documents.--.. code-block:: python+the links between documents::docs = store.similarity_search("What did the president say about Ketanji Brown Jackson?")-****************Traversal search-****************+----------------The :meth:`~langchain_community.graph_vectorstores.base.GraphVectorStore.traversal_search`method returns documents similar to a query considering the linksbetween documents. It first does a similarity search and then traverses the graph to-find linked documents.--.. code-block:: python+find linked documents::docs = list(store.traversal_search("What did the president say about Ketanji Brown Jackson?"))-*************Async methods-*************--The graph vector store has async versions of the methods prefixed with ``a``.+--------------.. code-block:: python+The graph vector store has async versions of the methods prefixed with ``a``::docs = [doc@@ -127,15 +123,12 @@ The graph vector store has async versions of the methods prefixed with ``a``.)]-****************************Graph vector store retriever-****************************+----------------------------The graph vector store can be converted to a retriever.It is similar to the vector store retriever but it also has traversal search methods-such as ``traversal`` and ``mmr_traversal``.--.. code-block:: python+such as ``traversal`` and ``mmr_traversal``::retriever = store.as_retriever(search_type="mmr_traversal")docs = retriever.invoke("What did the president say about Ketanji Brown Jackson?")