The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
Kùzu package integration docs (#29076)
Prashanth Raob1dafaef9b2c
diff --git a/docs/docs/integrations/graphs/kuzu_db.ipynb b/docs/docs/integrations/graphs/kuzu_db.ipynbindex dde4dddc6c..a030a20538 100644--- a/docs/docs/integrations/graphs/kuzu_db.ipynb+++ b/docs/docs/integrations/graphs/kuzu_db.ipynb@@ -7,12 +7,17 @@"source": ["# Kuzu\n","\n",- ">[Kùzu](https://kuzudb.com) is an embeddable property graph database management system built for query speed and scalability.\n",- "> \n",- "> Kùzu has a permissive (MIT) open source license and implements [Cypher](https://en.wikipedia.org/wiki/Cypher_(query_language)), a declarative graph query language that allows for expressive and efficient data querying in a property graph.\n",- "> It uses columnar storage and its query processor contains novel join algorithms that allow it to scale to very large graphs without sacrificing query performance.\n",- "> \n",- "> This notebook shows how to use LLMs to provide a natural language interface to [Kùzu](https://kuzudb.com) database with Cypher."+ "> [Kùzu](https://kuzudb.com/) is an embeddable, scalable, extremely fast graph database.\n",+ "> It is permissively licensed with an MIT license, and you can see its source code [here](https://github.com/kuzudb/kuzu).\n",+ "\n",+ "> Key characteristics of Kùzu:\n",+ ">- Performance and scalability: Implements modern, state-of-the-art join algorithms for graphs.\n",+ ">- Usability: Very easy to set up and get started with, as there are no servers (embedded architecture).\n",+ ">- Interoperability: Can conveniently scan and copy data from external columnar formats, CSV, JSON and relational databases.\n",+ ">- Structured property graph model: Implements the property graph model, with added structure.\n",+ ">- Cypher support: Allows convenient querying of the graph in Cypher, a declarative query language.\n",+ "\n",+ "> Get started with Kùzu by visiting their [documentation](https://docs.kuzudb.com/)."]},{@@ -22,19 +27,28 @@"source": ["## Setting up\n","\n",- "Kùzu is an embedded database (it runs in-process), so there are no servers to manage.\n",- "Simply install it via its Python package:\n",+ "Kùzu is an embedded database (it runs in-process), so there are no servers to manage. Install the\n",+ "following dependencies to get started:\n","\n","```bash\n",- "pip install kuzu\n",+ "pip install -U langchain-kuzu langchain-openai langchain-experimental\n","```\n","\n",- "Create a database on the local machine and connect to it:"+ "This installs Kùzu along with the LangChain integration for it, as well as the OpenAI Python package\n",+ "so that we can use OpenAI's LLMs. If you want to use other LLM providers, you can install their\n",+ "respective Python packages that come with LangChain."+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {},+ "source": [+ "Here's how you would first create a Kùzu database on your local machine and connect to it:"]},{"cell_type": "code",- "execution_count": 2,+ "execution_count": 1,"metadata": {},"outputs": [],"source": [@@ -45,102 +59,75 @@]},{- "attachments": {},"cell_type": "markdown","metadata": {},"source": [- "First, we create the schema for a simple movie database:"+ "## Create `KuzuGraph`"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {},+ "source": [+ "Kùzu's integration with LangChain makes it convenient to create and update graphs from unstructured text, and also to query graphs via a Text2Cypher pipeline that utilizes the\n",+ "power of LangChain's LLM chains. To begin, we create a `KuzuGraph` object that uses the database object we created above in combination with the `KuzuGraph` constructor."]},{"cell_type": "code",- "execution_count": 3,+ "execution_count": 2,"metadata": {},- "outputs": [- {- "data": {- "text/plain": [- "<kuzu.query_result.QueryResult at 0x103a72290>"- ]- },- "execution_count": 3,- "metadata": {},- "output_type": "execute_result"- }- ],+ "outputs": [],"source": [- "conn.execute(\"CREATE NODE TABLE Movie (name STRING, PRIMARY KEY(name))\")\n",- "conn.execute(\n",- " \"CREATE NODE TABLE Person (name STRING, birthDate STRING, PRIMARY KEY(name))\"\n",- ")\n",- "conn.execute(\"CREATE REL TABLE ActedIn (FROM Person TO Movie)\")"+ "from langchain_kuzu.graphs.kuzu_graph import KuzuGraph\n",+ "\n",+ "graph = KuzuGraph(db, allow_dangerous_requests=True)"]},{- "attachments": {},"cell_type": "markdown","metadata": {},"source": [- "Then we can insert some data."+ "Say we want to transform the following text into a graph:"]},{"cell_type": "code",- "execution_count": 4,+ "execution_count": 3,"metadata": {},- "outputs": [- {- "data": {- "text/plain": [- "<kuzu.query_result.QueryResult at 0x103a9e750>"- ]- },- "execution_count": 4,- "metadata": {},- "output_type": "execute_result"- }- ],+ "outputs": [],"source": [- "conn.execute(\"CREATE (:Person {name: 'Al Pacino', birthDate: '1940-04-25'})\")\n",- "conn.execute(\"CREATE (:Person {name: 'Robert De Niro', birthDate: '1943-08-17'})\")\n",- "conn.execute(\"CREATE (:Movie {name: 'The Godfather'})\")\n",- "conn.execute(\"CREATE (:Movie {name: 'The Godfather: Part II'})\")\n",- "conn.execute(\n",- " \"CREATE (:Movie {name: 'The Godfather Coda: The Death of Michael Corleone'})\"\n",- ")\n",- "conn.execute(\n",- " \"MATCH (p:Person), (m:Movie) WHERE p.name = 'Al Pacino' AND m.name = 'The Godfather' CREATE (p)-[:ActedIn]->(m)\"\n",- ")\n",- "conn.execute(\n",- " \"MATCH (p:Person), (m:Movie) WHERE p.name = 'Al Pacino' AND m.name = 'The Godfather: Part II' CREATE (p)-[:ActedIn]->(m)\"\n",- ")\n",- "conn.execute(\n",- " \"MATCH (p:Person), (m:Movie) WHERE p.name = 'Al Pacino' AND m.name = 'The Godfather Coda: The Death of Michael Corleone' CREATE (p)-[:ActedIn]->(m)\"\n",- ")\n",- "conn.execute(\n",- " \"MATCH (p:Person), (m:Movie) WHERE p.name = 'Robert De Niro' AND m.name = 'The Godfather: Part II' CREATE (p)-[:ActedIn]->(m)\"\n",- ")"+ "text = \"Tim Cook is the CEO of Apple. Apple has its headquarters in California.\""]},{- "attachments": {},"cell_type": "markdown","metadata": {},"source": [- "## Creating `KuzuQAChain`\n",- "\n",- "We can now create the `KuzuGraph` and `KuzuQAChain`. To create the `KuzuGraph` we simply need to pass the database object to the `KuzuGraph` constructor."+ "We will make use of `LLMGraphTransformer` to use an LLM to extract nodes and relationships from the text.\n",+ "To make the graph more useful, we will define the following schema, such that the LLM will only\n",+ "extract nodes and relationships that match the schema."]},{"cell_type": "code",- "execution_count": 5,+ "execution_count": 4,"metadata": {},"outputs": [],"source": [- "from langchain.chains import KuzuQAChain\n",- "from langchain_community.graphs import KuzuGraph\n",- "from langchain_openai import ChatOpenAI"+ "# Define schema\n",+ "allowed_nodes = [\"Person\", \"Company\", \"Location\"]\n",+ "allowed_relationships = [\n",+ " (\"Person\", \"IS_CEO_OF\", \"Company\"),\n",+ " (\"Company\", \"HAS_HEADQUARTERS_IN\", \"Location\"),\n",+ "]"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {},+ "source": [+ "The `LLMGraphTransformer` class provides a convenient way to convert the text into a list of graph documents."]},{@@ -149,7 +136,47 @@"metadata": {},"outputs": [],"source": [- "graph = KuzuGraph(db)"+ "from langchain_core.documents import Document\n",+ "from langchain_experimental.graph_transformers import LLMGraphTransformer\n",+ "from langchain_openai import ChatOpenAI\n",+ "\n",+ "# Define the LLMGraphTransformer\n",+ "llm_transformer = LLMGraphTransformer(\n",+ " llm=ChatOpenAI(model=\"gpt-4o-mini\", temperature=0, api_key=OPENAI_API_KEY), # noqa: F821\n",+ " allowed_nodes=allowed_nodes,\n",+ " allowed_relationships=allowed_relationships,\n",+ ")\n",+ "\n",+ "documents = [Document(page_content=text)]\n",+ "graph_documents = llm_transformer.convert_to_graph_documents(documents)"+ ]+ },+ {+ "cell_type": "code",+ "execution_count": 7,+ "metadata": {},+ "outputs": [+ {+ "data": {+ "text/plain": [+ "[GraphDocument(nodes=[Node(id='Tim Cook', type='Person', properties={}), Node(id='Apple', type='Company', properties={}), Node(id='California', type='Location', properties={})], relationships=[Relationship(source=Node(id='Tim Cook', type='Person', properties={}), target=Node(id='Apple', type='Company', properties={}), type='IS_CEO_OF', properties={}), Relationship(source=Node(id='Apple', type='Company', properties={}), target=Node(id='California', type='Location', properties={}), type='HAS_HEADQUARTERS_IN', properties={})], source=Document(metadata={}, page_content='Tim Cook is the CEO of Apple. Apple has its headquarters in California.'))]"+ ]+ },+ "execution_count": 7,+ "metadata": {},+ "output_type": "execute_result"+ }+ ],+ "source": [+ "graph_documents[:2]"+ ]+ },+ {+ "cell_type": "markdown",+ "metadata": {},+ "source": [+ "We can then call the above defined `KuzuGraph` object's `add_graph_documents` method to ingest the graph documents into the Kùzu database.\n",+ "The `include_source` argument is set to `True` so that we also create relationships between each entity node and the source document that it came from."]},{@@ -158,10 +185,10 @@"metadata": {},"outputs": [],"source": [- "chain = KuzuQAChain.from_llm(\n",- " llm=ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-16k\"),\n",- " graph=graph,\n",- " verbose=True,\n",+ "# Add the graph document to the graph\n",+ "graph.add_graph_documents(\n",+ " graph_documents,\n",+ " include_source=True,\n",")"]},@@ -170,10 +197,9 @@"cell_type": "markdown","metadata": {},"source": [- "## Refresh graph schema information\n",+ "## Creating `KuzuQAChain`\n","\n",- "If the schema of database changes, you can refresh the schema information needed to generate Cypher statements.\n",- "You can also display the schema of the Kùzu graph as demonstrated below."+ "To query the graph via a Text2Cypher pipeline, we can define a `KuzuQAChain` object. Then, we can invoke the chain with a query by connecting to the existing database that's stored in the `test_db` directory defined above."]},{@@ -182,27 +208,22 @@"metadata": {},"outputs": [],"source": [- "# graph.refresh_schema()"+ "from langchain_kuzu.chains.graph_qa.kuzu import KuzuQAChain\n",+ "\n",+ "# Create the KuzuQAChain with verbosity enabled to see the generated Cypher queries\n",+ "chain = KuzuQAChain.from_llm(\n",+ " llm=ChatOpenAI(model=\"gpt-4o-mini\", temperature=0.3, api_key=OPENAI_API_KEY), # noqa: F821\n",+ " graph=graph,\n",+ " verbose=True,\n",+ " allow_dangerous_requests=True,\n",+ ")"]},{- "cell_type": "code",- "execution_count": 10,+ "cell_type": "markdown","metadata": {},- "outputs": [- {- "name": "stdout",- "output_type": "stream",- "text": [- "Node properties: [{'properties': [('name', 'STRING')], 'label': 'Movie'}, {'properties': [('name', 'STRING'), ('birthDate', 'STRING')], 'label': 'Person'}]\n",- "Relationships properties: [{'properties': [], 'label': 'ActedIn'}]\n",- "Relationships: ['(:Person)-[:ActedIn]->(:Movie)']\n",- "\n"- ]- }- ],"source": [- "print(graph.get_schema)"+ "Note that we set a temperature that's slightly higher than zero to avoid the LLM being overly concise in its response."]},{@@ -210,14 +231,12 @@"cell_type": "markdown","metadata": {},"source": [- "## Querying the graph\n",- "\n",- "We can now use the `KuzuQAChain` to ask questions of the graph."+ "Let's ask some questions using the QA chain."]},{"cell_type": "code",- "execution_count": 11,+ "execution_count": 10,"metadata": {},"outputs": [{@@ -228,11 +247,9 @@"\n","\u001b[1m> Entering new KuzuQAChain chain...\u001b[0m\n","Generated Cypher:\n",- "\u001b[32;1m\u001b[1;3mMATCH (p:Person)-[:ActedIn]->(m:Movie)\n",- "WHERE m.name = 'The Godfather: Part II'\n",- "RETURN p.name\u001b[0m\n",+ "\u001b[32;1m\u001b[1;3mMATCH (p:Person)-[:IS_CEO_OF]->(c:Company {id: 'Apple'}) RETURN p\u001b[0m\n","Full Context:\n",- "\u001b[32;1m\u001b[1;3m[{'p.name': 'Al Pacino'}, {'p.name': 'Robert De Niro'}]\u001b[0m\n",+ "\u001b[32;1m\u001b[1;3m[{'p': {'_id': {'offset': 0, 'table': 1}, '_label': 'Person', 'id': 'Tim Cook', 'type': 'entity'}}]\u001b[0m\n","\n","\u001b[1m> Finished chain.\u001b[0m\n"]@@ -240,22 +257,22 @@{"data": {"text/plain": [- "{'query': 'Who acted in The Godfather: Part II?',\n",- " 'result': 'Al Pacino, Robert De Niro acted in The Godfather: Part II.'}"+ "{'query': 'Who is the CEO of Apple?',\n",+ " 'result': 'Tim Cook is the CEO of Apple.'}"]},- "execution_count": 11,+ "execution_count": 10,"metadata": {},"output_type": "execute_result"}],"source": [- "chain.invoke(\"Who acted in The Godfather: Part II?\")"+ "chain.invoke(\"Who is the CEO of Apple?\")"]},{"cell_type": "code",- "execution_count": 12,+ "execution_count": 11,"metadata": {},"outputs": [{@@ -266,11 +283,9 @@"\n","\u001b[1m> Entering new KuzuQAChain chain...\u001b[0m\n","Generated Cypher:\n",- "\u001b[32;1m\u001b[1;3mMATCH (p:Person)-[:ActedIn]->(m:Movie)\n",- "WHERE p.name = 'Robert De Niro'\n",- "RETURN m.name\u001b[0m\n",+ "\u001b[32;1m\u001b[1;3mMATCH (c:Company {id: 'Apple'})-[:HAS_HEADQUARTERS_IN]->(l:Location) RETURN l\u001b[0m\n","Full Context:\n",- "\u001b[32;1m\u001b[1;3m[{'m.name': 'The Godfather: Part II'}]\u001b[0m\n",+ "\u001b[32;1m\u001b[1;3m[{'l': {'_id': {'offset': 0, 'table': 2}, '_label': 'Location', 'id': 'California', 'type': 'entity'}}]\u001b[0m\n","\n","\u001b[1m> Finished chain.\u001b[0m\n"]@@ -278,93 +293,50 @@{"data": {"text/plain": [- "{'query': 'Robert De Niro played in which movies?',\n",- " 'result': 'Robert De Niro played in The Godfather: Part II.'}"+ "{'query': 'Where is Apple headquartered?',\n",+ " 'result': 'Apple is headquartered in California.'}"]},- "execution_count": 12,+ "execution_count": 11,"metadata": {},"output_type": "execute_result"}],"source": [- "chain.invoke(\"Robert De Niro played in which movies?\")"+ "chain.invoke(\"Where is Apple headquartered?\")"]},{- "cell_type": "code",- "execution_count": 13,+ "attachments": {},+ "cell_type": "markdown","metadata": {},- "outputs": [- {- "name": "stdout",- "output_type": "stream",- "text": [- "\n",- "\n",- "\u001b[1m> Entering new KuzuQAChain chain...\u001b[0m\n",- "Generated Cypher:\n",- "\u001b[32;1m\u001b[1;3mMATCH (:Person)-[:ActedIn]->(:Movie {name: 'Godfather: Part II'})\n",- "RETURN count(*)\u001b[0m\n",- "Full Context:\n",- "\u001b[32;1m\u001b[1;3m[{'COUNT_STAR()': 0}]\u001b[0m\n",- "\n",- "\u001b[1m> Finished chain.\u001b[0m\n"- ]- },- {- "data": {- "text/plain": [- "{'query': 'How many actors played in the Godfather: Part II?',\n",- " 'result': \"I don't know the answer.\"}"- ]- },- "execution_count": 13,- "metadata": {},- "output_type": "execute_result"- }- ],"source": [- "chain.invoke(\"How many actors played in the Godfather: Part II?\")"+ "## Refresh graph schema\n",+ "\n",+ "If you mutate or update the graph, you can inspect the refreshed schema information that's used by the Text2Cypher chain to generate Cypher statements.\n",+ "You don't need to manually call `refresh_schema()` each time as it's called automatically when you invoke the chain."]},{"cell_type": "code",- "execution_count": 14,+ "execution_count": 12,"metadata": {},"outputs": [{"name": "stdout","output_type": "stream","text": [- "\n",- "\n",- "\u001b[1m> Entering new KuzuQAChain chain...\u001b[0m\n",- "Generated Cypher:\n",- "\u001b[32;1m\u001b[1;3mMATCH (p:Person)-[:ActedIn]->(m:Movie {name: 'The Godfather: Part II'})\n",- "RETURN p.name\n",- "ORDER BY p.birthDate ASC\n",- "LIMIT 1\u001b[0m\n",- "Full Context:\n",- "\u001b[32;1m\u001b[1;3m[{'p.name': 'Al Pacino'}]\u001b[0m\n",- "\n",- "\u001b[1m> Finished chain.\u001b[0m\n"+ "Node properties: [{'properties': [('id', 'STRING'), ('type', 'STRING')], 'label': 'Person'}, {'properties': [('id', 'STRING'), ('type', 'STRING')], 'label': 'Location'}, {'properties': [('id', 'STRING'), ('text', 'STRING'), ('type', 'STRING')], 'label': 'Chunk'}, {'properties': [('id', 'STRING'), ('type', 'STRING')], 'label': 'Company'}]\n",+ "Relationships properties: [{'properties': [], 'label': 'HAS_HEADQUARTERS_IN'}, {'properties': [('label', 'STRING'), ('triplet_source_id', 'STRING')], 'label': 'MENTIONS_Chunk_Person'}, {'properties': [('label', 'STRING'), ('triplet_source_id', 'STRING')], 'label': 'MENTIONS_Chunk_Location'}, {'properties': [], 'label': 'IS_CEO_OF'}, {'properties': [('label', 'STRING'), ('triplet_source_id', 'STRING')], 'label': 'MENTIONS_Chunk_Company'}]\n",+ "Relationships: ['(:Company)-[:HAS_HEADQUARTERS_IN]->(:Location)', '(:Chunk)-[:MENTIONS_Chunk_Person]->(:Person)', '(:Chunk)-[:MENTIONS_Chunk_Location]->(:Location)', '(:Person)-[:IS_CEO_OF]->(:Company)', '(:Chunk)-[:MENTIONS_Chunk_Company]->(:Company)']\n",+ "\n"]- },- {- "data": {- "text/plain": [- "{'query': 'Who is the oldest actor who played in The Godfather: Part II?',\n",- " 'result': 'Al Pacino is the oldest actor who played in The Godfather: Part II.'}"- ]- },- "execution_count": 14,- "metadata": {},- "output_type": "execute_result"}],"source": [- "chain.invoke(\"Who is the oldest actor who played in The Godfather: Part II?\")"+ "graph.refresh_schema()\n",+ "\n",+ "print(graph.get_schema)"]},{@@ -378,30 +350,22 @@},{"cell_type": "code",- "execution_count": 15,+ "execution_count": 13,"metadata": {},- "outputs": [- {- "name": "stderr",- "output_type": "stream",- "text": [- "/Users/prrao/code/langchain/.venv/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:119: LangChainDeprecationWarning: The class `LLMChain` was deprecated in LangChain 0.1.17 and will be removed in 0.3.0. Use RunnableSequence, e.g., `prompt | llm` instead.\n",- " warn_deprecated(\n"- ]- }- ],+ "outputs": [],"source": ["chain = KuzuQAChain.from_llm(\n",- " cypher_llm=ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo-16k\"),\n",+ " cypher_llm=ChatOpenAI(temperature=0, model=\"gpt-4o-mini\"),\n"," qa_llm=ChatOpenAI(temperature=0, model=\"gpt-4\"),\n"," graph=graph,\n"," verbose=True,\n",+ " allow_dangerous_requests=True,\n",")"]},{"cell_type": "code",- "execution_count": 16,+ "execution_count": 14,"metadata": {},"outputs": [{@@ -410,40 +374,11 @@"text": ["\n","\n",- "\u001b[1m> Entering new KuzuQAChain chain...\u001b[0m\n"- ]- },- {- "name": "stderr",- "output_type": "stream",- "text": [- "/Users/prrao/code/langchain/.venv/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:119: LangChainDeprecationWarning: The method `Chain.run` was deprecated in langchain 0.1.0 and will be removed in 0.2.0. Use invoke instead.\n",- " warn_deprecated(\n"- ]- },- {- "name": "stdout",- "output_type": "stream",- "text": [+ "\u001b[1m> Entering new KuzuQAChain chain...\u001b[0m\n","Generated Cypher:\n",- "\u001b[32;1m\u001b[1;3mMATCH (:Person)-[:ActedIn]->(:Movie {name: 'The Godfather: Part II'})\n",- "RETURN count(*)\u001b[0m\n",+ "\u001b[32;1m\u001b[1;3mMATCH (p:Person)-[:IS_CEO_OF]->(c:Company {id: 'Apple'}) RETURN p.id, p.type\u001b[0m\n","Full Context:\n",- "\u001b[32;1m\u001b[1;3m[{'COUNT_STAR()': 2}]\u001b[0m\n"- ]- },- {- "name": "stderr",- "output_type": "stream",- "text": [- "/Users/prrao/code/langchain/.venv/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:119: LangChainDeprecationWarning: The method `Chain.__call__` was deprecated in langchain 0.1.0 and will be removed in 0.2.0. Use invoke instead.\n",- " warn_deprecated(\n"- ]- },- {- "name": "stdout",- "output_type": "stream",- "text": [+ "\u001b[32;1m\u001b[1;3m[{'p.id': 'Tim Cook', 'p.type': 'entity'}]\u001b[0m\n","\n","\u001b[1m> Finished chain.\u001b[0m\n"]@@ -451,17 +386,17 @@{"data": {"text/plain": [- "{'query': 'How many actors played in The Godfather: Part II?',\n",- " 'result': 'Two actors played in The Godfather: Part II.'}"+ "{'query': 'Who is the CEO of Apple?',\n",+ " 'result': 'Tim Cook is the CEO of Apple.'}"]},- "execution_count": 16,+ "execution_count": 14,"metadata": {},"output_type": "execute_result"}],"source": [- "chain.invoke(\"How many actors played in The Godfather: Part II?\")"+ "chain.invoke(\"Who is the CEO of Apple?\")"]}],@@ -481,7 +416,7 @@"name": "python","nbconvert_exporter": "python","pygments_lexer": "ipython3",- "version": "3.11.7"+ "version": "3.13.1"}},"nbformat": 4,diff --git a/docs/docs/integrations/providers/kuzu.mdx b/docs/docs/integrations/providers/kuzu.mdxindex 286b38e0d8..aff0a0f668 100644--- a/docs/docs/integrations/providers/kuzu.mdx+++ b/docs/docs/integrations/providers/kuzu.mdx@@ -1,32 +1,40 @@# Kùzu->[Kùzu](https://kuzudb.com/) is a company based in Waterloo, Ontario, Canada.-> It provides a highly scalable, extremely fast, easy-to-use [embeddable graph database](https://github.com/kuzudb/kuzu).+> [Kùzu](https://kuzudb.com/) is an embeddable, scalable, extremely fast graph database.+> It is permissively licensed with an MIT license, and you can see its source code [here](https://github.com/kuzudb/kuzu).+> Key characteristics of Kùzu:+>- Performance and scalability: Implements modern, state-of-the-art join algorithms for graphs.+>- Usability: Very easy to set up and get started with, as there are no servers (embedded architecture).+>- Interoperability: Can conveniently scan and copy data from external columnar formats, CSV, JSON and relational databases.+>- Structured property graph model: Implements the property graph model, with added structure.+>- Cypher support: Allows convenient querying of the graph in Cypher, a declarative query language.++> Get started with Kùzu by visiting their [documentation](https://docs.kuzudb.com/).## Installation and Setup-You need to install the `kuzu` python package.+Install the Python SDK as follows:```bash-pip install kuzu+pip install -U langchain-kuzu```-## Graph database+## Usage++## GraphsSee a [usage example](/docs/integrations/graphs/kuzu_db).```python-from langchain_community.graphs import KuzuGraph+from langchain_kuzu.graphs.kuzu_graph import KuzuGraph```-## Chain+## ChainsSee a [usage example](/docs/integrations/graphs/kuzu_db/#creating-kuzuqachain).```python-from langchain.chains import KuzuQAChain+from langchain_kuzu.chains.graph_qa.kuzu import KuzuQAChain```--diff --git a/libs/packages.yml b/libs/packages.ymlindex 5fd27064a3..ce75cf8672 100644--- a/libs/packages.yml+++ b/libs/packages.yml@@ -324,4 +324,8 @@ packages:- name: langchain-pull-mdpath: .repo: chigwell/langchain-pull-md- downloads: 0\ No newline at end of file+ downloads: 0+- name: langchain-kuzu+ path: .+ repo: kuzudb/langchain-kuzu+ downloads: 0