Zǻid8ddlmZddlZddlZddlmZmZmZddlZddl m Z ddl m Z m Z mZmZddlmZmZddlmZmZmZej.eZ d dd Z d dd Z d dd Zdej:f dd Z d dd Z d ddZ d ddZ! d ddZ" ddZ# d ddZ$gdf d dZ%y)!) annotationsN)ListLiteralOptional)ValidationError)UPSERT_VECTOR_ON_NODE_QUERY#UPSERT_VECTOR_ON_RELATIONSHIP_QUERYUPSERT_VECTORS_ON_NODE_QUERY$UPSERT_VECTORS_ON_RELATIONSHIP_QUERY)Neo4jIndexErrorNeo4jInsertionError) EntityTypeFulltextIndexModelVectorIndexModelc t|||||| d|rdndd|d|d } tj d |d |j | |||d | y#t$r"}td|j|d}~wwxYw#tjj$r}td|j|d}~wwxYw)a This method constructs a Cypher query and executes it to create a new vector index in Neo4j. See Cypher manual on `creating vector indexes `_. Ensure that the index name provided is unique within the database context. Example: .. code-block:: python from neo4j import GraphDatabase from neo4j_graphrag.indexes import create_vector_index URI = "neo4j://localhost:7687" AUTH = ("neo4j", "password") INDEX_NAME = "vector-index-name" # Connect to Neo4j database driver = GraphDatabase.driver(URI, auth=AUTH) # Creating the index create_vector_index( driver, INDEX_NAME, label="Document", embedding_property="vectorProperty", dimensions=1536, similarity_fn="euclidean", fail_if_exists=False, ) Args: driver (neo4j.Driver): Neo4j Python driver instance. name (str): The unique name of the index. label (str): The node label to be indexed. embedding_property (str): The property key of a node which contains embedding values. dimensions (int): Vector embedding dimension similarity_fn (str): case-insensitive values for the vector similarity function: ``euclidean`` or ``cosine``. fail_if_exists (bool): If True raise an error if the index already exists. Defaults to False. neo4j_database (Optional[str]): The name of the Neo4j database. If not provided, this defaults to the server's default database ("neo4j" by default) (`see reference to documentation `_). Raises: ValueError: If validation of the input arguments fail. neo4j.exceptions.ClientError: If creation of vector index fails. )drivernamelabelembedding_property dimensions similarity_fnz(Error for inputs to create_vector_index NzCREATE VECTOR INDEX $name IF NOT EXISTSz FOR (n:z) ON n.zw OPTIONS { indexConfig: { `vector.dimensions`: toInteger($dimensions), `vector.similarity_function`: $similarity_fn } }zCreating vector index named '')rrr database_z$Neo4j vector index creation failed: ) rrr errorsloggerinfo execute_queryneo4j exceptions ClientErrormessage) rrrrrrfail_if_existsneo4j_databaseequerys T/opt/lhia/marcimex/agent/venv/lib/python3.12/site-packages/neo4j_graphrag/indexes.pycreate_vector_indexr+%sx 1!'   Y(~?(SS[\a[bbij|i}~} }   3D6;< m T$   6qxxzl C      ' 'Y DQYYKPQWXXYs/AAB BA<<BB?!B::B?c  t|||| d|rdndd|dd j |Dcgc] }d |zd z c}d }t j d |d|j|d|i|y#t$r"}td|j|d}~wwxYwcc}w#tjj$r}td|j|d}~wwxYw)a This method constructs a Cypher query and executes it to create a new fulltext index in Neo4j. See Cypher manual on `creating fulltext indexes `_. Ensure that the index name provided is unique within the database context. Example: .. code-block:: python from neo4j import GraphDatabase from neo4j_graphrag.indexes import create_fulltext_index URI = "neo4j://localhost:7687" AUTH = ("neo4j", "password") INDEX_NAME = "fulltext-index-name" # Connect to Neo4j database driver = GraphDatabase.driver(URI, auth=AUTH) # Creating the index create_fulltext_index( driver, INDEX_NAME, label="Document", node_properties=["vectorProperty"], fail_if_exists=False, ) Args: driver (neo4j.Driver): Neo4j Python driver instance. name (str): The unique name of the index. label (str): The node label to be indexed. node_properties (list[str]): The node properties to create the fulltext index on. fail_if_exists (bool): If True raise an error if the index already exists. Defaults to False. neo4j_database (Optional[str]): The name of the Neo4j database. If not provided, this defaults to the server's default database ("neo4j" by default) (`see reference to documentation `_). Raises: ValueError: If validation of the input arguments fail. neo4j.exceptions.ClientError: If creation of fulltext index fails. )rrrnode_propertiesz+Error for inputs to create_fulltext_index: NzCREATE FULLTEXT INDEX $name rrz FOR (n:`z `) ON EACH [z, zn.``]zCreating fulltext index named 'rrrz%Neo4j fulltext index creation failed ) rrr rjoinrr r!r"r#r$r%) rrrr-r&r'r(propr)s r*create_fulltext_indexr2~sjE?  *2_*UVg /J$54<#-JKLA O   5dV1=>UVTNnM 9!((* F  K    ' '3AII; ?  s>A5B(B#9B(5 B >BB #B((C#CC#c d}d|i}tjd|d|j|||y#tjj $r}t d|j|d}~wwxYw)a This method constructs a Cypher query and executes it to drop an index in Neo4j, if the index exists. See Cypher manual on `dropping vector indexes `_. Example: .. code-block:: python from neo4j import GraphDatabase from neo4j_graphrag.indexes import drop_index_if_exists URI = "neo4j://localhost:7687" AUTH = ("neo4j", "password") INDEX_NAME = "fulltext-index-name" # Connect to Neo4j database driver = GraphDatabase.driver(URI, auth=AUTH) # Dropping the index if it exists drop_index_if_exists( driver, INDEX_NAME, ) Args: driver (neo4j.Driver): Neo4j Python driver instance. name (str): The name of the index to delete. neo4j_database (Optional[str]): The name of the Neo4j database. If not provided, this defaults to the server's default database ("neo4j" by default) (`see reference to documentation `_). Raises: neo4j.exceptions.ClientError: If dropping of index fails. zDROP INDEX $name IF EXISTSrzDropping index named 'rrzDropping Neo4j index failed: N)rr r!r"r#r$r r%)rrr'r) parametersr(s r*drop_index_if_existsr5sLR, D   ,TF!45UJ.I    ' 'R =aii[IJPQQRs36A1A,,A1c|tjk(rt}n%|tjk(rt}n t dt |t k7r t dtfdDs t d t|Dcgc] \}}||d c}}|d} |j|| |y cc}}w#tjj$r} td| j| d } ~ wwxYw) a This method constructs a Cypher query and executes it to upsert (insert or update) embeddings on a set of nodes or relationships. Example: .. code-block:: python from neo4j import GraphDatabase from neo4j_graphrag.indexes import upsert_vectors URI = "neo4j://localhost:7687" AUTH = ("neo4j", "password") # Connect to Neo4j database driver = GraphDatabase.driver(URI, auth=AUTH) # Upsert embeddings data for several nodes upsert_vectors( driver, ids=['123', '456', '789'], embedding_property="vectorProperty", embeddings=[ [0.12, 0.34, 0.56], [0.78, 0.90, 0.12], [0.34, 0.56, 0.78], ], neo4j_database="neo4j", entity_type='NODE', ) Args: driver (neo4j.Driver): Neo4j Python driver instance. ids (List[int]): The element IDs of the nodes or relationships. embedding_property (str): The name of the property to store the vectors in. embeddings (List[List[float]]): The list of vectors to store, one per ID. neo4j_database (Optional[str]): The name of the Neo4j database. If not provided, defaults to the server's default database. 'neo4j' by default. entity_type (EntityType): Specifies whether to upsert to nodes ('NODE') or relationships ('RELATIONSHIP'). Defaults to 'NODE'. Raises: ValueError: If the lengths of IDs and embeddings do not match, or if embeddings are not of uniform dimension. Neo4jInsertionError: If an error occurs while attempting to upsert the vectors in Neo4j. z3entity_type must be either 'NODE' or 'RELATIONSHIP'z*ids and embeddings must be the same lengthc3RK|]}t|tdk( yw)rN)len).0 embedding embeddingss r* z!upsert_vectors..8s#P s9~Z]!33Ps$'z'All embeddings must be of the same size)idr:)rowsrquery_ parameters_rz#Upserting vectors to Neo4j failed: N)rNODEr RELATIONSHIPr ValueErrorr8allzipr!r"r#r$rr%) ridsrr;r' entity_typer)r=r:r4r(s ` r*upsert_vectorsrIsjjoo%,  // /4NOO 3x3z?"EFF PZP PBCC&)j%9!B  2#5   jN      ' '!1!)) =  s*CB=!C=CC> C99C>ctjdtd |||d}|jt||y#t j j$r}td|j|d}~wwxYw)an .. warning:: 'upsert_vector' is deprecated and will be removed in a future version, please use 'upsert_vectors' instead. This method constructs a Cypher query and executes it to upsert (insert or update) a vector property on a specific node. Example: .. code-block:: python from neo4j import GraphDatabase from neo4j_graphrag.indexes import upsert_vector URI = "neo4j://localhost:7687" AUTH = ("neo4j", "password") # Connect to Neo4j database driver = GraphDatabase.driver(URI, auth=AUTH) # Upsert the vector data upsert_vector( driver, node_id="nodeId", embedding_property="vectorProperty", vector=..., ) Args: driver (neo4j.Driver): Neo4j Python driver instance. node_id (int): The element id of the node. embedding_property (str): The name of the property to store the vector in. vector (list[float]): The vector to store. neo4j_database (Optional[str]): The name of the Neo4j database. If not provided, this defaults to the server's default database ("neo4j" by default) (`see reference to documentation `_). Raises: Neo4jInsertionError: If upserting of the vector fails. zk'upsert_vector' is deprecated and will be removed in a future version, please use 'upsert_vectors' instead. stacklevel)node_element_idrvectorr"Upserting vector to Neo4j failed: N warningswarnDeprecationWarningr!rr"r#r$rr%rnode_idrrOr'r4r(s r* upsert_vectorrWKsX MMu &"4  '~      ' '!0 <  =A8A33A8ctjdtd |||d}|jt||y#t j j$r}td|j|d}~wwxYw)a .. warning:: 'upsert_vector_on_relationship' is deprecated and will be removed in a future version, please use 'upsert_vectors' instead. This method constructs a Cypher query and executes it to upsert (insert or update) a vector property on a specific relationship. Example: .. code-block:: python from neo4j import GraphDatabase from neo4j_graphrag.indexes import upsert_vector_on_relationship URI = "neo4j://localhost:7687" AUTH = ("neo4j", "password") # Connect to Neo4j database driver = GraphDatabase.driver(URI, auth=AUTH) # Upsert the vector data upsert_vector_on_relationship( driver, node_id="nodeId", embedding_property="vectorProperty", vector=..., ) Args: driver (neo4j.Driver): Neo4j Python driver instance. rel_id (int): The element id of the relationship. embedding_property (str): The name of the property to store the vector in. vector (list[float]): The vector to store. neo4j_database (Optional[str]): The name of the Neo4j database. If not provided, this defaults to the server's default database ("neo4j" by default) (`see reference to documentation `_). Raises: Neo4jInsertionError: If upserting of the vector fails. z{'upsert_vector_on_relationship' is deprecated and will be removed in a future version, please use 'upsert_vectors' instead.rKrL)rel_element_idrrOrrPN rRrSrTr!r r"r#r$rr%rrel_idrrOr'r4r(s r*upsert_vector_on_relationshipr^sX MM F $"4  /~      ' '!0 <  rXcKtjdtd |||d}|jt||d{y7#t j j$r}td|j|d}~wwxYww)a .. warning:: 'async_upsert_vector' is deprecated and will be removed in a future version. This method constructs a Cypher query and asynchronously executes it to upsert (insert or update) a vector property on a specific node. Example: .. code-block:: python from neo4j import AsyncGraphDatabase from neo4j_graphrag.indexes import upsert_vector URI = "neo4j://localhost:7687" AUTH = ("neo4j", "password") # Connect to Neo4j database driver = AsyncGraphDatabase.driver(URI, auth=AUTH) # Upsert the vector data async_upsert_vector( driver, node_id="nodeId", embedding_property="vectorProperty", vector=..., ) Args: driver (neo4j.AsyncDriver): Neo4j Python asynchronous driver instance. node_id (int): The element id of the node. embedding_property (str): The name of the property to store the vector in. vector (list[float]): The vector to store. neo4j_database (Optional[str]): The name of the Neo4j database. If not provided, this defaults to the server's default database ("neo4j" by default) (`see reference to documentation `_). Raises: Neo4jInsertionError: If upserting of the vector fails. zL'async_upsert_vector' is deprecated and will be removed in a future version.rKrL)rVrrOrNrPrQrUs r*async_upsert_vectorr`sZ MMV "4 "" '~#       ' '!0 <  :B!A AA BA B&A??BBcKtjdtd |||d}|jt||d{y7#t j j$r}td|j|d}~wwxYww)a .. warning:: 'async_upsert_vector_on_relationship' is deprecated and will be removed in a future version. This method constructs a Cypher query and asynchronously executes it to upsert (insert or update) a vector property on a specific relationship. Example: .. code-block:: python from neo4j import AsyncGraphDatabase from neo4j_graphrag.indexes import upsert_vector_on_relationship URI = "neo4j://localhost:7687" AUTH = ("neo4j", "password") # Connect to Neo4j database driver = AsyncGraphDatabase.driver(URI, auth=AUTH) # Upsert the vector data async_upsert_vector_on_relationship( driver, node_id="nodeId", embedding_property="vectorProperty", vector=..., ) Args: driver (neo4j.AsyncDriver): Neo4j Python asynchronous driver instance. rel_id (int): The element id of the relationship. embedding_property (str): The name of the property to store the vector in. vector (list[float]): The vector to store. neo4j_database (Optional[str]): The name of the Neo4j database. If not provided, this defaults to the server's default database ("neo4j" by default) (`see reference to documentation `_). Raises: Neo4jInsertionError: If upserting of the vector fails. z\'async_upsert_vector_on_relationship' is deprecated and will be removed in a future version.rKrL)r]rrOrNrPr[r\s r*#async_upsert_vector_on_relationshiprc sZ MMf "4 "" /~#       ' '!0 <  rac$t|fdS)a Sorts the provided list of dictionaries containing index information so that any item whose 'name' key matches the given 'index_name' appears at the front of the list. Args: records (List[Dict[str, Any]]): The list of records containing index information to sort. index_name (str): The index name to match against the 'name' key of each dictionary. Returns: List[Dict[str, Any]]: A newly sorted list with items matching 'index_name' placed first. c,|jdk7S)Nr)get)x index_names r*z%_sort_by_index_name.._sv*)D)key)sorted)recordsrhs `r*_sort_by_index_namernMs$ 'D EErjc|jd|||d|}t|j|}t|dkDr|dSy)a Check if a vector index exists in a Neo4j database and return its information. If no matching index is found, returns None. Args: driver (neo4j.Driver): Neo4j Python driver instance. index_name (str): The name of the index to look up. label_or_type (str): The label (for nodes) or type (for relationships) of the index. embedding_property (str): The name of the property containing the embeddings. neo4j_database (Optional[str]): The name of the Neo4j database. If not provided, this defaults to the server's default database ("neo4j" by default) (`see reference to documentation `_). Returns: Optional[Dict[str, Any]]: A dictionary containing the first matching index's information if found, or None otherwise. a SHOW INDEXES YIELD name, type, entityType, labelsOrTypes, properties, options WHERE type = 'VECTOR' AND (name = $index_name OR (labelsOrTypes[0] = $label_or_type AND properties[0] = $embedding_property)) RETURN name, type, entityType, labelsOrTypes, properties, options)rh label_or_typerr?rNr!rnrmr8)rrhrprr'resultindex_informations r*retrieve_vector_index_infortbsc6 ! ! P%*"4 !"F,FNNJG ! ##rjc|jd|||d|}t|j|}t|dkDr|dSy)a Check if a full text index exists in a Neo4j database and return its information. If no matching index is found, returns None. Args: driver (neo4j.Driver): Neo4j Python driver instance. index_name (str): The name of the index to look up. label_or_type (str): The label (for nodes) or type (for relationships) of the index. text_properties (List[str]): The names of the text properties indexed. neo4j_database (Optional[str]): The name of the Neo4j database. If not provided, this defaults to the server's default database ("neo4j" by default) (`see reference to documentation `_). Returns: Optional[Dict[str, Any]]: A dictionary containing the first matching index's information if found, or None otherwise. aSHOW INDEXES YIELD name, type, entityType, labelsOrTypes, properties, options WHERE type = 'FULLTEXT' AND (name = $index_name OR (labelsOrTypes = [$label_or_type] AND properties = $text_properties)) RETURN name, type, entityType, labelsOrTypes, properties, options)rhrptext_propertiesr?rNrq)rrhrprvr'rrrss r*retrieve_fulltext_index_inforwsc4 ! ! P%*. !"F,FNNJG ! ##rj)FN)r neo4j.DriverrstrrryrryrintrzLiteral['euclidean', 'cosine']r&boolr' Optional[str]returnNone)rrxrryrryr-z list[str]r&r{r'r|r}r~)N)rrxrryr'r|r}r~)rrxrG List[str]rryr;zList[List[float]]r'r|rHrr}r~) rrxrVrzrryrO list[float]r'r|r}r~) rrxr]rzrryrOrr'r|r}r~) rneo4j.AsyncDriverrVrzrryrOrr'r|r}r~) rrr]rzrryrOrr'r|r}r~)rmList[neo4j.Record]rhryr}r) rrxrhryrpryrryr'r|r}Optional[neo4j.Record]) rrxrhryrpryrvrr'r|r}r)& __future__rloggingrRtypingrrrr"pydanticrneo4j_graphrag.neo4j_queriesrr r r r#r rtypesrrr getLogger__name__rr+r2r5rBrIrWr^r`rcrnrtrwrjr*rsV#** $=CC   8 $!$(VY VY VY VY VY  VY 2 VYVY"VY VY|!$( I I I I I  I " I IZFJ.R .R #.R5B.R .Rl%)(oo M M MM" M " M  M Mj%) = = ==  = " =  =J%) = = ==  = " =  =J%) > > >>  > " >  >L%) > > >>  > " >  >BF F-0FF4%) . ... . " .  .j"$$( - --- - " -  -rj