3fidZddlmZddlZddlZddlZddlmZmZm Z m Z m Z m Z m Z mZmZmZmZmZddlZddlZddlmZddlmZmZddlmZddlmZdd lm Z dd l!m"Z"m#Z#dd l$m%Z%dd l&m'Z'm(Z(m)Z)m*Z*dd l+m,Z,m-Z-ddl.m/Z/ej`e1Z2e e e3e3fZ4erddl5m6Z7ddl8m9Z9ddl:m;Z;ddld dZ?edddGdde"Z6d!dZ@d"dZAGdde#ZBy)#z%Wrapper around Redis vector database.) annotationsN) TYPE_CHECKINGAnyCallableDictIterableListMappingOptionalTupleTypeUnioncast) deprecated)#AsyncCallbackManagerForRetrieverRunCallbackManagerForRetrieverRun)Document) Embeddings)get_from_dict_or_env) VectorStoreVectorStoreRetriever) ConfigDict)_array_to_buffer_buffer_to_arraycheck_redis_module_exist get_client)REDIS_REQUIRED_MODULESREDIS_TAG_SEPARATOR)maximal_marginal_relevance)RedisQuery)RedisFilterExpression) RedisModelc d|z S)N)vals i/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/langchain_community/vectorstores/redis/base.py_default_relevance_scorer*;s s7Nc |j|jtjdy#tjdYyxYw)zCheck if Redis index exists.zIndex does not existFzIndex already existsT)ftinfologgerdebug)client index_names r)check_index_existsr3?sE *""$ LL'(   +,s 7Az0.3.13z1.0z langchain_redis.RedisVectorStore)sinceremovalalternative_importc"eZdZdZddddddZ d% d&d Zed'd Ze d% d(d Z e d% d)d Z e d* d+d Z ed,dZ d-dZ d* d.dZe d/dZ d0 d1dZd2dZedd d3 d4dZ d5 d6dZ d7 d8dZ d7 d9dZ d: d;dZddZ d? d@dZ d? d@dZ d? dAd ZdBdCd!ZdDd"ZdEd#Z dFd$Z!y)Gr uRedis vector database. Deployment Options: Below, we will use a local deployment as an example. However, Redis can be deployed in all of the following ways: - [Redis Cloud](https://redis.com/redis-enterprise-cloud/overview/) - [Docker (Redis Stack)](https://hub.docker.com/r/redis/redis-stack) - Cloud marketplaces: [AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-e6y7ork67pjwg?sr=0-2&ref_=beagle&applicationId=AWSMPContessa), [Google Marketplace](https://console.cloud.google.com/marketplace/details/redislabs-public/redis-enterprise?pli=1), or [Azure Marketplace](https://azuremarketplace.microsoft.com/en-us/marketplace/apps/garantiadata.redis_enterprise_1sp_public_preview?tab=Overview) - On-premise: [Redis Enterprise Software](https://redis.com/redis-enterprise-software/overview/) - Kubernetes: [Redis Enterprise Software on Kubernetes](https://docs.redis.com/latest/kubernetes/) Setup: Install ``redis``, ``redisvl``, and ``langchain-community`` and run Redis locally. .. code-block:: bash pip install -qU redis redisvl langchain-community docker run -d -p 6379:6379 -p 8001:8001 redis/redis-stack:latest Key init args — indexing params: index_name: str Name of the index. index_schema: Optional[Union[Dict[str, ListOfDict], str, os.PathLike]] Schema of the index and the vector schema. Can be a dict, or path to yaml file. embedding: Embeddings Embedding function to use. Key init args — client params: redis_url: str Redis connection url. Instantiate: .. code-block:: python from langchain_community.vectorstores.redis import Redis from langchain_openai import OpenAIEmbeddings vector_store = Redis( redis_url="redis://localhost:6379", embedding=OpenAIEmbeddings(), index_name="users", ) Add Documents: .. code-block:: python from langchain_core.documents import Document document_1 = Document(page_content="foo", metadata={"baz": "bar"}) document_2 = Document(page_content="thud", metadata={"bar": "baz"}) document_3 = Document(page_content="i will be deleted :(") documents = [document_1, document_2, document_3] ids = ["1", "2", "3"] vector_store.add_documents(documents=documents, ids=ids) Delete Documents: .. code-block:: python vector_store.delete(ids=["3"]) Search: .. code-block:: python results = vector_store.similarity_search(query="thud",k=1) for doc in results: print(f"* {doc.page_content} [{doc.metadata}]") .. code-block:: python * thud [{'id': 'doc:users:2'}] Search with filter: .. code-block:: python from langchain_community.vectorstores.redis import RedisTag results = vector_store.similarity_search(query="thud",k=1,filter=(RedisTag("baz") != "bar")) for doc in results: print(f"* {doc.page_content} [{doc.metadata}]") .. code-block:: python * thud [{'id': 'doc:users:2'}] Search with score: .. code-block:: python results = vector_store.similarity_search_with_score(query="qux",k=1) for doc, score in results: print(f"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]") .. code-block:: python * [SIM=0.167700] foo [{'id': 'doc:users:1'}] Async: .. code-block:: python # add documents # await vector_store.aadd_documents(documents=documents, ids=ids) # delete documents # await vector_store.adelete(ids=["3"]) # search # results = vector_store.asimilarity_search(query="thud",k=1) # search with score results = await vector_store.asimilarity_search_with_score(query="qux",k=1) for doc,score in results: print(f"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]") .. code-block:: python * [SIM=0.167700] foo [{'id': 'doc:users:1'}] Use as Retriever: .. code-block:: python retriever = vector_store.as_retriever( search_type="mmr", search_kwargs={"k": 1, "fetch_k": 2, "lambda_mult": 0.5}, ) retriever.invoke("thud") .. code-block:: python [Document(metadata={'id': 'doc:users:2'}, page_content='thud')] **Advanced examples:** Custom vector schema can be supplied to change the way that Redis creates the underlying vector schema. This is useful for production use cases where you want to optimize the vector schema for your use case. ex. using HNSW instead of FLAT (knn) which is the default .. code-block:: python vector_schema = { "algorithm": "HNSW" } rds = Redis.from_texts( texts, # a list of strings metadata, # a list of metadata dicts embeddings, # an Embeddings object vector_schema=vector_schema, redis_url="redis://localhost:6379", ) Custom index schema can be supplied to change the way that the metadata is indexed. This is useful for you would like to use the hybrid querying (filtering) capability of Redis. By default, this implementation will automatically generate the index schema according to the following rules: - All strings are indexed as text fields - All numbers are indexed as numeric fields - All lists of strings are indexed as tag fields (joined by langchain_community.vectorstores.redis.constants.REDIS_TAG_SEPARATOR) - All None values are not indexed but still stored in Redis these are not retrievable through the interface here, but the raw Redis client can be used to retrieve them. - All other types are not indexed To override these rules, you can pass in a custom index schema like the following .. code-block:: yaml tag: - name: credit_score text: - name: user - name: job Typically, the ``credit_score`` field would be a text field since it's a string, however, we can override this behavior by specifying the field type as shown with the yaml config (can also be a dictionary) above and the code below. .. code-block:: python rds = Redis.from_texts( texts, # a list of strings metadata, # a list of metadata dicts embeddings, # an Embeddings object index_schema="path/to/index_schema.yaml", # can also be a dictionary redis_url="redis://localhost:6379", ) When connecting to an existing index where a custom schema has been applied, it's important to pass in the same schema to the ``from_existing_index`` method. Otherwise, the schema for newly added samples will be incorrect and metadata will not be returned. content_vectorFLATCOSINEFLOAT32)name algorithmdimsdistance_metricdatatypeNc r|j| ddl} ||_||_ t dd|i|} t | t| |_ ||_ |j|||_ |||_ yd||_ y#t$r} td| d} ~ wwxYw#t$r} td| d} ~ wwxYw)z8Initialize Redis vector store with necessary components.rNRCould not import redis python package. Please install it with `pip install redis`. redis_urlzRedis failed to connect: zdoc:r')_check_deprecated_kwargsredis ImportErrorr2 _embeddingsrrr ValueErrorr1relevance_score_fn_get_schema_with_defaults_schema key_prefix) selfrDr2 embedding index_schema vector_schemarJrMkwargsrFe redis_clients r)__init__zRedis.__init__s %%f-  %$ >%D DVDL $\3I J# "455lMR (2(>*d:,DW% >   >8<= = >s.A=B= B BB B6#B11B6c|jS)z/Access the query embedding object if available.)rHrNs r) embeddingszRedis.embeddingsAsr+c  ddl}ddlm} t |dd} d|vr|j dd|vr|j dd} d|vr|j d} |st jj}|rt|tr"t|t|k7r td t|trt|dts td t|d} |r1| |}|| k7r&tj!d d |d zd| d zn| }|| ||f||d|}|j#||| } || fS#t$r} td| d} ~ wwxYw)a Create a Redis vectorstore from raw documents. This is a user-friendly interface that: 1. Embeds documents. 2. Creates a new Redis index if it doesn't already exist 3. Adds the documents to the newly created Redis index. 4. Returns the keys of the newly created documents once stored. This method will generate schema based on the metadata passed in if the `index_schema` is not defined. If the `index_schema` is defined, it will compare against the generated schema and warn if there are differences. If you are purposefully defining the schema for the metadata, then you can ignore that warning. To examine the schema options, initialize an instance of this class and print out the schema using the `Redis.schema`` property. This will include the content and content_vector classes which are always present in the langchain schema. Example: .. code-block:: python from langchain_community.vectorstores import Redis from langchain_community.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() redis, keys = Redis.from_texts_return_keys( texts, embeddings, redis_url="redis://localhost:6379" ) Args: texts (List[str]): List of texts to add to the vectorstore. embedding (Embeddings): Embeddings to use for the vectorstore. metadatas (Optional[List[dict]], optional): Optional list of metadata dicts to add to the vectorstore. Defaults to None. index_name (Optional[str], optional): Optional name of the index to create or add to. Defaults to None. index_schema (Optional[Union[Dict[str, ListOfDict], str, os.PathLike]], optional): Optional fields to index within the metadata. Overrides generated schema. Defaults to None. vector_schema (Optional[Dict[str, Union[str, int]]], optional): Optional vector schema to use. Defaults to None. **kwargs (Any): Additional keyword arguments to pass to the Redis client. Returns: Tuple[Redis, List[str]]: Tuple of the Redis instance and the keys of the newly created documents. Raises: ValueError: If the number of metadatas does not match the number of texts. rN) read_schemarCrD REDIS_URLgeneratekeys.Number of metadatas must match number of texts!Metadatas must be a list of dictsz`index_schema` does not match generated metadata schema. If you meant to manually override the schema, please ignore this message. zindex_schema:  zgenerated_schema: )rPrQ)r])rF-langchain_community.vectorstores.redis.schemarZrGrpopuuiduuid4hex isinstancelistlenrIdict_generate_field_schemar/warning add_texts)clstextsrO metadatasr2rPrQrRrFrZrSrDr]generated_schema user_schemainstances r)from_texts_return_keyszRedis.from_texts_return_keysFs@   Q)kJ & JJ{ #   JJz " V ::f%D))J )T*s9~U/K !QRRy$/Jy|T4R !DEE5ilC ),7 "22NN3+;-r:;//?.@C D 0     &'    !!%!>~A >  s E E EEc >|j||f||||d|\}} |S)a Create a Redis vectorstore from a list of texts. This is a user-friendly interface that: 1. Embeds documents. 2. Creates a new Redis index if it doesn't already exist 3. Adds the documents to the newly created Redis index. This method will generate schema based on the metadata passed in if the `index_schema` is not defined. If the `index_schema` is defined, it will compare against the generated schema and warn if there are differences. If you are purposefully defining the schema for the metadata, then you can ignore that warning. To examine the schema options, initialize an instance of this class and print out the schema using the `Redis.schema`` property. This will include the content and content_vector classes which are always present in the langchain schema. Example: .. code-block:: python from langchain_community.vectorstores import Redis from langchain_community.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() redisearch = RediSearch.from_texts( texts, embeddings, redis_url="redis://username:password@localhost:6379" ) Args: texts (List[str]): List of texts to add to the vectorstore. embedding (Embeddings): Embedding model class (i.e. OpenAIEmbeddings) for embedding queries. metadatas (Optional[List[dict]], optional): Optional list of metadata dicts to add to the vectorstore. Defaults to None. index_name (Optional[str], optional): Optional name of the index to create or add to. Defaults to None. index_schema (Optional[Union[Dict[str, ListOfDict], str, os.PathLike]], optional): Optional fields to index within the metadata. Overrides generated schema. Defaults to None. vector_schema (Optional[Dict[str, Union[str, int]]], optional): Optional vector schema to use. Defaults to None. **kwargs (Any): Additional keyword arguments to pass to the Redis client. Returns: Redis: Redis VectorStore instance. Raises: ValueError: If the number of metadatas does not match the number of texts. ImportError: If the redis python package is not installed. )ror2rPrQ)rs) rmrnrOror2rPrQrRrr_s r) from_textszRedis.from_textssEB1c00    !%'   !r+c t|dd}d|vr|jd||||f||d|}t|j|st d|d|S)a Connect to an existing Redis index. Example: .. code-block:: python from langchain_community.vectorstores import Redis from langchain_community.embeddings import OpenAIEmbeddings embeddings = OpenAIEmbeddings() # must pass in schema and key_prefix from another index existing_rds = Redis.from_existing_index( embeddings, index_name="my-index", schema=rds.schema, # schema dumped from another index key_prefix=rds.key_prefix, # key prefix from another index redis_url="redis://username:password@localhost:6379", ) Args: embedding (Embeddings): Embedding model class (i.e. OpenAIEmbeddings) for embedding queries. index_name (str): Name of the index to connect to. schema (Union[Dict[str, str], str, os.PathLike, Dict[str, ListOfDict]]): Schema of the index and the vector schema. Can be a dict, or path to yaml file. key_prefix (Optional[str]): Prefix to use for all keys in Redis associated with this index. **kwargs (Any): Additional keyword arguments to pass to the Redis client. Returns: Redis: Redis VectorStore instance. Raises: ValueError: If the index does not exist. ImportError: If the redis python package is not installed. rDr[)rPrMzRedis failed to connect: Index z does not exist.)rrbr3r1rI)rmrOr2schemarMrRrDrrs r)from_existing_indexzRedis.from_existing_indexs\)kJ  & JJ{ #     !    "(//:>1*=MN r+c6|jjS)zReturn the schema of the index.)rLas_dictrWs r)rxz Redis.schemacs||##%%r+ct|d5}tj|j|dddy#1swYyxYw)z Write the schema to a yaml file.zw+N)openyamldumprx)rNpathfs r) write_schemazRedis.write_schemahs5 $  & IIdkk1 % & & &s !7Ac x|j} |r$|j|tjdy#YyxYw)a Delete a Redis entry. Args: ids: List of ids (keys in redis) to delete. redis_url: Redis connection url. This should be passed in the kwargs or set as an environment variable: REDIS_URL. Returns: bool: Whether or not the deletions were successful. Raises: ValueError: If the redis python package is not installed. ValueError: If the ids (keys in redis) are not provided zEntries deletedTF)r1deleter/r.)rNidsrRr1s r)rz Redis.deletems=(  s# -. s&59c Vt|dd} ddl} d|vr|jdt d d|i|} |j |j|tjdy#t$r tdwxYw#t $r}t d|d}~wwxYw#Yy xYw) a Drop a Redis search index. Args: index_name (str): Name of the index to drop. delete_documents (bool): Whether to drop the associated documents. Returns: bool: Whether or not the drop was successful. rDr[rNrCzYour redis connected error: z Drop indexTFr') rrFrGrbrrIr- dropindexr/r.)r2delete_documentsrRrDrFr1rSs r) drop_indexzRedis.drop_indexs )kJ     Af$ ;'>)>v>F  IIj ! + +,< = KK %# >   A;A3?@ @ A s-A-"B5B$-B B!BB!$B(c "g}|jd|jd}|r`t|tr"t|t|k7r t dt|trt|dt s t d|xs$|j jt|}|jt|d|jjd} t|D]\} } |r|| n&ttjj} | j!|j"d zs|j"d z| z} |r|| ni} |r t%| n| } | j'| |j(j*| |j(j,t/|| |j(j0i|  |j3| | |zdk(s| j5 | j5|S) aAdd more texts to the vectorstore. Args: texts (Iterable[str]): Iterable of strings/text to add to the vectorstore. metadatas (Optional[List[dict]], optional): Optional list of metadatas. Defaults to None. embeddings (Optional[List[List[float]]], optional): Optional pre-generated embeddings. Defaults to None. keys (List[str]) or ids (List[str]): Identifiers of entries. Defaults to None. batch_size (int, optional): Batch size to use for writes. Defaults to 1000. Returns: List[str]: List of ids added to the vectorstore r]rr^rr_)dimF) transaction:)mapping)getrfrgrhrIrirHembed_documents_create_index_if_not_existr1pipeline enumeratestrrcrdre startswithrM_prepare_metadatahsetrL content_keycontent_vector_keyr vector_dtypeappendexecute)rNrnrorX batch_sizeclean_metadatarRr keys_or_idsritextkeymetadatas r)rlzRedis.add_textss0jjE):;  )T*s9~U/K !QRRy$/Jy|T4R !DEEP4#3#3#C#CDK#P  ''C 1 ,>'?;;''E': ' #GAt$/+a.S9I9I5JC>>$//C"78oo+c1'0y|bH6D(2(H MMLL,,dLL335E"1 t||'@'@6     JJsO:~"  "+ #0  r+c |jddxsg}|j|jtdd|i|d|iS)Ntags vectorstorer')rbextend_get_retriever_tagsRedisVectorStoreRetriever)rNrRrs r) as_retrieverzRedis.as_retrieversDzz&$'-2 D,,./(OTOVO$OOr+z0.0.1z)similarity_search(distance_threshold=0.1)) alternativec .|j|f||d|S)a* Returns the most similar indexed documents to the query text within the score_threshold range. Deprecated: Use similarity_search with distance_threshold instead. Args: query (str): The query text for which to find similar documents. k (int): The number of documents to return. Default is 4. score_threshold (float): The minimum matching *distance* required for a document to be considered a match. Defaults to 0.2. Returns: List[Document]: A list of documents that are most similar to the query text including the match score for each document. Note: If there are no documents that satisfy the score_threshold value, an empty list is returned. )kdistance_threshold)similarity_search)rNqueryrscore_thresholdrRs r)similarity_search_limit_scorez#Redis.similarity_search_limit_scores.2&t%%  ? >D  r+c 2 ddl}d|vrtjd|jj |}|j |f|||dd|\} } |jj|jj| | } g} | j D]} i}|r.d | j"i}|j%|j'| |j(j*}t-t/| || }|j1| j2}| j5||f| S#t$r}td|d}~wwxYw#|jj$r3}t|jddd k(r td ||d}~wwxYw) aRun similarity search with **vector distance**. The "scores" returned from this function are the raw vector distances from the query vector. For similarity scores, use ``similarity_search_with_relevance_scores``. Args: query (str): The query text for which to find similar documents. k (int): The number of documents to return. Default is 4. filter (RedisFilterExpression, optional): Optional metadata filter. Defaults to None. return_metadata (bool, optional): Whether to return metadata. Defaults to True. Returns: List[Tuple[Document, float]]: A list of documents that are most similar to the query with the distance for each document. rNrCrscore_threshold is deprecated. Use distance_threshold instead.score_threshold should only be used in similarity_search_with_relevance_scores.score_threshold will be removed in a future release.T)rfilter with_metadata with_distance SyntaxgQuery failed with syntax error. This is likely due to malformation of filter, vector, or query argumentid page_contentr)rFrGr/rkrH embed_query_prepare_queryr1r-r2search exceptions ResponseErrorrsplitrIdocsrupdate_collect_metadatarLrrgetattr_calculate_fp_distancedistancer)rNrrrreturn_metadatarRrFrSquery_embedding redis_query params_dictresultsdocs_with_scoresresultrrdocrs r)similarity_search_with_scorez"Redis.similarity_search_with_scores4    & NNI **66u=#64#6#6 $ ) $  $  [ kknnT__5<<[+VG:<ll 5FH &)), 6 6v >?,,22K (DxXC226??CH  # #S(O 4 5 i >  :-- 1v||C #x/ :  G s/D-5E - E6 EE F#.FFc h|jj|}|j|f||||d|S)aRun similarity search Args: query (str): The query text for which to find similar documents. k (int): The number of documents to return. Default is 4. filter (RedisFilterExpression, optional): Optional metadata filter. Defaults to None. return_metadata (bool, optional): Whether to return metadata. Defaults to True. distance_threshold (Optional[float], optional): Maximum vector distance between selected documents and the query vector. Defaults to None. Returns: List[Document]: A list of documents that are most similar to the query text. rrrr)rHrsimilarity_search_by_vector)rNrrrrrrRrs r)rzRedis.similarity_searchosM2**66u=/t//  +1     r+c  ddl}d|vrtjd|j |||||d\} } |j j |jj| | } g} | jD]p} i}|r.d | ji}|j!|j#| |j$j&}| j)t+t-| || r| S#t$r}td|d}~wwxYw#|jj$r3}t|jddd k(r td ||d}~wwxYw) aRun similarity search between a query vector and the indexed vectors. Args: embedding (List[float]): The query vector for which to find similar documents. k (int): The number of documents to return. Default is 4. filter (RedisFilterExpression, optional): Optional metadata filter. Defaults to None. return_metadata (bool, optional): Whether to return metadata. Defaults to True. distance_threshold (Optional[float], optional): Maximum vector distance between selected documents and the query vector. Defaults to None. Returns: List[Document]: A list of documents that are most similar to the query text. rNrCrrF)rrrrrrrrrr)rFrGr/rkrr1r-r2rrrrrrIrrrrrLrrrr)rNrOrrrrrRrFrSrrrrrrrs r)rz!Redis.similarity_search_by_vectorsu4    & NNI $(#6#6 1) $7$  [ kknnT__5<<[+VGll FH &)), 6 6v >?,,22K KKgfk&BXV   c >  6-- 1v||C #x/ :  G s.C25D2 D ; DD E(.EEc |jj|} |j| f||||d|} | D cgc]} | jd} } | D cgc]_} t t t |jj| |jj|jja}} ttj| |||}|Dcgc]}| | }}|Scc} wcc} wcc}w)aReturn docs selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents. Args: query (str): Text to look up documents similar to. k (int): Number of Documents to return. Defaults to 4. fetch_k (int): Number of Documents to fetch to pass to MMR algorithm. lambda_mult (float): Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5. filter (RedisFilterExpression, optional): Optional metadata filter. Defaults to None. return_metadata (bool, optional): Whether to return metadata. Defaults to True. distance_threshold (Optional[float], optional): Maximum vector distance between selected documents and the query vector. Defaults to None. Returns: List[Document]: A list of Documents selected by maximal marginal relevance. rr)dtype) lambda_multr)rHrrrrrbytesr1hgetrLrrrnparray)rNrrfetch_krrrrrRr prefetch_docsr prefetch_ids prefetch_idprefetch_embeddingsselected_indicesr selected_docss r)max_marginal_relevance_searchz#Redis.max_marginal_relevance_searchsF**66u=988  +1    7DDs T*D D ,   KK$$[$,,2Q2QRll//      6 HH_ %': WX 4DDaq)D D)E  EsC0A$C5 C:ci}|jjD]} t||||<|S#t$r?tj d|ddzdz|jjzd||<Y^wxYw)aCollect metadata from Redis. Method ensures that there isn't a mismatch between the metadata and the index schema passed to this class by the user or generated by this class. Args: result (Document): redis.commands.search.Document object returned from Redis. Returns: Dict[str, Any]: Collected metadata. z Metadata key z not found in metadata. zSetting to None. z+Metadata fields defined for this instance: N)rL metadata_keysrAttributeErrorr/rk)rNrmetars r)rzRedis._collect_metadata&s<<-- !C !#FC0S  ! " !#C5(@A+,CD3346 !S  !s0AA87A8cNdt||jji}|jjg}|r|j d|r%|j |jj |r||d<|j||||fS|j||||fS)Nvectorrr)r return_fields) rrLrrrrr_prepare_range_query_prepare_vector_query) rNrrrrrrrrs r)rzRedis._prepare_queryDs & 8Q8QR< 112    ,   !;!; < 0BK, -))fM*    & &q} & U   r+cD ddlm}|xsg}|jj}d|d}|rt |dz|z}|dz}||j |jdjd|jd S#t$r}td|d}~wwxYw) Nrr!rC@z+:[VECTOR_RANGE $distance_threshold $vector]rz =>{$yield_distance_as: distance}r) redis.commands.search.queryr"rGrLrrrsort_bypagingdialect) rNrrrr"rS vector_key base_query query_strings r)rzRedis._prepare_range_queryfs   9 &+ \\44  $OP Vs*Z7J!$FF  E,  ]M + WZ VAq\ WQZ   >  B B BBcD ddlm}|xsg}d}|r t|}|jj }d|d|d|d }||j |jd jd|jd } | S#t$r}td|d}~wwxYw) zPrepare query for vector search. Args: k: Number of results to return. filter: Optional metadata filter. Returns: query: Query object. rr!rCN*(z)=>[KNN z @z $vector AS distance]rr) rr"rGrrLrrrrr) rNrrrr"rS query_prefixrrrs r)rzRedis._prepare_vector_querys  9 &+  !&k]L\\44 hqcJ  rcLddlm}m}|}|r ||}|di|}|j |j|rt j d|S#t$rB|jj}|r|j||j|Y|SwxYw)Nr)r$rZzP`vector_schema` is ignored since content_vector is overridden in `index_schema`.r') rar$rZadd_content_fieldr8r/rkrIDEFAULT_VECTOR_SCHEMAcopyradd_vector_field)rNrPrQr$rZrx schema_values vector_fields r)rKzRedis._get_schema_with_defaultss   ' 5M0-0F  $ $ &  2  ! !6  2 55::  s B22Cc|jjjdk(rtt |dStt |dS)zCalculate the distance based on the vector datatype Two datatypes supported: - FLOAT32 - FLOAT64 if it's FLOAT32, we need to round the distance to 4 decimal places otherwise, round to 7 decimal places. r<)rLr8rAroundfloat)rNrs r)rzRedis._calculate_fp_distances> << & & / /9 <x!, ,U8_a((r+cxddddddd}|jD]\}}||vs td|d||dy) zCheck for deprecated kwargs.rDrPrQ) redis_host redis_portredis_passwordrrr@zKeyword argument 'z' is deprecated. Please use 'z ' instead.N)itemsrI)rNrRdeprecated_kwargsrvalues r)rEzRedis._check_deprecated_kwargssn&%))).  !,,. JC'' (.##4S#9":*F r+c|jr |jS|j|j|jd} ||jj j S#t$r tcYSwxYw)N)r;IPL2) rJ_cosine_relevance_score_fn%_max_inner_product_relevance_score_fn_euclidean_relevance_score_fnrLr8r@KeyErrorr*)rN metric_maps r)_select_relevance_score_fnz Redis._select_relevance_score_fnsp  " "** *55<<44  ,dll99IIJ J ,+ + ,s"A!!A32A3)NNNN)rDrr2rrOrrP8Optional[Union[Dict[str, ListOfDict], str, os.PathLike]]rQ$Optional[Dict[str, Union[str, int]]]rJz"Optional[Callable[[float], float]]rM Optional[str]rRr)returnzOptional[Embeddings])rn List[str]rOrroOptional[List[dict]]r2r'rPr%rQr&rRrr(zTuple[Redis, List[str]])rmz Type[Redis]rnr)rOrror*r2r'rPr%rQr&rRrr(r )N) rOrr2rrxzEUnion[Dict[str, ListOfDict], str, os.PathLike, Dict[str, ListOfDict]]rMr'rRrr(r )r(zDict[str, List[Any]])rzUnion[str, os.PathLike]r(None)rOptional[List[str]]rRrr(bool)r2rrr-rRrr(r-)NNiT)rnz Iterable[str]ror*rXzOptional[List[List[float]]]rintrr-rRrr(r))rRrr(r)rg?) rrrr.rrrRrr(List[Document])rNT) rrrr.rOptional[RedisFilterExpression]rr-rRrr(zList[Tuple[Document, float]])rNTN)rrrr.rr0rr-rOptional[float]rRrr(r/)rO List[float]rr.rr0rr-rr1rRrr(r/)rg?NTN)rrrr.rr.rrrr0rr-rr1rRrr(r/)rz 'Document'r(Dict[str, Any])rNNTF)rr2rr.rr0rr1rr-rr-r(zTuple['Query', Dict[str, Any]])NN)rr.rr0rr,r(z'Query')rPr%rQr&r(z 'RedisModel')r:)rr.r(r+)rrr(r)rRzMapping[str, Any]r(r+)r(zCallable[[float], float])"__name__ __module__ __qualname____doc__rrUpropertyrX classmethodrsrvryrxrr staticmethodrrlrrrrrrrrrrrrKrrrEr$r'r+r)r r JsDN!# RV>BAE$(#X#X#X #X O #X < #X?#X"#X#XJ   +/$(QU>BEEE( E " E O E<EE !EEN +/$(QU>BI III( I " I O I<II IIV %) FFFV F " F  F FFP&&&$(   >&&&&  &&V+/26# CC(C0 C  C  CC CJP %PQ?B    7< NQ  R >26 $ Q Q  Q 0 Q  Q  Q  &Q l26 $.2 ! !  ! 0 !  ! , ! !  ! L26 $.2 NN N0 N  N , NN Nf 26 $.2BB B B  B 0 BB,BB BHB26.2"#  $     0  ,       (  J37-1   0 +    B37-1 $ $0$+ $  $PRV>B/N/</  /b8 )$ ,r+r c.gggd}|jD]'\}} t||djd|i)|S#ttf$rYnwxYw|Dt |t tfrV|rt |dtr|djd|in)t|dj}td|d|t |tr|djd|it|j}td d |d|z) a1 Generate a schema for the search index in Redis based on the input metadata. Given a dictionary of metadata, this function categorizes each metadata field into one of the three categories: - text: The field contains textual data. - numeric: The field contains numeric data (either integer or float). - tag: The field contains list of tags (strings). Args data (Dict[str, Any]): A dictionary where keys are metadata field names and values are the metadata values. Returns: Dict[str, Any]: A dictionary with three keys "text", "numeric", and "tag". Each key maps to a list of fields that belong to that category. Raises: ValueError: If a metadata field cannot be categorized into any of the three known types. )rnumerictagr=r=rr>z+List/tuple values should contain strings: 'z': rz2Could not generate Redis index field type mapping zfor metadata: ') rr.rrI TypeErrorrfrgtuplertyper5)datarrrr=s r)rjrj&sF.F jjl" U  J 9  $ $fc] 3  " H M=I&    =  edE] +JuQx5u $$fc]3E!H~.. A#c$P  eS ! 6N ! !63- 0 E{## @uCv. /  s!AAAcBdd}i}|jD]\}}|d||<t|tttfr|||</t|t t fr8|rt|dtrtj|||<s|||}||||S)a Prepare metadata for indexing in Redis by sanitizing its values. - String, integer, and float values remain unchanged. - None or empty values are replaced with empty strings. - Lists/tuples of strings are joined into a single string with a comma separator. Args: metadata (Dict[str, Any]): A dictionary where keys are metadata field names and values are the metadata values. Returns: Dict[str, Any]: A sanitized dictionary ready for indexing in Redis. Raises: ValueError: If any metadata value is not one of the known types (string, int, float, or list of strings). cRtd|ddt|jz)NzMetadata value for key 'z' must be a string, int, zfloat, or list of strings. Got )rIrAr5)rrs r) raise_errorz&_prepare_metadata..raise_error}s7&se+D E/U 0D0D/EF G  r+r)rrrrr(r+) rrfrr.rrgr@rjoin)rrE clean_metarrs r)rris( 57Jnn&$ U = JsO  ec3. /#JsOe} -JuQx5"5":":5"A 3C' U #!$" r+ceZdZUdZded< dZded< ddd d Zd ed < gd Z edZ ddZ ddZ ddZ ddZ y )rz Retriever for Redis VectorStore.r r similarityr search_typerg?N)rrrr4 search_kwargs)rJsimilarity_distance_thresholdsimilarity_score_thresholdmmrT)arbitrary_types_allowedc |j|z}|jdk(r|jj|fi|}|S|jdk(r/|d t d|jj|fi|}|S|jdk(r3|jj |fi|}|Dcgc]\}}| }}}|S|jdk(r|jj |fi|}|St d|jdcc}}w NrJrMrzOdistance_threshold must be provided for similarity_distance_threshold retrieverrNrOzsearch_type of z not allowed.)rLrKrrrI'similarity_search_with_relevance_scoresr rNr run_managerrR_kwargsrdocs_and_similaritiesrrus r)_get_relevant_documentsz1RedisVectorStoreRetriever._get_relevant_documentssI$$v-   | +54##55eGwGD( '  !@ @+,4 @64##55eGwGD   != =H  HH$ " '< D5 D-4D5D3 D5)D5+D5-D5c <|jj|fi|S)Add documents to vectorstore.)r add_documentsrN documentsrRs r)r`z'RedisVectorStoreRetriever.add_documentss -t--iB6BBr+cXK|jj|fi|d{S7w)r_N)raadd_documentsras r)rdz(RedisVectorStoreRetriever.aadd_documentss,5T%%44YI&IIIIs !*(*)rrrUrrRrr(r/)rrrUrrRrr(r/)rbr/rRrr(r))r5r6r7r8__annotations__rKrLallowed_search_typesr model_configrXr]r`rdr'r+r)rrs*#K#" %M> !   $L*HTW 69     @CJ'J36J Jr+r)r(rr(r)r1 RedisTyper2rr(r-)rBr4r(r4)rr4r(r4)Cr8 __future__rloggingosrctypingrrrrrr r r r r rrnumpyrr~langchain_core._apirlangchain_core.callbacksrrlangchain_core.documentsrlangchain_core.embeddingsrlangchain_core.utilsrlangchain_core.vectorstoresrrpydanticr#langchain_community.utilities.redisrrrr0langchain_community.vectorstores.redis.constantsrr&langchain_community.vectorstores.utilsr getLoggerr5r/r ListOfDict redis.clientr rhrr".langchain_community.vectorstores.redis.filtersr#rar$r*r3rjrrr'r+r)r|s+"      *.05I N   8 $ $sCx. ! /1TH E6XV,KV,V,r&@F,^cJ 4cJr+