jQj\"ddlZddlmZddlmZddlmZmZmZm Z m Z m Z m Z ddl mZddl mZddl mZdd l mZdd l mZdd l mZdd l mZdd l mZddlmZmZddlmZddlmZmZm Z ddl!m"Z"ddl#m$Z$ddl%m&Z&m'Z'm(Z(m)Z)ddl*m+Z+m,Z,ddl-m.Z.ddl/m0Z0m1Z1ddl2m3Z4ddl2m5Z6ddl2m7Z7ddl8m9Z9m:Z:m;Z;mZ>m?Z?m@Z@mAZAmBZBddlCmDZDddlCmEZEddlFmGZGmHZHmIZIddlJmKZKddlLmMZMmNZNmOZOdd lPmQZQdd!l mRZRdd"lSmTZTmUZUmVZVmWZWdd#lXmYZYmZZZm[Z[m\Z\e rdd$l]m^Z^d%e_fd&Z`d'e_d(eee_e_fd)dfd*Za dYdd+dddddddd,dddd- d'eed.ee_d/e_d0ee_d1ee_d2eed3eeebefd4ee"ee_e fdfd(eee_e_fd5eeRd6ecd7ee_d8eee_e_fd9ee e_d:e d)ef d;Zdd?dddd?d@d@d,dA dBe_dCeQdDe_dEeebdFecdGeecdHeecdIee e_dJecdKebdLebdMecd)e efdNZdOZddPeee_e_fd)eee_e_ffdQZfd,dRdSe_dTecd)efdUZgdd+ddddddd,dddV d'ed.ee_d/e_d0ee_d1ee_d2eed4eee"ee_e ffd(eee_e_fd5eeRd6ecd8eee_e_fd)efdWZhgdXZiy)ZN)ThreadPoolExecutor) timedelta)DictOptionalUnionAnyListIterable TYPE_CHECKING) __version__)connect)FtsToken)FunctionErrorFragment)FunctionErrorRecord)FunctionErrors) RTEWriteSpec)tokenize)URI sanitize_uri)urlparse)AsyncConnection DBConnectionLanceDBConnection) ClientConfig)RemoteDBConnection)Exprcollitfunc)blobvector) BlobReader)AsyncJobJob) AsyncQuery)Query)QueryDescription) AssignmentMappingFunctionArtifactRequestFunctionApplicationFunctionBindingFunctionRegistrationRequestFunctionVersionPythonRuntimeSpecRefreshColumnResult UdfDefinitionudf) EnvVarSecret) SecretInfo)AsyncMaterializedViewMaterializedViewMaterializedViewDefinition)ViewDescription) AsyncTableCompactionOptionsTable)BaseTokenizerType)Session)connect_namespaceconnect_namespace_asyncLanceNamespaceDBConnectionAsyncLanceNamespaceDBConnection) AsyncCatalogCatalogconnect_catalogconnect_catalog_asyncBlobTypenamec`|dk(rddlm}|td<|Stdtd|)NrGr rFzmodule z has no attribute )schemarGglobalsAttributeError__name__)rHrGs U/home/oem/CyberBrain26-unified/.venv/lib/python3.12/site-packages/lancedb/__init__.py __getattr__rOHs7 z$ ( * 78,.@I JJuristorage_optionsreturnct|tr|jdsyt|}|j}d|vryddh}xrt fd|D}|st d|dy) a Check if an S3 URI has a bucket name containing dots and warn if no region is specified. S3 buckets with dots cannot use virtual-hosted-style URLs, which breaks automatic region detection. See: https://github.com/lancedb/lancedb/issues/1898 zs3://N.region aws_regionc3&K|]}|v ywN).0krRs rN z-_check_s3_bucket_with_dots..fs(S!o)=(SszS3 bucket name 'a' contains dots, which prevents automatic region detection. Please specify the region explicitly via storage_options={'region': ''} or storage_options={'aws_region': ''}. See https://github.com/lancedb/lancedb/issues/1898 for details.) isinstancestr startswithrnetlocany ValueError)rQrRparsedbucket region_keys has_regions ` rN_check_s3_bucket_with_dotsrhQs c3 s~~g'> c]F ]]F &\*K SS(S{(S%SJ vh'N O   rP us-east-1F) api_keyrV host_overridesql_host_overrideread_consistency_intervalrequest_thread_pool client_configrRsessionmanifest_enablednamespace_client_implnamespace_client_properties$namespace_client_pushdown_operationsrjrVrkrlrmrnrorprqrrrsrtkwargsc | .| td|rtd|t| | ||| | S| | s td| td| tdt|tr|j dr|j Dcic] \}}|dvr||}}}|rtd|| t d | r t d |tjjd }|td |t|tr t|}t||||f|||||d |Stt|||rtd|t|||| | | Scc}}w)aUConnect to a LanceDB database. Parameters ---------- uri: str or Path, optional The uri of the database. When ``namespace_client_impl`` is provided you may omit ``uri`` and connect through a namespace client instead. api_key: str, optional If presented, connect to LanceDB cloud. Otherwise, connect to a database on file system or cloud storage. Can be set via environment variable `LANCEDB_API_KEY`. OAuth configuration is currently supported only by ``connect_async``; synchronous LanceDB Cloud connections require an API key. region: str, default "us-east-1" The region to use for LanceDB Cloud. host_override: str, optional The override url for LanceDB Cloud. sql_host_override: str, optional The remote SQL service endpoint override. The client connects lazily when SQL is first executed and retains that connection. read_consistency_interval: timedelta, default None The interval at which to check for updates to the table from other processes. If None, then consistency is not checked. For performance reasons, this is the default. For strong consistency, set this to zero seconds. Then every read will check for updates from other processes. As a compromise, you can set this to a non-zero timedelta for eventual consistency. If more than that interval has passed since the last check, then the table will be checked for updates. Note: this consistency only applies to read operations. Write operations are always consistent. Stronger consistency is not free. The smaller the interval, the more often each read pays the cost of checking for updates against object storage, raising per-read latency and cost. client_config: ClientConfig or dict, optional Configuration options for the LanceDB Cloud HTTP client. If a dict, then the keys are the attributes of the ClientConfig class. If None, then the default configuration is used. storage_options: dict, optional Additional options for the storage backend. See available options at manifest_enabled : bool, default False When true for local/native connections, use directory namespace manifests as the source of truth for table metadata. Existing directory-listed root tables are migrated into the manifest on access. session: Session, optional (For LanceDB OSS only) A session to use for this connection. Sessions allow you to configure cache sizes for index and metadata caches, which can significantly impact memory use and performance. They can also be re-used across multiple connections to share the same cache state. namespace_client_impl : str, optional When provided along with ``namespace_client_properties``, ``connect`` returns a namespace-backed connection by delegating to :func:`connect_namespace`. The value identifies which namespace implementation to load (e.g., ``"dir"`` or ``"rest"``). namespace_client_properties : dict, optional Configuration to pass to the namespace client implementation. Required when ``namespace_client_impl`` is set. namespace_client_pushdown_operations : list[str], optional Only used when ``namespace_client_properties`` is provided. Forwards to :func:`connect_namespace` to control which operations are executed on the namespace service (e.g., ``["QueryTable", "CreateTable"]``). Examples -------- For a local directory, provide a path for the database: >>> import lancedb >>> db = lancedb.connect("~/.lancedb") For object storage, use a URI prefix: >>> db = lancedb.connect( # doctest: +SKIP ... "s3://my-bucket/lancedb", ... storage_options={ ... "aws_access_key_id": "***", ... "aws_secret_access_key": "***", ... "aws_region": "us-east-1", ... }, ... ) For Azure Blob Storage, credentials can be passed directly without setting environment variables: >>> azure_storage_options = { ... "account_name": "some-account", ... "account_key": "some-key", ... } >>> db = lancedb.connect( # doctest: +SKIP ... "az://my-container/my-database", ... storage_options=azure_storage_options, ... ) For tests and temporary data, use an in-memory database: >>> db = lancedb.connect("memory://") In-memory databases are not persisted. Tables are dropped when the last connection or table handle referencing them is closed. Connect to LanceDB cloud: >>> db = lancedb.connect("db://my_database", api_key="ldb_...", ... client_config={"retry_config": {"retries": 5}}) Connect to a namespace-backed database: >>> db = lancedb.connect(namespace_client_impl="dir", ... namespace_client_properties={"root": "/tmp/ns"}) Returns ------- conn : DBConnection A connection to a LanceDB database. zNnamespace_client_properties must be provided when namespace_client_impl is setzUnknown keyword arguments: )rmrRrprtzjnamespace_client_impl must be provided when using namespace_client_properties unless manifest_enabled=TruezVnamespace_client_pushdown_operations is only valid when connecting through a namespacez>uri is required when not connecting through a namespace clientzdb://)connection_timeout read_timeoutz/session is not supported for remote connectionsz8manifest_enabled is not supported for remote connectionsLANCEDB_API_KEYz1api_key is required to connect to LanceDB cloud: )rlrnrorRrm)rmrRrprqrs)rcr>r^r_r`itemsNotImplementedErrorosenvirongetintrrrhr)rQrjrVrkrlrmrnrorRrprqrrrsrtrukeyvalueunknown_kwargss rNrrrsN( & ./  :6(CD D ! '&?+1U   #.7G G  ,7 -   { L  #sw 7 %lln U@@ J  :>:JKL L  %&WX X %J  ?jjnn%67G ?PQTPUVW W )3 /"45H"I !      0 3'+&?    s3x9 6vh?@@  ";')$?  K sE#simpleEnglish(T base_tokenizerlanguagemax_token_length lower_casestemremove_stop_wordscustom_stop_words ascii_foldingngram_min_lengthngram_max_length prefix_onlyqueryrrrrrrrrrrrc 0t|||||||||| | |  S)aiTokenize a full-text search query using an explicit tokenizer. This does not require an FTS index. The tokenizer options match :class:`lancedb.index.FTS`. ``custom_stop_words`` accepts a list of strings. When ``stem`` or ``remove_stop_words`` is None, the base tokenizer's default applies: False for ``code`` and ``ngram``, True otherwise. r) _tokenize) rrrrrrrrrrrrs rNrrKs5.  %) ++#))  rP_lancedb_worker_propsc|Dcgc]}|jts|}}|s|St|}|D]*}|j|}|t td}|||<,|Scc}w)aApply worker property overrides. Any key starting with ``_lancedb_worker_`` is extracted, the prefix is stripped, and the resulting key-value pair is put back into the map (overriding the existing value if present). The original prefixed key is removed. N)r`WORKER_PROPERTY_PREFIXdictpoplen)rr\ worker_keysresultrrreal_keys rN_apply_worker_overridesrusz$Lq||4J'K1LKL  %[F! 3s1245 x! MMs A&A&) for_workerdatarc ddl}|j|}|jd}|jd}| t|nd}|jd}|dk(rMt |jdxsi}|r t |}t |d ||||jd  S|d k(r2t|d |||jdd|jdS|dk(rUt|d|d|jdd|jd|jd|jd|Std|)afReconstruct a DBConnection from a serialized string. The string must have been produced by :meth:`DBConnection.serialize`. Parameters ---------- data : str String produced by ``serialize()``. for_worker : bool, default False When ``True``, any namespace client property whose key starts with ``_lancedb_worker_`` has that prefix stripped and the value overrides the corresponding property. For example, ``_lancedb_worker_uri`` replaces ``uri``. Returns ------- DBConnection A new connection matching the serialized state. rNconnection_type!read_consistency_interval_seconds)secondsrR namespacersrrrt)rrrsrmrRrtlocalrQrqF)rmrRrqrsremotedb_urlrjrVrirkrlro)rkrlrorRzUnknown connection_type: ) jsonloadsr~rrrr>rrrc) rrrrdrrci_secsrcirRrs rNdeserialize_connrsb2 ZZ Fjj!23Ozz=>H)1)=)H %4Cjj!23O+%VZZ =>D"E +E2E "()@"A(-&)+1762    G # 5M&)+#ZZ(:EB(. 3P(Q    H $! 8  9  JJx - **_5$jj)<= **_5+  4_4EFGGrP) rjrVrkrlrmrorRrprqrs oauth_configc K||j} nd} t|tr tdi|}t t ||t tt|||||| |||| | | d{S7w)aConnect to a LanceDB database. Parameters ---------- uri: str or Path The uri of the database. api_key: str, optional If present, connect to LanceDB cloud. Otherwise, connect to a database on file system or cloud storage. Can be set via environment variable `LANCEDB_API_KEY`. region: str, default "us-east-1" The region to use for LanceDB Cloud. host_override: str, optional The override url for LanceDB Cloud. sql_host_override: str, optional The remote SQL service endpoint override. The client connects lazily when SQL is first executed and retains that connection. read_consistency_interval: timedelta, default None The interval at which to check for updates to the table from other processes. If None, then consistency is not checked. For performance reasons, this is the default. For strong consistency, set this to zero seconds. Then every read will check for updates from other processes. As a compromise, you can set this to a non-zero timedelta for eventual consistency. If more than that interval has passed since the last check, then the table will be checked for updates. Note: this consistency only applies to read operations. Write operations are always consistent. Stronger consistency is not free. The smaller the interval, the more often each read pays the cost of checking for updates against object storage, raising per-read latency and cost. client_config: ClientConfig or dict, optional Configuration options for the LanceDB Cloud HTTP client. If a dict, then the keys are the attributes of the ClientConfig class. If None, then the default configuration is used. storage_options: dict, optional Additional options for the storage backend. See available options at session: Session, optional (For LanceDB OSS only) A session to use for this connection. Sessions allow you to configure cache sizes for index and metadata caches, which can significantly impact memory use and performance. They can also be re-used across multiple connections to share the same cache state. manifest_enabled : bool, default False When true for local/native connections, use directory namespace manifests as the source of truth for table metadata. Existing directory-listed root tables are migrated into the manifest on access. namespace_client_properties : dict, optional Additional directory namespace client properties to use with ``manifest_enabled=True``. oauth_config : OAuthConfig, optional OAuth configuration for LanceDB Cloud/Enterprise. This is supported by ``connect_async`` only; synchronous ``connect`` uses API key authentication for ``db://`` URIs. Examples -------- >>> import lancedb >>> azure_storage_options = { ... "account_name": "some-account", ... "account_key": "some-key", ... } >>> async def doctest_example(): ... # For a local directory, provide a path to the database ... db = await lancedb.connect_async("~/.lancedb") ... # For object storage, use a URI prefix ... db = await lancedb.connect_async("s3://my-bucket/lancedb", ... storage_options={ ... "aws_access_key_id": "***"}) ... # Azure credentials can also be passed directly ... db = await lancedb.connect_async( ... "az://my-container/my-database", ... storage_options=azure_storage_options, ... ) ... # For tests and temporary data, use an in-memory database ... db = await lancedb.connect_async("memory://") ... # Connect to LanceDB cloud ... db = await lancedb.connect_async("db://my_database", api_key="ldb_...", ... client_config={ ... "retry_config": {"retries": 5}}) Returns ------- conn : AsyncConnection A connection to a LanceDB database. NrZ) total_secondsr^rrrhr_rlancedb_connectr) rQrjrVrkrlrmrorRrprqrsrread_consistency_interval_secss rN connect_asyncrsN!,)B)P)P)R&)-&-&$5}5 s3x9        *     '     sA-A:/A80 A:)(rCrBrDrEr5r6r7r8rrrr>r?rr$ AsyncSqlQueryrAr9r:rrrr rrrr!rGr"rr%r(SqlQueryrr@rrr=r;r rY)jr|concurrent.futuresrdatetimertypingrrrrr r r _lancedbr rrrrrrrrrcommonrr urllib.parserdbrrrrr remote.dbrexprrrrr rJr!r" _blob_readerr#jobr$r%sqlr&rr'rr( functionsr)r*r+r,r-r.r/r0r1r2secretsr3r4materialized_viewr5r6r7viewr8tabler9r:r;typesr<r=rr>r?r@rAcatalogrBrCrDrE lance.blobrGr_rOrhrboolrrrrr__all__rZrPrNrsG  1LLL00D@6"+%!@@ )&& 2,"!   2- 577$/KcK  'S#X7   DV"#''+59DH?C04!%"+/<@@DV #Vc]V  V C= V  } V ( 2V"%-?(?"@AVtCH~t;<Vd38n-Vg VV$C=V"*$sCx.!9V+349*=V !V"#Vx)1&((,-1$ $&$ $ sm $  $ 4.$ ~$ S *$$$$$h$N,4S>d38n,BH BHBH BHP"#''+59CG04!%"<@@ @c]@  @ C= @  } @ ( 2@E,S#X">?@@d38n-@g @@"*$sCx.!9@@F) rP