NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI · #348 most downloaded on PyPI
A python native Weaviate client
Last release 25 days ago
07 Sep 2026
Ships fairly regularly
a new release about every 3 weeks
Nearly every release is documented
notes for 60 of the last 60 stable releases
1 version withdrawn
withdrawn after publishing
7 years old
296 releases · first in 2019
Increase version of requests library by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/353
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.19.2...v3.20.0
This minor version includes:
Increase maximum version of request library to 2.31.0. This also updates to urllib 2.0. This may contain minor breaking changes if you use urllib in other projects in the same virtual environment.
Add licensing information to pypi package
Increase default embedded version to 1.19.7
One column per quarter.
Add custom headers to all requests by @antas-marcin in https://github.com/weaviate/weaviate-python-client/pull/339
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.19.1...v3.19.2
This patch version includes:
Add custom headers to all requests
Support properties field in generative groupedResult field
Fix imports without grcp by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/334
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.19.0...v3.19.1
This patch version includes:
Fixes imports of of weaviate_pb2.
Fix rest get types by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/323
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.18.0...v3.19.0
This minor version includes:
Increases default embedded version to 1.19.3
Clients emits warning if used weaviate version is too old (3 versions behind latest minor version)
Adds native support for querying reference properties
result = client.query.get( "Article", ["title", "url", "wordCount", LinkTo(link_on="caller", linked_class="Person", properties=["name"])] )
Adds dataclasses to easier access to additional properties:
query = client.query.get("Test").with_additional( weaviate.AdditionalProperties( uuid=True, vector=True, creationTimeUnix=True, lastUpdateTimeUnix=True, distance=True, ) )
Typing fixes
BM25 and hybrid search
Additional properties (via dataclass shown above)
Querying reference properties (via dataclass shown above)
Nothing published for this version
Nothing published for this version
Fix publishing of documentation to readthedocs by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/320
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.17.1...v3.18.0
This minor version includes:
Add support for properties with hybrid search
Fixes documentation publishing on readthedocs
Fix schemas with indexFilterable and indexSearchable by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/316
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/3.17.0...v3.17.1
This patch version includes:
Fix schemas with new property keys indexFilterable and indexSearchable.
Add optional options to client by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/302
Get{} tunable consistency by @parkerduckworth in https://github.com/weaviate/weaviate-python-client/pull/285Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.16.2...3.17.0
This minor version includes:
Add support for groupBy to group objects:
.with_group_by(properties=["caller"], groups=2, objects_per_group=3)
Add support for uuid and uuid[] datatypes.
Add schema.exists(class).
Add support for Support GQL Get{} tunable consistency:
resp = ( client.query.get("Article", ["name"]) .with_additional("isConsistent") .with_consistency_level(ConsistencyLevel.ALL) .do() )
Fix urls containing username and password by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/304
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.16.1...v3.16.2
This patch version includes:
Fix url containing username and password.
Ignore timeouts for grcp port by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/301
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.16.0...v3.16.1
This patch version includes:
Fixes timeout error in detection of grpc.
Minimum supported version is python 3.8 by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/271
pip install weaviate-client[GRPC] or install the grpcio package manually.grpcio package.Get with NearObject or NearVector if only non-reference queries are retrieved and no other options are set.Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.15.6...v3.16.0
This minor version includes:
Can by enabled by installing the client with pip install weaviate-client[GRPC] or install the grpcio package manually.
To disable uninstall the grpcio package.
This will speed up certain GraphQL queries: Get with NearObject or NearVector if only non-reference queries are retrieved and no other options are set.
Removal of python 3.7 support. Minimum supported version is python 3.8
Removal of the WCS module. Note that the module was used to administrate old WCS instances and does not work anymore.
Nothing published for this version
Fix multi line queries for hybrid and BM25 by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/290
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.15.5...v3.15.6
This patch version includes:
Fix multi-line queries for BM25 and hybrid search.
Remove cluster hostname from weaviate embedded and set deterministic default by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/27
1.18.2) which downloads that weaviate version for your platformclient = weaviate.Client(embedded_options=EmbeddedOptions(version="latest"))
client = weaviate.Client(embedded_options=EmbeddedOptions(version="1.18.2"))
by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/281
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.15.4...v3.15.5
This patch version includes:
EmbeddedDB now supports latest and versions (eg 1.18.3) as version argument.
Removed cluster_hostname from EmbeddedOptions. It can still be set by using additional_env_vars.
Fix multi-line queries for generative search.
Fix imports for embeddedDB by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/273
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.15.3...v3.15.4
This patch version includes:
Fix imports of EmbeddedDB on Mac. It now properly raises an exception that MacOS is currently unsupported.
Allow authentification via 'additional_headers' by @dennis-ge in https://github.com/weaviate/weaviate-python-client/pull/267
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.15.2...v3.15.3
This patch version includes:
Improve embedded weaviate: Better folder structures, add support for env variables and support multiple versions.
Fix edge case for timeout retries: When all objects have been added, no empty batch will be send.
Fix authentication via additional_headers
Fix simple API with weaviate without OIDC by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/259
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.15.1...v3.15.2
This patch version includes:
Fixes API keys with Weaviate setups that do not have OIDC enabled.
Add handling for failed requests in token refresh by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/233
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.14.0...v3.15.1
This patch version includes:
Fixes refreshing of OIDC tokens on unstable connections
Add support for API keys by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/250
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.13.0...v3.14.0
This minor version includes:
Support for API-Keys:
client = weaviate.Client(url, auth_client_secret=AuthApiKey(api_key="my-secret-key"))
Extend CRUD operations for single data objects and reference with consistency level by @redouan-rhazouani in https://github.com/weaviate/weaviate-pyth
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.12.0...v3.13.0
This minor version includes:
Extend CRUD operations for single data objects and reference with consistency level.
Extend batch operations with consistency level.
Add Cursor api.
Add support for azure backup module.
Extend CRUD operations for single data objects and reference with consistency level by @redouan-rhazouani in https://github.com/weaviate/weaviate-pyth
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.12.0...v3.12.1b
OIDC default scopes by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/218
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.11.0...v3.12.0
This minor version includes:
Adds ~weaviate.gql.get.GetBuilder.with_generate in ~weaviate.gql.get.GetBuilder which allows to use the generative openai module. Needs Weaviate with version >=v1.17.3.
Fix for empty OIDC scopes
New startup_period parameter in ~weaviate.client.Client. The client will wait for the given timeout for Weaviate to start. By default 5 seconds.
Improved error messages for where filters and authentication.
Add status code member to UnexpectedStatusCode exception by @dirkkul in https://github.com/weaviate/weaviate-python-client/pull/197
Full Changelog: https://github.com/weaviate/weaviate-python-client/compare/v3.9.0...v3.11.0
This minor version includes:
New status code attribute for ~weaviate.exceptions.UnexpectedStatusCodeException that can be accessed like this:
try: # your code except weaviate.UnexpectedStatusCodeException as err: print(err.status_code)
Fix for ~weaviate.client.Client.get_meta.
Caches server version at ~weaviate.client.Client initialization. This improves batch reference creation performance.
Changes accepted data types for arguments from_object_uuid and to_object_uuid of the method ~weaviate.batch.Batch.add_reference to str and uuid.UUID.
All errors:
from weaviate import WeaviateErrorRetryConf with client.batch( weaviate_error_retries=WeaviateErrorRetryConf(number_retries=3), ) as batch: # Your codeExclude errors, all the other errors will be retried:
from weaviate import WeaviateErrorRetryConf with client.batch( weaviate_error_retries=WeaviateErrorRetryConf(number_retries=3, errors_to_exclude=["Ignore me", "other error to ignore"]), ) as batch: # Your codeInclude errors, all the other errors will be ignored:
from weaviate import WeaviateErrorRetryConf with client.batch( weaviate_error_retries=WeaviateErrorRetryConf(number_retries=3, errors_to_include=["error to retry", "other error to test again"]), ) as batch: # Your code
Adds new arguments sort and offset for ~weaviate.data.DataObject.get.
Improve error message for error "413: Payload Too Large" by @dirkkul in https://github.com/semi-technologies/weaviate-python-client/pull/159
client_credentials_config = weaviate.AuthClientCredentials(
client_secret = "client_secret",
scope = "scope1 scope2" # optional, depends on the configuration of your identity provider
)
client = weaviate.Client("https://localhost:8080", auth_client_secret=client_credentials_config)
Full Changelog: https://github.com/semi-technologies/weaviate-python-client/compare/v3.9.0...v3.10.0
This minor version includes:
Improves error message for error "413: Payload Too Large"
client_credentials_config = weaviate.AuthClientCredentials( client_secret = "client_secret", scope = "scope1 scope2" # optional, depends on the configuration of your identity provider ) client = weaviate.Client("https://localhost:8080", auth_client_secret=client_credentials_config)
Improves size of batches on dynamic batching.
New limit argument to ~weaviate.data.DataObject.get method of the ~weaviate.data.DataObject client attribute.
Bump minimum version of request to 2.28.0
my_class = { "class": "MyClass", ..., "replicationConfig": { "factor": 1 } }
Adds support for Bm25 for Get queries, ~weaviate.gql.get.GetBuilder.with_bm25. This can be used ONLY with Weaviate Server v1.17.0 or later.
Adds support for with_hybrid for Get queries, ~weaviate.gql.get.GetBuilder.with_hybrid. This can be used ONLY with Weaviate Server v1.17.0 or later.
Improve error message for error "413: Payload Too Large" by @dirkkul in https://github.com/semi-technologies/weaviate-python-client/pull/159
client_credentials_config = weaviate.AuthClientCredentials(
client_secret = "client_secret",
scope = "scope1 scope2" # optional, depends on the configuration of your identity provider
)
client = weaviate.Client("https://localhost:8080", auth_client_secret=client_credentials_config)
Full Changelog: https://github.com/semi-technologies/weaviate-python-client/compare/v3.9.0...v3.10.0b0
Authentication using Bearer token, by adding additional_headers to the class Client initialization: `python client = weaviate.Client( url='http://loca
This minor version includes:
Authentication using Bearer token, by adding additional_headers to the class Client initialization:
client = weaviate.Client(
url='http://localhost:8080',
additional_headers={
{"authorization": "Bearer <MY_TOKEN>"}
}
)
Multi-threading class Batch import:
num_workers in method Batch.configure and method Batch.__call__, defaults to 1 ( Use with care to not overload your weaviate instance.).connection_error_retries to retry on ConnectionError that can be set in method Batch.configure and method Batch.__call__ or using the property getter/setter: client.batch.connection_error_retries to get the value and client.batch.connection_error_retries = 5 to set the value.Batch.start to create a BatchExecutor (ThreadExecutor). This method does NOT need to be called if using the class Batch in a context manager (with). Also it is idempotent.Batch.shutdown to shutdown the existing BatchExecutor (ThreadExecutor) to release any resources that it is holding once the batch import is done. This method does NOT need to be called if using the class Batch in a context manager (with). Also it is idempotent.New class Client attribute cluster (class Cluster) to check the status of the cluster nodes.
Cluster.get_nodes_status returns the status of each node as a list of dictionaries. client.cluster.get_nodes_status()
Fix for method DataObject.replace and method DataObject.update when using with Weaviate server >=v1.14.0.
New default timeout_config: (10, 60).
Full Changelog: https://github.com/semi-technologies/weaviate-python-client/compare/v3.8.0...v3.9.0
This minor version includes:
client = weaviate.Client(
url='http://localhost:8080',
additional_headers={
{"authorization": "Bearer <MY_TOKEN>"}
}
)client.cluster.get_nodes_status()Fix for ~weaviate.data.DataObject.replace and ~weaviate.data.DataObject.update when using with Weaviate server >=v1.14.0.
New default timeout_config: (10, 60).
Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
Backup functionalities (Backup class):
This minor version includes:
Backup functionalities (Backup class):
Backup.create method to create backups (all/subset of classes).Backup.get_create_status method to get the status of the created backup.Backup.restore method to restore Weaviate from a backup (all/subset of classes).Backup.get_restore_status method to get the status of the restored backup.New Client attribute: backup to create, restore and get status of the backups. All backup operations MUST be done through Client.backup.
Added return value for Batch.add_data_object, it now returns the UUID of the added object, if one was not set then an UUIDv4 will be generated.
This minor version includes:
~weaviate.backup.Backup.create method to create backups (all/subset of classes).
~weaviate.backup.Backup.get_create_status method to get the status of the created backup.
~weaviate.backup.Backup.restore method to restore Weaviate from a backup (all/subset of classes).
~weaviate.backup.Backup.get_restore_status method to get the status of the restored backup.
New ~weaviate.Client attribute: backup to create, restore and get status of the backups. All backup operations MUST be done through Client.backup.
Added return value for ~weaviate.batch.Batch.add_data_object, it now returns the UUID of the added object, if one was not set then an UUIDv4 will be generated.
Adds rolling average (last 5 batches) for batch creation time used by Dynamic Batching method.
This minor version includes:
client.query.get() without specifying any properties IF Additional Properties (client.query.get(...).with_additional()) are set before executing the query.WeaviateBaseError.Client initialization by using the new proxies or trust_env arguments.Batch creates UUIDs (UUIDv4) for all added objects that do not have one at client side (fixes data duplication on Batch retries).WCS for instances that have authentication enabled:
get_users_of_cluster() to get users (emails) for all the users that have access to the created Weaviate instance.add_user_to_cluster() to add users (email) to the created Weaviate instance.remove_user_from_cluster() to remove user (email) from the created Weaviate instance.This minor version includes:
Adds rolling average (last 5 batches) for batch creation time used by Dynamic Batching method.
Adds ability to use ~weaviate.gql.Query.get without specifying any properties IF Additional Properties (~weaviate.gql.get.GetBuilder.with_additional) are set before executing the query.
Adds base Weaviate Exception ~weaviate.exceptions.WeaviateBaseError.
Adds ability to set proxies. Can be set at ~weaviate.client.Client initialization by using the new proxies or trust_env arguments.
~weaviate.batch.crud_batch.Batch creates UUIDs (UUIDv4) for all added objects that do not have one at client side (fixes data duplication on Batch retries).
~weaviate.wcs.WCS.get_users_of_cluster to get users (emails) for all the users that have access to the created Weaviate instance.
~weaviate.wcs.WCS.add_user_to_cluster to add users (email) to the created Weaviate instance.
~weaviate.wcs.WCS.remove_user_from_cluster to remove user (email) from the created Weaviate instance.
Deprecation Warning if Weaviate Server version >= 1.14.0 and class_name is None OR if Weaviate Server version < 1.14.0 and class_name is NOT None.
This minor version includes:
New function weaviate.util.check_batch_result used to print errors from batch creation.
New function argument class_name for function weaviate.util.generate_local_beacon, used ONLY with Weaviate Server version >= 1.14.0 (defaults to None for backwards compatibility).
Function weaviate.util.check_batch_result is the default callback function for class weaviate.batch.Batch
(methods weaviate.batch.Batch.configure and weaviate.batch.Batch.__call__) (instead of None).
New method argument to_object_class_name for method weaviate.batch.Batch.add_reference, used ONLY with Weaviate Server version >= 1.14.0
(defaults to None for backwards compatibility).
Support for distance in GraphQL filters (only with Weaviate server >= 1.14.0).
For class weaviate.data.DataObject:
class_name for method weaviate.data.DataObject.get_by_id, method weaviate.data.DataObject.get, method weaviate.data.DataObject.delete
method weaviate.data.DataObject.exists, used ONLY with Weaviate Server version >= 1.14.0 (defaults to None for backwards compatibility).class_name is None OR if Weaviate Server version < 1.14.0 and class_name is NOT None.For class weaviate.data.references.Reference:
from_class_name and to_class_name (to_class_names for method weaviate.data.references.Reference.update) for
method weaviate.data.references.Reference.add, method weaviate.data.references.Reference.delete,
method weaviate.data.references.Reference.update, used ONLY with Weaviate Server version >= 1.14.0 (defaults to None for backwards compatibility).class_name is None OR if Weaviate Server version < 1.14.0 and class_name is NOT None.This minor version includes:
New function in ~weaviate.util.check_batch_result used to print errors from batch creation.
(defaults to None for backwards compatibility).
Support for distance in GraphQL filters (only with Weaviate server >= 1.14.0).
Deprecation Warning if Weaviate Server version >= 1.14.0 and class_name is None OR if Weaviate Server version < 1.14.0 and class_name is NOT None.
Deprecation Warning if Weaviate Server version >= 1.14.0 and class_name is None OR if Weaviate Server version < 1.14.0 and class_name is NOT None.
the rerank not being set bug in client.query.get().with_ask().
This patch version fixes:
rerank not being set bug in client.query.get().with_ask().") in question field in client.query.get().with_ask().nearText filter checks for objects in moveXXX clause but never sets it.This patch version fixes:
This minor version contains functionality for the new features introduced in Weaviate v1.13.0.
This minor version contains functionality for the new features introduced in Weaviate v1.13.0.
New Batch method .delete_objects(...) to delete all objects that match a particular expression (where filter).
New GetBuilder method .with_sort(...) that allows sorting data on a particular field/s.
New AggregateBuilder method .with_near_text(...) that allows to aggregate data that is matching nearText filter.
New AggregateBuilder method .with_near_object(...) that allows to aggregate data that is matching nearObject filter.
New AggregateBuilder method .with_near_vector(...) that allows to aggregate data that is matching nearVector filter.
This minor version contains functionality for the new features introduced in Weaviate v1.13.0.
Another bug fix in DataObject.exists.
Another bug fix in DataObject.exists.
bug fix in DataObject.exists.
bug fix in DataObject.exists.
This minor version fixes the bug in setting the Schema's invertedIndexConfig field.
invertedIndexConfig field.client.chema.get_class_shards() to get all shards configuration of a particular class.client.schema.update_class_shard() to update one/all shard/s configuration of a particular class.tokenization.| This patch version fixes the nearImage filter requests.
| This patch version allows using UUIDs in hex format for ~weaviate.data.DataObject too i.e. UUIDs without hyphens.
| This patch version allows using UUIDs in hex format too i.e. UUIDs without hyphens.
| This minor version adds a new ~weaviate.gql.get.GetBuilder.with_offset for the Get queries. This method should be used with the ~weaviate.gql.get.Ge
This patch fixes the 'Batch' object is not callable error.
This patch fixes the 'Batch' object is not callable error.
All class_name and cross-refs dataType are implicitly capitalized. (This functionality is added because if class_name is not capitalized then Weaviate
All class_name and cross-refs dataType are implicitly capitalized. (This functionality is added because if class_name is not capitalized then Weaviate server does it for you, and this was leading to errors where the client and server have different configurations.)
contains() to accept separate class schemas as argument i.e. it does not expect to have only this format: {"classes": [CLASS_1, CLASS_2, ...]}; now it is possible to pass just CLASS_X as well.This patch fixes the with_near_object() method. It uses now explicit string literals for id/beacon in _nearoOject_ clauses.
This patch fixes the with_near_object() method. It uses now explicit string literals for id/beacon in nearoOject clauses.
This patch fixes the ~weaviate.gql.get.GetBuilder.with_near_object. It uses now explicit string literals for id/beacon in nearoOject clauses.
This patch adds support for array data types: boolean[] and date[].
This patch adds support for array data types: boolean[] and date[].
This patch adds support for array data types: boolean[], date[].
This patch adds support for `array data types: int[], number[], text[], string[]`.
This patch adds support for array data types: int[], number[], text[], string[].
This patch adds support for array data types: int[], number[], text[], string[].
Fixes/updates in weaviate.wcs.WCS class:
Fixes/updates in weaviate.wcs.WCS class:
weaviate.wcs.WCS.create, it is being updated in Notebooks too, instead of printing each iteration on new line.weaviate.wcs.WCS.create now prints the creation status above the bar.Updates in weaviate.gql sub-package:
autocorrect: <bool> introduced for the weaviate.gql.filter.NearText and weaviate.gql.filter.Ask filters.
The autocorrect is enabled only if Weaviate server has the text-spellcheck module enabled. If autocorrect is True the query is corrected before the query is made. Usage example:# with 'nearText' filter
client.query\
.get('Article', ['title', 'author'])\
.near_text(
{
'concepts': ['Ecconomy'],
'autocorrect': True
}
)
# the concept should be corrected to 'Economy'
# with 'ask' filter
client.query\
.get('Article', ['title', 'author'])\
.with_ask(
{
'question': 'When was the last financial crysis?',
'autocorrect': True
}
)
# the question should be corrected to 'When was the last financial crisis?'
weaviate.gql.get.GetBuilder.with_additional is added to GET the _additional properties. Usage example:# single additional property with this GraphQL query
'''
{
Get {
Article {
title
author
_additional {
id
}
}
}
}
'''
client.query\
.get('Article', ['title', 'author'])\
.with_additional('id']) # argument as `str`
# multiple additional property with this GraphQL query
'''
{
Get {
Article {
title
author
_additional {
id
certainty
}
}
}
}
'''
client.query\
.get('Article', ['title', 'author'])\
.with_additional(['id', 'certainty']) # argument as `List[str]`
# additional properties as clause with this GraphQL query
'''
{
Get {
Article {
title
author
_additional {
classification {
basedOn
classifiedFields
completed
id
scope
}
}
}
}
}
'''
client.query\
.get('Article', ['title', 'author'])\
.with_additional(
{
'classification' : ['basedOn', 'classifiedFields', 'completed', 'id']
}
) # argument as `dict[str, List[str]]`
# or with this GraphQL query
'''
{
Get {
Article {
title
author
_additional {
classification {
completed
}
}
}
}
}
'''
client.query\
.get('Article', ['title', 'author'])\
.with_additional(
{
'classification' : 'completed'
}
) # argument as `Dict[str, str]`
Consider the following GraphQL clause:
'''
{
Get {
Article {
title
author
_additional {
token (
properties: ["content"]
limit: 10
certainty: 0.8
) {
certainty
endPosition
entity
property
startPosition
word
}
}
}
}
}
'''
# Then the python translation of this is the following:
clause = {
'token': [ # if only one, can be passes as `str`
'certainty',
'endPosition',
'entity',
'property',
'startPosition',
'word',
]
}
settings = {
'properties': ["content"], # is required
'limit': 10, # optional, int
'certainty': 0.8 # optional, float
}
client.query\
.get('Article', ['title', 'author'])\
.with_additional(
(clause, settings)
) # argument as `Tuple[Dict[str, List[str]], Dict[str, Any]]`
If the desired clause does not match any example above, then the clause can always be
converted to string before passing it to the .with_additional() method.
Make WCS’s methods’ argument cluster_name case insensitive (lowercased inside the method) to match Weaviate Cloud Service’ naming convention, this fix
Fixes in WCS class:
WCS’s methods’ argument cluster_name case insensitive (lowercased inside the method) to match Weaviate Cloud Service’ naming convention, this fixes the error when Weaviate Cloud Service lowercases the cluster_name but the users are not aware of this and get the exception KeyError.New weaviate.batch.Batch methods:
New weaviate.batch.Batch methods:
weaviate.batch.Batch.pop_object / weaviate.batch.Batch.pop_reference to remove and return an added object/reference from theweaviate.batch.Batch at position index (by default -1).weaviate.batch.Batch.empty_objects / weaviate.batch.Batch.empty_references to remove all the existing objects/references from the weaviate.batch.Batch instance.weaviate.batch.Batch.is_empty_objects /weaviate.batch.Batch.is_empty_references to check there are any objects/reference in the weaviate.batch.Batch instance.Fixes in weaviate.wcs.WCS class:
weaviate.auth.AuthClientPassword.weaviate.wcs.WCS.create argument module is renamed to modules and can also be a list of modules to enable for the WCS cluster. The argument can be used on the PROD WCS too.weaviate.wcs.WCS.get_cluster_config does not raise an exception if the cluster does not exist but returns a empty configuration.weaviate.wcs.WCS.delete_cluster does not raise an exception if the cluster does not exist.Add phoneNumber to the Weaviate's primitive types. Thanks to GitHub user @cdpierse.
Bug fix in weaviate.connect.Connection.
Fix ConnectionError handling.
Optimization in weaviate.batch.requests and weaviate.connect.connection.
weaviate.tools module is REMOVED.
weaviate.tools module is REMOVED.
Batcher class is REMOVED.WCS class is moved from the weaviate.tools to the new module weaviate.wcsweaviate.tools.generate_uuid is REMOVED.weaviate.util.generate_uuid5 is ADDED.weaviate.batch.Batch class implementation to replace the old one. This implementation uses the BatchRequest
objects under the hood, which means that there is no need to create BatchRequest's anymore. This new class implementation
allows 3 different batch creations methods: manual, auto-create and auto-create with dynamic batching.
See the weaviate.batch.Batch documentation for more information.BatchRequest classes (ObjectsBatchRequest and ReferenceBatchRequest) are hidden from the user and should not be
used anymore. This is due to the new weaviate.batch.Batch class implementation.weaviate.schema.Schema field is ADDED, "shardingConfig". It can bu used with Weaviate version >= 1.6.0.weaviate.schema.Schema.update_config used to update mutable schema configuration (like efConstruction, ...).Nothing published for this version
Nothing published for this version
Nothing published for this version
Nothing published for this version
The new version is compatible with Weaviate v1.4.0.
The new version is compatible with Weaviate v1.4.0.
with_near_image(content: dict, encode: bool = True) is added for the GET query. E.g.:<br>content = {
"image": "IMAGE_PATH/image.png",
"certainty": 0.7,
}
client.query.get("Article", "coverImage").with_near_image(content=content, encode=True).do()
image_encoder_b64 to encode a image to base64, the argument is the image path OR the file object in "br" mode.<br>weaviate.util.image_encoder_b64(
image_or_image_path: Union[str, BufferedReader]
) -> str
image_decoder_b64 to decode a image from base64 to bytes stream, the argument is the base64 encoded image string.<br>weaviate.util.image_decoder_b64(
encoded_image: str
) -> bytes
The new version is compatible with Weaviate v1.3.0.
The new version is compatible with Weaviate v1.3.0.
with_ask is added for the GET query. E.g.:<br>ask = {
"question": "Who is the king of the Netherlands?",
"certainty": 0.7,
"properties": ["summary"]
}
client.query.get("Article", ["title", "_additional {hasAnswer certainty property result startPosition endPosition}"]).with_ask(ask).do()
with_auth argument for WCS.create that enables/disables the authentication of the to be created Weaviate instance.<br>WCS.create(self,
cluster_name: str=None,
cluster_type: str='sandbox',
with_auth: bool=False, # <- NEW
module: Optional[Union[str, dict]]=None,
config: dict=None,
wait_for_completion: bool=True
) -> str
Nothing published for this version
Nothing published for this version
Your coding agent can read these notes before it upgrades. Set up the MCP server →