?h2%dZddlmZmZmZddlmZddlmZddl m Z m Z m Z m Z mZmZmZmZddlmZddlmZddlmZdd lmZdd lmZmZmZmZmZm Z m!Z!m"Z"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z(m)Z)dd l*m+Z+dd l,m-Z-m.Z.m/Z/m0Z0m1Z1dd l2m3Z3 ddl4m5Z5ddl6Z6eGddZ8Gdde9e1Z:eGddZ;eGddZeGddZ?GddeZ@y#e7$rYywxYw)z GraphQL `Get` command. ) dataclassFieldfields)Enum)dumps)AnyDictListLiteralOptionalSequenceTupleUnion)util) Connection)ConsistencyLevel)AdditionalPropertiesException)WhereNearText NearVectorGraphQL NearObjectFilterAsk NearImage NearVideo NearAudio NearThermal NearDepthNearIMU MediaTypeSort)UUID)image_encoder_b64_capitalize_first_letterget_valid_uuidfile_encoder_b64BaseEnum) _Warnings)search_get_pb2Nc:eZdZUeed<eeeed<defdZy)BM25query propertiesreturncdtj|j}|jr?r=r,r,/s" Jc##$$r?r,ceZdZdZdZy) HybridFusion rankedFusionrelativeScoreFusionN)r@rArBRANKEDRELATIVE_SCORErEr?r=rGrG<s F*Nr?rGcpeZdZUeed<eeed<eeeed<eeeed<eeed<defdZ y) Hybridr-alphavectorr. fusion_typer/cdtj|j}|j|d|jz }|j|d|jz }|j zHybrid.__str__Is**4::678 ;; " Z }- -C :: ! Ytzzl+ +C ?? &3t+?!+CJJt/E %eWB/ /C    '$**D1(8(8(>(>'?@@(8(8'9::C#%%r?N) r@rArBrCrDr floatr rGr>rEr?r=rMrMAsF J E? T%[ !!c##,''&&r?rMc>eZdZUeeed<eed<eed<defdZy)GroupBypathgroupsobjects_per_groupr/cxdj|j}d|d|jd|jdS)Nr2zgroupBy:{path:["z "], groups:z, objectsPerGroup:r5)r8rWrXrYr:r<s r=r>zGroupBy.__str__as= 499%"5'T[[MASTXTjTjSkkmnnr?N)r@rArBr rCrDintr>rEr?r=rVrV[s$ s)O Koor?rVcHeZdZUeed<eed<eeedfed<defdZy)LinkTolink_on linked_classr.r/cdjd|jD}|jdz|jzdz|zdzS)N c32K|]}t|ywNrC.0xs r= z!LinkTo.__str__..ms9AQ9z{... on {}})r8r.r_r`r[s r=r>zLinkTo.__str__lsC999||j(4+<+<rEr?r=r^r^fs/ LsH}-..RRr?r^ceZdZUdZeed<dZeed<dZeed<dZeed<dZ eed<dZ eed<dZ eed<dZ eed <d e fd Zy ) AdditionalPropertiesFuuidrOcreationTimeUnixlastUpdateTimeUnixdistance certaintyscore explainScorer/cNg}t|j}|D]d}t|jtst ||j }|s7|j }|j dk(rd}|j|ft|dkDrddj|zdzSy)Nroidrz _additional{rb} ) r __class__ issubclasstypeboolgetattrnameappendr7r8)r:additional_props cls_fieldsfieldenabledrs r=r>zAdditionalProperties.__str__s&((.t~~(>  2E%**d+ 'ejj 9 ::DzzV+#$++D1 2  1 $"SXX.>%??$F Fr?N)r@rArBror}rDrOrprqrrrsrtrurCr>rEr?r=rnrnts`D$FD"d"$$HdItE4L$r?rnc <eZdZdZdedeedeffd Zde ddfdZ d eddfd Z d e ddfd Z d eddfdZedefdZd eddfdZd eddfdZd eddfdZd@d ededdfdZd@d ededdfdZd@d ededdfdZd@d ededdfdZd@d ededdfdZd@d ededdfdZde ddfdZde ddfdZd eddfdZdee ee!eee eeffe"eefe#fddfdZ$d ee%efddfd Z&dAd"edee eddfd#Z' dBd"ed$ee(d%ee e(dee ed&ee)ddf d'Z*de ed(e d)e ddfd*Z+ dCd+eed,eed-ee eddfd.Z,d/eddfd0Z-d1e.ddfd2Z/d@d3edefd4Z0deffd5 Z1d6d7de!eeffd8Z2dd9de!fd:Z3de4ee5efdd;fd<Z6defd=Z7d>e8dd!fd?Z9xZ:S)D GetBuilderz: GetBuilder class used to create GraphQL queries. class_namer. connectionct||t|tst dt ||g}t|tr|g}t|t st dt |g|_|D]H}t|tst|ts t d|jj|Jt||_ dti|_ d|_d|_d|_d|_d|_d|_d|_d|_d|_d|_d|_d|_d|_d|_d|_y)a Initialize a GetBuilder class instance. Parameters ---------- class_name : str Class name of the objects to interact with. properties : str or list of str Properties of the objects to interact with. connection : weaviate.connect.Connection Connection object to an active and running Weaviate instance. Raises ------ TypeError If argument/s is/are of wrong type. z'class name must be of type str but was Nz $ r?contentc4t||_d|_|S)a Set `where` filter. Parameters ---------- content : dict The content of the `where` filter to set. See examples below. Examples -------- The `content` prototype is like this: >>> content = { ... 'operator': '', ... 'operands': [ ... { ... 'path': [path], ... 'operator': '' ... '': ... }, ... { ... 'path': [], ... 'operator': '', ... '': ... } ... ] ... } This is a complete `where` filter but it does not have to be like this all the time. Single operand: >>> content = { ... 'path': ["wordCount"], # Path to the property that should be used ... 'operator': 'GreaterThan', # operator ... 'valueInt': 1000 # value (which is always = to the type of the path property) ... } Or >>> content = { ... 'path': ["id"], ... 'operator': 'Equal', ... 'valueString': "e5dc4a4c-ef0f-3aed-89a3-a73435c6bbcf" ... } Multiple operands: >>> content = { ... 'operator': 'And', ... 'operands': [ ... { ... 'path': ["wordCount"], ... 'operator': 'GreaterThan', ... 'valueInt': 1000 ... }, ... { ... 'path': ["wordCount"], ... 'operator': 'LessThan', ... 'valueInt': 1500 ... } ... ] ... } Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. T)rrrr:rs r= with_wherezGetBuilder.with_wheresNGn $ r?cJ|jr |jS|jSrd)rr)r:s r=rzGetBuilder.name:s"kkt{{?t/?/??r?cb|j tdt||_d|_|S)a Set `nearText` filter. This filter can be used with text modules (text2vec). E.g.: text2vec-contextionary, text2vec-transformers. NOTE: The 'autocorrect' field is enabled only with the `text-spellcheck` Weaviate module. Parameters ---------- content : dict The content of the `nearText` filter to set. See examples below. Examples -------- Content full prototype: >>> content = { ... 'concepts': , ... # certainty ONLY with `cosine` distance specified in the schema ... 'certainty': , # Optional, either 'certainty' OR 'distance' ... 'distance': , # Optional, either 'certainty' OR 'distance' ... 'moveAwayFrom': { # Optional ... 'concepts': , ... 'force': ... }, ... 'moveTo': { # Optional ... 'concepts': , ... 'force': ... }, ... 'autocorrect': , # Optional ... } Full content: >>> content = { ... 'concepts': ["fashion"], ... 'certainty': 0.7, # or 'distance' ... 'moveAwayFrom': { ... 'concepts': ["finance"], ... 'force': 0.45 ... }, ... 'moveTo': { ... 'concepts': ["haute couture"], ... 'force': 0.85 ... }, ... 'autocorrect': True ... } Partial content: >>> content = { ... 'concepts': ["fashion"], ... 'certainty': 0.7, # or 'distance' ... 'moveTo': { ... 'concepts': ["haute couture"], ... 'force': 0.85 ... } ... } Minimal content: >>> content = { ... 'concepts': "fashion" ... } Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. Raises ------ AttributeError If another 'near' filter was already set. QCannot use multiple 'near' filters, or a 'near' filter along with a 'ask' filter!T)rAttributeErrorrrrs r=with_near_textzGetBuilder.with_near_text>s?V    ( ( %W- $ r?cb|j tdt||_d|_|S)a Set `nearVector` filter. Parameters ---------- content : dict The content of the `nearVector` filter to set. See examples below. Examples -------- Content full prototype: >>> content = { ... 'vector' : , ... # certainty ONLY with `cosine` distance specified in the schema ... 'certainty': , # Optional, either 'certainty' OR 'distance' ... 'distance': , # Optional, either 'certainty' OR 'distance' ... } NOTE: Supported types for 'vector' are `list`, 'numpy.ndarray`, `torch.Tensor` and `tf.Tensor`. Full content: >>> content = { ... 'vector' : [.1, .2, .3, .5], ... 'certainty': 0.75, # or 'distance' ... } Minimal content: >>> content = { ... 'vector' : [.1, .2, .3, .5] ... } Or >>> content = { ... 'vector' : torch.tensor([.1, .2, .3, .5]) ... } Or >>> content = { ... 'vector' : torch.tensor([[.1, .2, .3, .5]]) # it is going to be squeezed. ... } Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. Raises ------ AttributeError If another 'near' filter was already set. rT)rrrrrs r=with_near_vectorzGetBuilder.with_near_vectors?v    ( ( 'w/ $ r?c|jjdk\}|j tdt |||_d|_|S)a Set `nearObject` filter. Parameters ---------- content : dict The content of the `nearObject` filter to set. See examples below. Examples -------- Content prototype: >>> { ... 'id': "e5dc4a4c-ef0f-3aed-89a3-a73435c6bbcf", ... # certainty ONLY with `cosine` distance specified in the schema ... 'certainty': , # Optional, either 'certainty' OR 'distance' ... 'distance': , # Optional, either 'certainty' OR 'distance' ... } >>> # alternatively >>> { ... 'beacon': "weaviate://localhost/ClassName/e5dc4a4c-ef0f-3aed-89a3-a73435c6bbcf" ... # certainty ONLY with `cosine` distance specified in the schema ... 'certainty': , # Optional, either 'certainty' OR 'distance' ... 'distance': , # Optional, either 'certainty' OR 'distance' ... } Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. Raises ------ AttributeError If another 'near' filter was already set. z1.14rT) _connectionserver_versionrrrr)r:ris_server_version_14s r=with_near_objectzGetBuilder.with_near_objectsYL $//>>&H    ( ( 'w0DE $ r?encodec|j td|rt|d|d<t||_d|_|S)a Set `nearImage` filter. Parameters ---------- content : dict The content of the `nearImage` filter to set. See examples below. encode : bool, optional Whether to encode the `content["image"]` to base64 and convert to string. If True, the `content["image"]` can be an image path or a file opened in binary read mode. If False, the `content["image"]` MUST be a base64 encoded string (NOT bytes, i.e. NOT binary string that looks like this: b'BASE64ENCODED' but simple 'BASE64ENCODED'). By default True. Examples -------- Content prototype: >>> content = { ... 'image': , ... # certainty ONLY with `cosine` distance specified in the schema ... 'certainty': , # Optional, either 'certainty' OR 'distance' ... 'distance': , # Optional, either 'certainty' OR 'distance' ... } >>> { ... 'image': "e5dc4a4c-ef0f-3aed-89a3-a73435c6bbcf", ... 'certainty': 0.7 # or 'distance' ... } With `encoded` True: >>> content = { ... 'image': "my_image_path.png", ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Image', 'description')\ ... .with_near_image(content, encode=True) # <- encode MUST be set to True OR >>> my_image_file = open("my_image_path.png", "br") >>> content = { ... 'image': my_image_file, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Image', 'description')\ ... .with_near_image(content, encode=True) # <- encode MUST be set to True >>> my_image_file.close() With `encoded` False: >>> from weaviate.util import image_encoder_b64, image_decoder_b64 >>> encoded_image = image_encoder_b64("my_image_path.png") >>> content = { ... 'image': encoded_image, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Image', 'description')\ ... .with_near_image(content, encode=False) # <- encode MUST be set to False OR >>> from weaviate.util import image_encoder_b64, image_decoder_b64 >>> with open("my_image_path.png", "br") as my_image_file: ... encoded_image = image_encoder_b64(my_image_file) >>> content = { ... 'image': encoded_image, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Image', 'description')\ ... .with_near_image(content, encode=False) # <- encode MUST be set to False Encode Image yourself: >>> import base64 >>> with open("my_image_path.png", "br") as my_image_file: ... encoded_image = base64.b64encode(my_image_file.read()).decode("utf-8") >>> content = { ... 'image': encoded_image, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Image', 'description')\ ... .with_near_image(content, encode=False) # <- encode MUST be set to False Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. Raises ------ AttributeError If another 'near' filter was already set. rimageT)rrr$rrr:rrs r=with_near_imagezGetBuilder.with_near_imagesVB    ( (  01ABGG %g. $ r?ctj|_|j t d|r9t ||jj ||jj <t||_d|_|S)a Set `nearAudio` filter. Parameters ---------- content : dict The content of the `nearAudio` filter to set. See examples below. encode : bool, optional Whether to encode the `content["audio"]` to base64 and convert to string. If True, the `content["audio"]` can be an audio path or a file opened in binary read mode. If False, the `content["audio"]` MUST be a base64 encoded string (NOT bytes, i.e. NOT binary string that looks like this: b'BASE64ENCODED' but simple 'BASE64ENCODED'). By default True. Examples -------- Content prototype: >>> content = { ... 'audio': , ... # certainty ONLY with `cosine` distance specified in the schema ... 'certainty': , # Optional, either 'certainty' OR 'distance' ... 'distance': , # Optional, either 'certainty' OR 'distance' ... } >>> { ... 'audio': "e5dc4a4c-ef0f-3aed-89a3-a73435c6bbcf", ... 'certainty': 0.7 # or 'distance' ... } With `encoded` True: >>> content = { ... 'audio': "my_audio_path.wav", ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Audio', 'description')\ ... .with_near_audio(content, encode=True) # <- encode MUST be set to True OR >>> my_audio_file = open("my_audio_path.wav", "br") >>> content = { ... 'audio': my_audio_file, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Audio', 'description')\ ... .with_near_audio(content, encode=True) # <- encode MUST be set to True >>> my_audio_file.close() With `encoded` False: >>> from weaviate.util import file_encoder_b64 >>> encoded_audio = file_encoder_b64("my_audio_path.wav") >>> content = { ... 'audio': encoded_audio, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Audio', 'description')\ ... .with_near_audio(content, encode=False) # <- encode MUST be set to False OR >>> from weaviate.util import file_encoder_b64 >>> with open("my_audio_path.wav", "br") as my_audio_file: ... encoded_audio = file_encoder_b64(my_audio_file) >>> content = { ... 'audio': encoded_audio, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Audio', 'description')\ ... .with_near_audio(content, encode=False) # <- encode MUST be set to False Encode Audio yourself: >>> import base64 >>> with open("my_audio_path.wav", "br") as my_audio_file: ... encoded_audio = base64.b64encode(my_audio_file.read()).decode("utf-8") >>> content = { ... 'audio': encoded_audio, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Audio', 'description')\ ... .with_near_audio(content, encode=False) # <- encode MUST be set to False Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. Raises ------ AttributeError If another 'near' filter was already set. rT) r!AUDIO _media_typerrr'rSrrrs r=with_near_audiozGetBuilder.with_near_audioszB%??    ( (  .>wtGWGWG]G]?^._GD$$** +%g. $ r?ctj|_|j t d|r9t ||jj ||jj <t||_d|_|S)a Set `nearVideo` filter. Parameters ---------- content : dict The content of the `nearVideo` filter to set. See examples below. encode : bool, optional Whether to encode the `content["video"]` to base64 and convert to string. If True, the `content["video"]` can be an video path or a file opened in binary read mode. If False, the `content["video"]` MUST be a base64 encoded string (NOT bytes, i.e. NOT binary string that looks like this: b'BASE64ENCODED' but simple 'BASE64ENCODED'). By default True. Examples -------- Content prototype: >>> content = { ... 'video': , ... # certainty ONLY with `cosine` distance specified in the schema ... 'certainty': , # Optional, either 'certainty' OR 'distance' ... 'distance': , # Optional, either 'certainty' OR 'distance' ... } >>> { ... 'video': "e5dc4a4c-ef0f-3aed-89a3-a73435c6bbcf", ... 'certainty': 0.7 # or 'distance' ... } With `encoded` True: >>> content = { ... 'video': "my_video_path.avi", ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Video', 'description')\ ... .with_near_video(content, encode=True) # <- encode MUST be set to True OR >>> my_video_file = open("my_video_path.avi", "br") >>> content = { ... 'video': my_video_file, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Video', 'description')\ ... .with_near_video(content, encode=True) # <- encode MUST be set to True >>> my_video_file.close() With `encoded` False: >>> from weaviate.util import file_encoder_b64 >>> encoded_video = file_encoder_b64("my_video_path.avi") >>> content = { ... 'video': encoded_video, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Video', 'description')\ ... .with_near_video(content, encode=False) # <- encode MUST be set to False OR >>> from weaviate.util import file_encoder_b64, video_decoder_b64 >>> with open("my_video_path.avi", "br") as my_video_file: ... encoded_video = file_encoder_b64(my_video_file) >>> content = { ... 'video': encoded_video, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Video', 'description')\ ... .with_near_video(content, encode=False) # <- encode MUST be set to False Encode Video yourself: >>> import base64 >>> with open("my_video_path.avi", "br") as my_video_file: ... encoded_video = base64.b64encode(my_video_file.read()).decode("utf-8") >>> content = { ... 'video': encoded_video, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Video', 'description')\ ... .with_near_video(content, encode=False) # <- encode MUST be set to False Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. Raises ------ AttributeError If another 'near' filter was already set. rT) r!VIDEOrrrr'rSrrrs r=with_near_videozGetBuilder.with_near_videorr?ctj|_|j t d|r9t ||jj ||jj <t||_d|_|S)a Set `nearDepth` filter. Parameters ---------- content : dict The content of the `nearDepth` filter to set. See examples below. encode : bool, optional Whether to encode the `content["depth"]` to base64 and convert to string. If True, the `content["depth"]` can be an depth path or a file opened in binary read mode. If False, the `content["depth"]` MUST be a base64 encoded string (NOT bytes, i.e. NOT binary string that looks like this: b'BASE64ENCODED' but simple 'BASE64ENCODED'). By default True. Examples -------- Content prototype: >>> content = { ... 'depth': , ... # certainty ONLY with `cosine` distance specified in the schema ... 'certainty': , # Optional, either 'certainty' OR 'distance' ... 'distance': , # Optional, either 'certainty' OR 'distance' ... } >>> { ... 'depth': "e5dc4a4c-ef0f-3aed-89a3-a73435c6bbcf", ... 'certainty': 0.7 # or 'distance' ... } With `encoded` True: >>> content = { ... 'depth': "my_depth_path.png", ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Depth', 'description')\ ... .with_near_depth(content, encode=True) # <- encode MUST be set to True OR >>> my_depth_file = open("my_depth_path.png", "br") >>> content = { ... 'depth': my_depth_file, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Depth', 'description')\ ... .with_near_depth(content, encode=True) # <- encode MUST be set to True >>> my_depth_file.close() With `encoded` False: >>> from weaviate.util import file_encoder_b64 >>> encoded_depth = file_encoder_b64("my_depth_path.png") >>> content = { ... 'depth': encoded_depth, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Depth', 'description')\ ... .with_near_depth(content, encode=False) # <- encode MUST be set to False OR >>> from weaviate.util import file_encoder_b64 >>> with open("my_depth_path.png", "br") as my_depth_file: ... encoded_depth = file_encoder_b64(my_depth_file) >>> content = { ... 'depth': encoded_depth, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Depth', 'description')\ ... .with_near_depth(content, encode=False) # <- encode MUST be set to False Encode Depth yourself: >>> import base64 >>> with open("my_depth_path.png", "br") as my_depth_file: ... encoded_depth = base64.b64encode(my_depth_file.read()).decode("utf-8") >>> content = { ... 'depth': encoded_depth, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Depth', 'description')\ ... .with_near_depth(content, encode=False) # <- encode MUST be set to False Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. Raises ------ AttributeError If another 'near' filter was already set. rT) r!DEPTHrrrr'rSrrrs r=with_near_depthzGetBuilder.with_near_depthMrr?ctj|_|j t d|r9t ||jj ||jj <t||_d|_|S)a  Set `nearThermal` filter. Parameters ---------- content : dict The content of the `nearThermal` filter to set. See examples below. encode : bool, optional Whether to encode the `content["thermal"]` to base64 and convert to string. If True, the `content["thermal"]` can be an thermal path or a file opened in binary read mode. If False, the `content["thermal"]` MUST be a base64 encoded string (NOT bytes, i.e. NOT binary string that looks like this: b'BASE64ENCODED' but simple 'BASE64ENCODED'). By default True. Examples -------- Content prototype: >>> content = { ... 'thermal': , ... # certainty ONLY with `cosine` distance specified in the schema ... 'certainty': , # Optional, either 'certainty' OR 'distance' ... 'distance': , # Optional, either 'certainty' OR 'distance' ... } >>> { ... 'thermal': "e5dc4a4c-ef0f-3aed-89a3-a73435c6bbcf", ... 'certainty': 0.7 # or 'distance' ... } With `encoded` True: >>> content = { ... 'thermal': "my_thermal_path.png", ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Thermal', 'description')\ ... .with_near_thermal(content, encode=True) # <- encode MUST be set to True OR >>> my_thermal_file = open("my_thermal_path.png", "br") >>> content = { ... 'thermal': my_thermal_file, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Thermal', 'description')\ ... .with_near_thermal(content, encode=True) # <- encode MUST be set to True >>> my_thermal_file.close() With `encoded` False: >>> from weaviate.util import file_encoder_b64 >>> encoded_thermal = file_encoder_b64("my_thermal_path.png") >>> content = { ... 'thermal': encoded_thermal, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Thermal', 'description')\ ... .with_near_thermal(content, encode=False) # <- encode MUST be set to False OR >>> from weaviate.util import file_encoder_b64 >>> with open("my_thermal_path.png", "br") as my_thermal_file: ... encoded_thermal = file_encoder_b64(my_thermal_file) >>> content = { ... 'thermal': encoded_thermal, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Thermal', 'description')\ ... .with_near_thermal(content, encode=False) # <- encode MUST be set to False Encode Thermal yourself: >>> import base64 >>> with open("my_thermal_path.png", "br") as my_thermal_file: ... encoded_thermal = base64.b64encode(my_thermal_file.read()).decode("utf-8") >>> content = { ... 'thermal': encoded_thermal, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('Thermal', 'description')\ ... .with_near_thermal(content, encode=False) # <- encode MUST be set to False Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. Raises ------ AttributeError If another 'near' filter was already set. rT) r!THERMALrrrr'rSrrrs r=with_near_thermalzGetBuilder.with_near_thermals|B%,,    ( (  .>wtGWGWG]G]?^._GD$$** +'0 $ r?ctj|_|j t d|r9t ||jj ||jj <t||_d|_|S)a Set `nearIMU` filter. Parameters ---------- content : dict The content of the `nearIMU` filter to set. See examples below. encode : bool, optional Whether to encode the `content["thermal"]` to base64 and convert to string. If True, the `content["thermal"]` can be an thermal path or a file opened in binary read mode. If False, the `content["thermal"]` MUST be a base64 encoded string (NOT bytes, i.e. NOT binary string that looks like this: b'BASE64ENCODED' but simple 'BASE64ENCODED'). By default True. Examples -------- Content prototype: >>> content = { ... 'thermal': , ... # certainty ONLY with `cosine` distance specified in the schema ... 'certainty': , # Optional, either 'certainty' OR 'distance' ... 'distance': , # Optional, either 'certainty' OR 'distance' ... } >>> { ... 'thermal': "e5dc4a4c-ef0f-3aed-89a3-a73435c6bbcf", ... 'certainty': 0.7 # or 'distance' ... } With `encoded` True: >>> content = { ... 'thermal': "my_thermal_path.png", ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('IMU', 'description')\ ... .with_near_thermal(content, encode=True) # <- encode MUST be set to True OR >>> my_thermal_file = open("my_thermal_path.png", "br") >>> content = { ... 'thermal': my_thermal_file, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('IMU', 'description')\ ... .with_near_thermal(content, encode=True) # <- encode MUST be set to True >>> my_thermal_file.close() With `encoded` False: >>> from weaviate.util import file_encoder_b64 >>> encoded_thermal = file_encoder_b64("my_thermal_path.png") >>> content = { ... 'thermal': encoded_thermal, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('IMU', 'description')\ ... .with_near_thermal(content, encode=False) # <- encode MUST be set to False OR >>> from weaviate.util import file_encoder_b64 >>> with open("my_thermal_path.png", "br") as my_thermal_file: ... encoded_thermal = file_encoder_b64(my_thermal_file) >>> content = { ... 'thermal': encoded_thermal, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('IMU', 'description')\ ... .with_near_thermal(content, encode=False) # <- encode MUST be set to False Encode IMU yourself: >>> import base64 >>> with open("my_thermal_path.png", "br") as my_thermal_file: ... encoded_thermal = base64.b64encode(my_thermal_file.read()).decode("utf-8") >>> content = { ... 'thermal': encoded_thermal, ... 'certainty': 0.7 # or 'distance' instead ... } >>> query = client.query.get('IMU', 'description')\ ... .with_near_thermal(content, encode=False) # <- encode MUST be set to False Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. Raises ------ AttributeError If another 'near' filter was already set. rT) r!IMUrrrr'rSr rrs r= with_near_imuzGetBuilder.with_near_imu'szB%==    ( (  .>wtGWGWG]G]?^._GD$$** +#G, $ r?limitcB|dkr td||_d|_|S)a^ The limit of objects returned. Parameters ---------- limit : int The max number of objects returned. Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. Raises ------ ValueError If 'limit' is non-positive. z)limit cannot be non-positive (limit >=1).T) ValueErrorrr)r:rs r= with_limitzGetBuilder.with_limits+( 19HI I $ r?offsetcJ|dkr tdd|d|_d|_|S)a The offset of objects returned, i.e. the starting index of the returned objects should be used in conjunction with the `with_limit` method. Parameters ---------- offset : int The offset used for the returned objects. Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. Raises ------ ValueError If 'offset' is non-positive. rz+offset cannot be non-positive (offset >=0).zoffset: rbT)rrr)r:rs r= with_offsetzGetBuilder.with_offsets4* A:JK K!&+ $ r?cb|j tdt||_d|_|S)as Ask a question for which weaviate will retrieve the answer from your data. This filter can be used only with QnA module: qna-transformers. NOTE: The 'autocorrect' field is enabled only with the `text-spellcheck` Weaviate module. Parameters ---------- content : dict The content of the `ask` filter to set. See examples below. Examples -------- Content full prototype: >>> content = { ... 'question' : , ... # certainty ONLY with `cosine` distance specified in the schema ... 'certainty': , # Optional, either 'certainty' OR 'distance' ... 'distance': , # Optional, either 'certainty' OR 'distance' ... 'properties': # Optional ... 'autocorrect': , # Optional ... } Full content: >>> content = { ... 'question' : "What is the NLP?", ... 'certainty': 0.7, # or 'distance' ... 'properties': ['body'] # search the answer in these properties only. ... 'autocorrect': True ... } Minimal content: >>> content = { ... 'question' : "What is the NLP?" ... } Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. rT)rrrrrs r=with_askzGetBuilder.with_asks>Z    ( (  L $ r?c t|trnt|jdkDst|jddkDr2t t |jt |j ||_|S|j 2t t |jt |j t|t r |jdj||St|trB|D];}t|t s td|jdj|=|St|tr|j||St|tstdt||jD]\}}t|t s tdt|j|<t|t r|j|j|gt|tstdt|dt|dk(r t!d |D];}t|t s td |j|j|=|S) a Add additional properties (i.e. properties from `_additional` clause). See Examples below. If the the 'properties' is of data type `str` or `list` of `str` then the method is idempotent, if it is of type `dict` or `tuple` then the exiting property is going to be replaced. To set the setting of one of the additional property use the `tuple` data type where `properties` look like this (clause: dict, settings: dict) where the 'settings' are the properties inside the '(...)' of the clause. See Examples for more information. Parameters ---------- properties : str, list of str, dict[str, str], dict[str, list of str] or tuple[dict, dict] The additional properties to include in the query. Can be property name as `str`, a list of property names, a dictionary (clause without settings) where the value is a `str` or list of `str`, or a `tuple` of 2 elements: (clause: Dict[str, str or list[str]], settings: Dict[str, Any]) where the 'clause' is the property and all its sub-properties and the 'settings' is the setting of the property, i.e. everything that is inside the `(...)` right after the property name. See Examples below. Examples -------- >>> # 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. Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. Raises ------ TypeError If one of the property is not of a correct data type. rrrzGIf type of 'properties' is `list` then all items must be of type `str`!zZThe 'properties' argument must be either of type `str`, `list`, `dict` or `tuple`! Given: zFIf type of 'properties' is `dict` then all keys must be of type `str`!znIf type of 'properties' is `dict` then all the values must be either of type `str` or `list` of `str`! Given: !zlIf type of 'properties' is `dict` and a value is of type `list` then at least one element should be present!zeIf type of 'properties' is `dict` and a value is of type `list` then all items must be of type `str`!)rRrnr7rrrCraddrrtuple_tuple_to_dictdictr|itemsrr)r:r.rkeyvaluesrSs r=with_additionalzGetBuilder.with_additionals|f j"6 74##$q(C0@0@0O,PST,T3(()3t/I/I+J*4D &K  ' ' 3/D$$%s4+E+E'F  j# &   ] + / / ;K j$ '" :!$,#a  /33D9  : K j% (    +K*d+##' #3"46  &++- 1KCc3'\%(ED  S !&#&  %))&1fd+88>> content = { ... 'path': ['name'] # Path to the property that should be used ... 'order': 'asc' # Sort order, possible values: asc, desc ... } >>> client.query.get('Author', ['name', 'address'])\ ... .with_sort(content) Or a list of sort configurations: >>> content = [ ... { ... 'path': ['name'] # Path to the property that should be used ... 'order': 'asc' # Sort order, possible values: asc, desc ... }, ... 'path': ['address'] # Path to the property that should be used ... 'order': 'desc' # Sort order, possible values: asc, desc ... } ... ] If we have a list we can add it in 2 ways. Pass the list: >>> client.query.get('Author', ['name', 'address'])\ ... .with_sort(content) Or one configuration at a time: >>> client.query.get('Author', ['name', 'address'])\ ... .with_sort(content[0]) ... .with_sort(content[1]) It is possible to call this method multiple times with lists only too. Returns ------- weaviate.gql.get.GetBuilder The updated GetBuilder. )rT)rr"rrrs r= with_sortzGetBuilder.with_sortsCr :: g.DJ$(D !  JJNN7N + r?Nr-c6t|||_d|_|S)a?Add BM25 query to search the inverted index for keywords. Parameters ---------- query: str The query to search for. properties: Optional[List[str]] Which properties should be searched. If 'None' or empty all properties will be searched. By default, None T)r,rr)r:r-r.s r= with_bm25zGetBuilder.with_bm254s%, $ r?rNrOrPc<t||||||_d|_|S)aGet objects using bm25 and vector, then combine the results using a reciprocal ranking algorithm. Parameters ---------- query: str The query to search for. alpha: Optional[float] Factor determining how BM25 and vector search are weighted. If 'None' the weaviate default of 0.75 is used. By default, None alpha = 0 -> bm25, alpha=1 -> vector search vector: Optional[List[float]] Vector that is searched for. If 'None', weaviate will use the configured text-to-vector module to create a vector from the "query" field. By default, None properties: Optional[List[str]]: Which properties should be searched by BM25. Does not have any effect for vector search. If None or empty all properties are searched. fusion_type: Optional[HybridFusionType]: Which fusion type should be used to merge keyword and vector search. T)rMrr)r:r-rNrOr.rPs r= with_hybridzGetBuilder.with_hybridCs%8eUFJ L $ r?rXrYc8t||||_d|_|S)aRetrieve groups of objects from Weaviate. Note that the return values must be set using .with_additional() to see the output. Parameters ---------- properties: List[str] Properties to group by groups: int Maximum number of groups objects_per_group: int Maximum number of objects per group T)rVrr)r:r.rXrYs r= with_group_byzGetBuilder.with_group_bycs""!V5FG $ r? single_prompt grouped_taskgrouped_propertiesc| | td|t|tr|t|ts td|jjdkr)t j |jjdg}d}|-|jd|dtj|dz }||t|d kDr|jd g}|'|jd tj||4t|d kDr&d j|}|jd |d|ddj|dz }|jdjd|ddj|d|S)aGenerate responses using the OpenAI generative search. At least one of the two parameters must be set. Parameters ---------- grouped_task: Optional[str] The task to generate a grouped response. grouped_properties: Optional[List[str]]: The properties whose contents are added to the prompts. If None or empty, all text properties contents are added. single_prompt: Optional[str] The prompt to generate a single response. zNEither parameter grouped_result_task or single_result_prompt must be not None.z&prompts and tasks must be of type str.z1.17.3errorry singleResultzsingleResult:{prompt:r5r groupedResultztask:r2z properties:["r4zgroupedResult:{,rz generate(z){rb)rrRrCrrr)weaviate_too_old_for_openairrr6r7r8rr)r:rrrresultstask_and_promptargsr<s r= with_generatezGetBuilder.with_generatexs(  \%9`   %j.L  $Z c-JDE E    * *X 5  1 1$2B2B2Q2Q R%Y  $ NN> * !78J8J=8Y7ZZ\] ]O  #  *s3E/F/J NN? +D' eD$6$6|$D#EFG!-#6H2IA2M #56 mE7"56 !1#((4.1AD DO '++i7HCHHU\L]K^^`,ab r?aliasc||_|S)zGives an alias for the query. Needs to be used if 'multi_get' requests the same 'class_name' twice. Parameters ---------- alias: str The alias for the query. )r)r:rs r= with_aliaszGetBuilder.with_aliass  r?consistency_levelc>d|jd|_d|_|S)z*Set the consistency level for the request.zconsistencyLevel: rbT)rSrr)r:rs r=with_consistency_levelz!GetBuilder.with_consistency_levels*%77H7N7N6Oq"Q $ r?wrap_getc|rd}nd}|j||jdzz }||jz }|jr|dz }|j|t |jz }|j |d|j dz }|j ||j z }|j|t |jz }|j|t |jz }|j|t |jz }|j|t |jz }|j|t |jz }|j||jz }|j||jz }|j|d|jdz }|j|d |jz }|d z }|j!}|s|j"s t%d dj'd |j"D|j!z}|d |zdzz }|r|dz }|S)a+ Build query filter as a string. Parameters ---------- wrap_get: bool A boolean to decide wether {Get{...}} is placed around the query. Useful for multi_get. Returns ------- str The GraphQL query as a string. z{Get{ry: (zlimit: rbz tenant: "rz autocut: )zeNo 'properties' or 'additional properties' specified to be returned. At least one should be included.c32K|]}t|ywrdrerfs r=riz#GetBuilder.build..s?c!f?rjrkr5rl)rrrrrCrrrrrrrrrrr_additional_to_strrrr8)r:rr-rr.s r=buildzGetBuilder.builds1 EE ;; " T[[4' 'E !!!  SLE{{&T[[)){{&74;;-q11||'%  ,T..//zz%TZZ(zz%TZZ(||'T\\**~~)T^^,,{{&$&&2000||'9T\\N!44}}(9T]]O44 SLE224 D$4$4 3  XX?d.>.>??$BYBYB[[  z!C''  TME r?cT |jjduxr|jduxs6t|jtxst|jt xrt |jdk(xrt |jddk(xsd|jdvxr\|jduxrL|jduxr<|jduxr,|jduxrtd|jD}|rd}|jj}t |dkDrd|ff} |jjjj!t#j$|j&|j(|jt|jtrwt#j|jj*d |jj*j-d d|jj*j-d d nd|jt|jt rwt#j |jj*d|jj*j-d d|jj*j-d d nd|j/|j|j0t#j2|j0j4|j0j6|j0j8|j0j:|j0j<|j0j>|j0j@nd|jB?t#jD|jBjF|jBjHnd|jJit#jL|jJjF|jJjH|jJjN|jJj6nd|\}}g}|jPD]\}|jS|jF}|jU|jV} t | dkDr| |d<|jY|^dd|j&|iii} | St` |S#tZj\$r} d| j_gi} Yd} ~ | Sd} ~ wwxYw)a[ Builds and runs the query. Returns ------- dict The response of the query. Raises ------ requests.ConnectionError If the network connection to weaviate fails. weaviate.UnexpectedStatusCodeException If weaviate reports a none OK status. Nrrrrwc3PK|]}t|tr d|vxrd|v yw)z...rN)rRrC)rgrs r=riz GetBuilder.do..#s4dC(T!?m4&??s$&rE authorizationrOrsrr)rOrsrr)rwrsrr)rorOcreation_time_unixlast_update_time_unixrr explain_scorert)r.r-)r.r-rNrO) collectionr near_vector near_objectr.metadata bm25_search hybrid_search)rrdataGeterrors)2r grpc_stubrrRrrr7rrrrrallrget_current_bearer_tokenSearch with_callr* SearchRequestrrrget_convert_references_to_grpcrMetadataRequestrorOrprqrrrurtrr,r.r-rrMrNr"_convert_references_to_grpc_result_extract_additional_propertiesrrgrpcRpcErrordetailsrdo) r: grpc_enabledr access_tokenres_objectsresultobj additionalrerzs r=r(z GetBuilder.dos"    & &d 2 !!T)=d//<=d//<   D$$%*  D$$]349dTTEUEUVcEd=d  $  d"  t#  t#  ,, * RTH++DDFL< 1$,l;=? 4))33::DD"00#'#3#3"kk  ,,8&t'8'8*E %3$=$=#'#4#4#<#%>%B%B:t%T%"  ,,8&t'8'8*E %3$=$=#0088>&*&7&7&?&?&C&CKQU&V%)%6%6%>%>%B%B:t%T%"#'#C#CDDTDT#U 55A"0!?!?!%!;!;!@!@#'#=#=#D#D/3/I/I/Z/Z262L2L2_2_%)%?%?%H%H*.*D*D*Q*Q"&"<"<"B"B"" ::1%3$7$7'+zz'<''>"&,,"4"4"&,,"4"4#'<<#6#6 '"W,Z&]E/Qb!kk(FAA&BSBSTC!%!D!DV__!UJ:*-7M*NN3' (UT%5%5w$?@Z N7:<  == 4#aiik]3N 4s=N)S66T' T""T'r<zsearch_get_pb2.MetadataResultci}|j|S|jjr|j|d<|jjr@t |jdkDr#|jDcgc] }t |c}nd|d<|jj r|jr |j nd|d<|jjr|jr |jnd|d<|jjr&|jrt|jnd|d<|jjr&|jrt|j nd|d<|jj"r|j$r |j"nd|d<|jj&r|j(r |j*nd|d <|Scc}w) NrwrrOrrrsrprqrtru)rrorwrOr7rTrrdistance_presentrscertainty_presentrpcreation_time_unix_presentrCrrqlast_update_time_unix_presentrrt score_presentruexplain_score_presentr)r:r<rnums r=r$z)GetBuilder._extract_additional_propertiesss,.  % % -# #  % % * *%*XX T "  % % , ,8;ELL8IA8Mu||4s4SW X &  % % . .=B=S=S5>>Y] Z (  % % / /?D?V?VEOO\` [ )  % % 6 6161Q1QE,,-W[ / 0  % % 8 8494W4WE//0]a 1 2  % % + +7<7J7J PT W %  % % 2 2','B'B## ^ , )5s2Gzsearch_get_pb2.PropertiesResultci}|jjD] \}}|||< |jD]8}|jDcgc]}|j |c}||j <:|Scc}wrd)non_ref_propertiesr ref_propsr.r# prop_name)r:r.r.r non_ref_propref_proprs r=r#z-GetBuilder._convert_references_to_grpc_results"$","?"?"E"E"G ( D,'F4L (#,, HJRJ]J]*BF77=*F8%% &   *sA3z search_get_pb2.PropertiesRequestc Dtj|Dcgc]}t|ts|c}|Dcgc]W}t|trEtj |j |j|j|jYc}Scc}wcc}w)N)target_collectionreference_propertyr.)r;ref_properties) r*PropertiesRequestrRrCr^RefPropertiesRequestr`r_r!r.)r:r.rs r=r!z&GetBuilder._convert_references_to_grpcs//1;Uz$PS?TU'  dF+ 33&*&7&7'+||#??P  UsBBAB cd|jt|jSd}d}t|jdD] }d}||dzz }t|jj dD]2\}}|dk(r d}||dzz }t|D] }||dzz } |d z }4|dury |d zS) z Convert `self._additional` attribute to a `str`. Returns ------- str The converted self._additional. z _additional {FrTrbc |dSNrrE key_values r=z/GetBuilder._additional_to_str..s R[\]R^r?rz {rxryr5)rrCsortedrr)r: str_to_return has_values one_levelrrrSs r=r zGetBuilder._additional_to_strs  % % 1t112 2(   0 0 ?@ -IJ Y_ ,M -"$"2"2"8"8":@^_ "KCm#J S4Z 'M -,  - T !M "  s""r? tuple_valuec"t|dk7r td|\}}t|trt|ts t dt|dk7rtdt|t|dk(rtdt|t |j d\}}t|ts t d|d z} t|j d D]7\}}t|ts t d ||d zt|zdzz }9 |dz }t|j|<t|tr|j|j|yt|t st dt|dt|dk(r td|D];}t|ts t d|j|j|=y#t$r t d dwxYw)a Convert the tuple data type argument to a dictionary. Parameters ---------- tuple_value : tuple The tuple value as (clause: , settings: ). Raises ------ ValueError If 'tuple_value' does not have exactly 2 elements. TypeError If the configuration of the 'tuple_value' is not correct. zcIf type of 'properties' is `tuple` then it should have length 2: (clause: , settings: )zWIf type of 'properties' is `tuple` then it should have this data type: (, )rzfIf type of 'properties' is `tuple` then the 'clause' (first element) should have only one key. Given: rzmIf type of 'properties' is `tuple` then the 'settings' (second element) should have at least one key. Given: zTIf type of 'properties' is `tuple` then first element's key should be of type `str`!rc |dSrHrErIs r=rKz+GetBuilder._tuple_to_dict..s YWX\r?rLzlIf type of 'properties' is `tuple` then the second elements () should have all the keys of type `str`!rrbNrz|If type of 'properties' is `tuple` then first element's dict values must be either of type `str` or `list` of `str`! Given: rzIf type of 'properties' is `tuple` and first element's dict value is of type `list` then at least one element should be present!zzIf type of 'properties' is `tuple` and first element's dict value is of type `list` then all items must be of type `str`!)r7rrRrrrrrCrMrrrrr|) r:rQclausesettings clause_keyrclause_with_settingsrrSs r=rzGetBuilder._tuple_to_dictsd" { q 5  '&$'z(D/I#  v;! --0[M;  x=A 114XA  "&,,.1!4 F*c*  *C/ $X^^%5;YZ H U!#s+#B%d U5\(AC(GG$  H #14-. fc "   1 2 6 6v > &$'CCG<.PQS  v;! F  >EeS)D   1 2 6 6u =  >+ :  s AG88H)Trd)NNNN)NNN);r@rArB__doc__rCr PROPERTIESrrr\rrr#rrrpropertyrrrrr}rrrrrrrrrrr r rrnrrrrrTrGrrrrrrr r(r$r#r r^r!r rr __classcell__)rzs@r=rrs:63:6HZ4H:6V`:6xCL#, T l I$I<IV@c@@RdR|RhBBBH///bjtjTj\jXktkTk\kZktkTk\kZktkTk\kZkktk|kZkTk4k<kZ 6#,8444lq #tCtCy#~!667tTz9JL` ` q  qf>tTz!2>|>@ s c0C | $"&(,*..2 e%  T#Y'  l+  @s)-0EH .(,&*26 3}3sm3%T#Y/ 3  3j    8H\?d?c?Bm Dm ^ 4 c3h B ;    "5#56 + #C#@T>%T>DT>r?r)ArY dataclassesrrrenumrjsonrtypingrr r r r r rrweaviaterweaviate.connectrweaviate.data.replicationrweaviate.exceptionsrweaviate.gql.filterrrrrrrrrrrrrr r!r"weaviate.typesr# weaviate.utilr$r%r&r'r(weaviate.warningsr)weaviate.proto.v1r*r% ImportErrorr,rCrGrMrVr^rZrnrrEr?r=rks810MMM'6=" ( 0   $ $  $+3+  && &2 oo o RR R8E#v+./4 5   6V>V>K  s C>>DD