Hello everyone!
After having recreated my Weaviate class instance with two extra properties, I suddenly get the error the following exception when trying to retrieve data from that class:
UnexpectedStatusCodeException: Query was not successful! Unexpected status code: 422, with response body: {'error': [{'message': 'no graphql provider present, this is most likely because no schema is present. Import a schema first!'}]}.
I never had this exception before and am not sure what I might have done wrong.
This is the function I use to create classes :
# CREATE CLASS
def create_class(self,
class_name: str,
class_description: str,
vectorizer: str = "text2vec-openai"
):
# Create list of properties
class_obj = {
"class": class_name,
"description": class_description,
"properties": [
{
"dataType": ["text"],
"indexSearchable": True,
"description": "Title of the document.",
"name": "title",
"tokenization": "word"
},
{
"dataType": ["text"],
"indexSearchable": True,
"description": "The text itself",
"name": "body",
"tokenization": "word"
},
{
"dataType": ["int"],
"description": "Page number / time stamp fragment",
"name": "referenceLocation",
},
{
"dataType": ["text"],
"description": "Unit of the page number/timestamp",
"name": "unit",
},
{
"dataType": ["text"],
"indexSearchable": True,
"description": "Type of document.",
"name": "documentType",
"tokenization": "word"
},
{
"dataType": ["text"],
"indexSearchable": True,
"description": "Type of document.",
"name": "url",
"tokenization": "word"
},
]
}
class_obj["vectorizer"] = vectorizer
self.client.schema.create_class(class_obj)
return {"Status": f"The collection {class_name} has been created."}
Data has been added by parsing PDFs.
Now when I check if the class exists, that still works, it correctly returns True, and I can also check the schema of the class, which returns this :
{
"class": "Geschiedenis",
"description": "Leermaterial ASO1 voor het vak Geschiedenis",
"invertedIndexConfig": {
"bm25": {
"b": 0.75,
"k1": 1.2
},
"cleanupIntervalSeconds": 60,
"stopwords": {
"additions": null,
"preset": "en",
"removals": null
}
},
"moduleConfig": {
"text2vec-openai": {
"baseURL": "https://api.openai.com",
"model": "ada",
"modelVersion": "002",
"type": "text",
"vectorizeClassName": true
}
},
"multiTenancyConfig": {
"enabled": false
},
"properties": [
{
"dataType": [
"text"
],
"description": "Title of the document.",
"indexFilterable": true,
"indexSearchable": true,
"moduleConfig": {
"text2vec-openai": {
"skip": false,
"vectorizePropertyName": false
}
},
"name": "title",
"tokenization": "word"
},
{
"dataType": [
"text"
],
"description": "The text itself",
"indexFilterable": true,
"indexSearchable": true,
"moduleConfig": {
"text2vec-openai": {
"skip": false,
"vectorizePropertyName": false
}
},
"name": "body",
"tokenization": "word"
},
{
"dataType": [
"int"
],
"description": "Page number / time stamp fragment",
"indexFilterable": true,
"indexSearchable": false,
"moduleConfig": {
"text2vec-openai": {
"skip": false,
"vectorizePropertyName": false
}
},
"name": "referenceLocation"
},
{
"dataType": [
"text"
],
"description": "Unit of the puge number/timestamp",
"indexFilterable": true,
"indexSearchable": true,
"moduleConfig": {
"text2vec-openai": {
"skip": false,
"vectorizePropertyName": false
}
},
"name": "unit",
"tokenization": "word"
},
{
"dataType": [
"text"
],
"description": "Type of document.",
"indexFilterable": true,
"indexSearchable": true,
"moduleConfig": {
"text2vec-openai": {
"skip": false,
"vectorizePropertyName": false
}
},
"name": "documentType",
"tokenization": "word"
},
{
"dataType": [
"text"
],
"description": "Type of document.",
"indexFilterable": true,
"indexSearchable": true,
"moduleConfig": {
"text2vec-openai": {
"skip": false,
"vectorizePropertyName": false
}
},
"name": "url",
"tokenization": "word"
}
],
"replicationConfig": {
"factor": 1
},
"shardingConfig": {
"virtualPerPhysical": 128,
"desiredCount": 1,
"actualCount": 1,
"desiredVirtualCount": 128,
"actualVirtualCount": 128,
"key": "_id",
"strategy": "hash",
"function": "murmur3"
},
"vectorIndexConfig": {
"skip": false,
"cleanupIntervalSeconds": 300,
"maxConnections": 64,
"efConstruction": 128,
"ef": -1,
"dynamicEfMin": 100,
"dynamicEfMax": 500,
"dynamicEfFactor": 8,
"vectorCacheMaxObjects": 1000000000000,
"flatSearchCutoff": 40000,
"distance": "cosine",
"pq": {
"enabled": false,
"bitCompression": false,
"segments": 0,
"centroids": 256,
"trainingLimit": 100000,
"encoder": {
"type": "kmeans",
"distribution": "log-normal"
}
}
},
"vectorIndexType": "hnsw",
"vectorizer": "text2vec-openai"
}
However, when I try to run a query on my data or retrieve data, e.g. like the following :
def get_data(self,
class_name: str,
batch_size: int = None,
return_prop: List[str] = ['title', 'body', 'referenceLocation', 'unit', 'url', 'documentType'],
cursor: UUID = None
) -> dict:
query = (
self.client.query.get(
class_name=class_name,
properties=return_prop
)
.with_additional(["id"])
.with_limit(batch_size)
)
# fetch next set of results
if cursor is not None:
result = query.with_after(cursor).do()
else:
result = query.do()
return result["data"]["Get"][class_name]
I get this error :
UnexpectedStatusCodeException: Query was not successful! Unexpected status code: 422, with response body: {'error': [{'message': 'no graphql provider present, this is most likely because no schema is present. Import a schema first!'}]}.
Does anyone maybe know what is causing this error? As you could see, I did import a schema and I can retrieve it, but when retrieving data, it says that there is no schema present.
Thanks a lot!
Birgit
