LlamaIndex
Log in

Find answers from the community

Updated 4 months ago

TypeError: descriptor '_mongodb_client'

At a glance
The post describes a TypeError that occurred while using an IngestionPipeline with a MongoDBAtlasVectorSearch object. The community members discuss the issue, with one member noting that they had used the same setup recently. However, there is no explicitly marked answer provided.
AAbhay
·
TypeError: descriptor '_mongodb_client' for 'MongoDBAtlasVectorSearch' objects doesn't apply to a 'MongoDBAtlasVectorSearch' object

while using ingestion pipeline
pipeline = IngestionPipeline(
transformations=[
SentenceWindowNodeParser.from_defaults(window_size=3, window_metadata_key="window",original_text_metadata_key="original_sentence"),
QuestionsAnsweredExtractor(questions=2, num_workers=2),
CohereEmbedding(cohere_api_key=key,model_name='embed-english-v3.0'),
],
vector_store=MongoDBAtlasVectorSearch(
pymongo.MongoClient(mongouri),
db_name="abhay_new",
collection_name="abhay_vector_store",
index_name='abhay_new_index'
),
docstore= MongoDocumentStore.from_uri(uri=mongouri, db_name='abhay_new',),
docstore_strategy= DocstoreStrategy.UPSERTS_AND_DELETE
)
L
2 comments
LLogan M
do you have a full stack trace? Pretty weird error
LLogan M
I just used this the other day
Add a reply
Sign up and join the conversation on Discord