Reputation: 1
Here’s a shorter message to ask for help on Stack Overflow:
Hi everyone,
I need help with the following function:
def add_collection_content_vector_field(collection_name: str):
'''
Add a new field to the collection to hold the vectorized content of each document.
'''
collection = db[collection_name]
bulk_operations = []
for doc in collection.find():
if "contentVector" in doc:
del doc["contentVector"]
content = json.dumps(doc, default=str)
content_vector = generate_embeddings(content)
bulk_operations.append(pymongo.UpdateOne(
{"_id": doc["_id"]},
{"$set": {"contentVector": content_vector}},
upsert=True
))
collection.bulk_write(bulk_operations)
When I run add_collection_content_vector_field("sales")
, I get the following error:
CursorNotFound: cursor id <> not found, full error: {'ok': 0.0, 'errmsg': 'cursor id <> not found', 'code': 43, 'codeName': 'CursorNotFound', '$clusterTime': {'clusterTime': Timestamp(1715923790, 2), 'signature': {'hash': b'\xca\x8f9\xf0f!'\xdb\xf5r\xbb\xe0\xf4to\xcc1\x93\x8e', 'keyId': 7313113004709511172}}, 'operationTime': Timestamp(1715923790, 2)}
Any ideas on how to fix this?
Thanks!
I tried running the function add_collection_content_vector_field("sales")
to add a new field to each document in the 'sales' collection. I expected the function to iterate through all documents, generate embeddings, and update each document with the new contentVector
field.
However, after processing some documents, I encountered the following error:
CursorNotFound: cursor id <> not found, full error: {'ok': 0.0, 'errmsg': 'cursor id <> not found', 'code': 43, 'codeName': 'CursorNotFound', '$clusterTime': {'clusterTime': Timestamp(1715923790, 2), 'signature': {'hash': b'\xca\x8f9\xf0f!'\xdb\xf5r\xbb\xe0\xf4to\xcc1\x93\x8e', 'keyId': 7313113004709511172}}, 'operationTime': Timestamp(1715923790, 2)}
This error occurs partway through the process, preventing the function from completing.
Upvotes: 0
Views: 50