Open uiaiek32 opened 2 weeks ago
To fix the error you're encountering with Pinecone, you need to adjust your code to match the updated Pinecone SDK's initialization process. The error message indicates that init
is no longer used directly. Instead, you should create an instance of the Pinecone class. Here's how you can do it:
import os
from pinecone import Pinecone, ServerlessSpec
pc = Pinecone(api_key=os.environ.get("PINECONE_API_KEY"))
# Example usage
if 'my_index' not in pc.list_indexes().names():
pc.create_index(
name='my_index',
dimension=1536,
metric='euclidean',
spec=ServerlessSpec(cloud='aws', region='us-west-2')
)
Make sure to replace the outdated pinecone.init
method with the creation of a Pinecone
instance as shown above. This change aligns with the latest Pinecone SDK guidelines. For the most accurate and up-to-date information, consult the Pinecone SDK documentation directly. This will ensure you're using the correct class and method names for initializing the Pinecone client with your API key and environment settings.
To continue the conversation, mention @dosu.
@dosu I still get the error, could you provide me with the correct code please?
I get this error: Error building node Pinecone(ID:Pinecone-0mjWP): init is no longer a top-level attribute of the pinecone package. Please create an instance of the Pinecone class instead. Example: import os from pinecone import Pinecone, ServerlessSpec pc = Pinecone( api_key=os.environ.get("PINECONE_API_KEY") ) # Now do stuff if 'my_index' not in pc.list_indexes().names(): pc.create_index( name='my_index', dimension=1536, metric='euclidean', spec=ServerlessSpec( cloud='aws', region='us-west-2' ) )
Hey @uiaiek32
It seems this component is outdated.
We'll get to it soon.
Feel free to update it if you got the know-how and thanks for the heads up!
Thanks for the response, I would like to ask how long this will take until it is fixed. Thank you very much. George
On Thu, May 2, 2024 at 7:10 PM Gabriel Luiz Freitas Almeida < @.***> wrote:
Hey @uiaiek32 https://github.com/uiaiek32
It seems this component is outdated.
We'll get to it soon.
Feel free to update it if you got the know-how and thanks for the heads up!
— Reply to this email directly, view it on GitHub https://github.com/langflow-ai/langflow/issues/1815#issuecomment-2090912627, or unsubscribe https://github.com/notifications/unsubscribe-auth/BF3I2B4NTMQRGPQI4HCK2TTZAJQQFAVCNFSM6AAAAABHCL67ESVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAOJQHEYTENRSG4 . You are receiving this because you were mentioned.Message ID: @.***>
Hey, I am following up on the Pinecone outdated component. Would it be possible to fix it? Thanks, George
On Thu, May 2, 2024 at 10:09 PM George @.***> wrote:
Thanks for the response, I would like to ask how long this will take until it is fixed. Thank you very much. George
On Thu, May 2, 2024 at 7:10 PM Gabriel Luiz Freitas Almeida < @.***> wrote:
Hey @uiaiek32 https://github.com/uiaiek32
It seems this component is outdated.
We'll get to it soon.
Feel free to update it if you got the know-how and thanks for the heads up!
— Reply to this email directly, view it on GitHub https://github.com/langflow-ai/langflow/issues/1815#issuecomment-2090912627, or unsubscribe https://github.com/notifications/unsubscribe-auth/BF3I2B4NTMQRGPQI4HCK2TTZAJQQFAVCNFSM6AAAAABHCL67ESVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAOJQHEYTENRSG4 . You are receiving this because you were mentioned.Message ID: @.***>
Hello I am sorry to bother you but I still get the same error. I re-deploy langflow but I still get the same error message This is the error message that I get.
If you could help me that would be great! Thanks a lot. George
I get this error when I try to connect the pinecone vector: Error building node Pinecone(ID:Pinecone-eKDBR): init is no longer a top-level attribute of the pinecone package. Please create an instance of the Pinecone class instead. Example: import os from pinecone import Pinecone, ServerlessSpec pc = Pinecone( api_key=os.environ.get("PINECONE_API_KEY") ) # Now do stuff if 'my_index' not in pc.list_indexes().names(): pc.create_index( name='my_index', dimension=1536, metric='euclidean', spec=ServerlessSpec( cloud='aws', region='us-west-2' ) )
Steps to reproduce the behavior: I click run and I get this error