Pinecone Error searching for documents: Passing index_api is no longer supported

General
,
1

I’m trying to use pinecone pod based index and run through this error in azure container apps. any idea why?

Error searching for documents: Passing index_api is no longer          
         supported. Please pass individual settings such as proxy_url,          
         proxy_headers, ssl_ca_certs, and ssl_verify directly to the Pinecone   
         constructor as keyword arguments. See the README at                    
         https://github.com/pinecone-io/pinecone-python-client/blob/main/README.
         md for examples.

with following code :

class VectorService:
    def __init__(self):
        self.settings = Settings()

    @lru_cache(maxsize=100)
    def get_vector_db(self, index_name: str) -> PineconeDb:
        try:
            return PineconeDb(
                name="hardcode index name here",
                namespace=index_name,
                dimension=self.settings.VECTOR_DB_DIMENSION,
                metric="dotproduct",
                spec=PodSpec(
                    pod_type="s1.x1", environment="asia-southeast1-gcp", replicas=3
                ),
                api_key=self.settings.PINECONE_API_KEY,
                use_hybrid_search=False,
            )
        except Exception as e:
            logger.error(f"Error initializing PineconeDb: {str(e)}")
            raise
2

Hi
Thanks for reaching out and for using Agno! I’ve looped in the right engineers to help with your question. We usually respond within 24 hours, but if this is urgent, just let us know, and we’ll do our best to prioritize it.
Appreciate your patience—we’ll get back to you soon! :smile:

3

Hello, Sorry about the error. We do not yet support Pinecone v6.x.x. We are actively working to achieve compatibility. In the meantime, we recommend using Pinecone v5.4.2 for the best experience.