I get a Max retries exceeded with url: (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:2427)'))) when trying to inject data in pinecone DB

When trying to inject data with LlamaIndex into a Pinecone DB i get the following error:

LlamaIndex_Doc_Helper-JJYEcwwZ\Lib\site-packages\urllib3\util\retry.py", line 515, in increment
    raise MaxRetryError(_pool, url, reason) from reason  # type: ignore[arg-type]
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='llamaindex-documentation-helper-ksad0bm.svc.gcp-starter.pinecone.io', port=443): Max retries exceeded with url: /vectors/upsert (Caused by SSLError(SSLEOFError(8, 'EOF occurred in violation of protocol (_ssl.c:2427)')))
Upserted vectors:   0%|          | 0/18 [00:02<?, ?it/s]

My Python code:

#--- Indexing in Pinecone
    # Init. Pinecone Index object
    index_name = "llamaindex-documentation-helper"
    pinecone_index = pinecone.Index(index_name=index_name)
    # Init. vector store object
    vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
    # Init storage context
    storage_context = StorageContext.from_defaults(vector_store=vector_store)
    # Creates
    index = VectorStoreIndex.from_documents(
        documents=documents, # documents = dir_reader.load_data()
        storage_context=storage_context, # storage_context = StorageContext.from_defaults(vector_store=vector_store)
        service_context=service_context, # service_context = ServiceContext.from_defaults(llm=llm, embed_model=embed_model, node_parser=node_parser)
        show_progress=True,
    )

I disabled firewalls, VPN, and Antivirus programs
I am using Windows 11 pro, Python version 3.12 in a pipenv and my pip install certifi --upgrade is up to date.

I can also ping the server:

LlamaIndex Tutorial\LlamaIndex Doc Helper> ping llamaindex-documentation-helper-ksad0bm.svc.gcp-starter.pinecone.io

Pinging ingress.gcp-starter.pinecone.io [34.160.88.44] with 32 bytes of data:
Reply from 34.160.88.44: bytes=32 time=10ms TTL=114
Reply from 34.160.88.44: bytes=32 time=9ms TTL=114
Reply from 34.160.88.44: bytes=32 time=11ms TTL=114
Reply from 34.160.88.44: bytes=32 time=9ms TTL=114

Ping statistics for 34.160.88.44:
    Packets: Sent = 4, Received = 4, Lost = 0 (0% loss),
Approximate round trip times in milli-seconds:
    Minimum = 9ms, Maximum = 11ms, Average = 9ms

Any comments on how to maybe fix the issue would be greatly appreciated

Same here. I’m also facing the same error

I found the source of the issue and resolved it.
The following code line was the source of the error:

index_name = "llamaindex-documentation-helper"

The name of the index did not perfectly match the name of the index on my Picone account… Typos are monsters.

My code lines below provide a way to check if the index name exists and wipes/resets the Pinecone database

index_name = "llamaindex-oc-helper"
# Checks if the picone DB exists
if index_name not in pinecone.list_indexes():
    print("\n\033[96m The index name is not in the list of indexes associated with the provided Pinecone account.\n")
    # Hard exit
    exit()
# Init. Pinecone Index object
pinecone_index = pinecone.Index(index_name=index_name)
# Warning! Wipes the pinecone DB
pinecone_index.delete(delete_all=True)

Improved my code:

Replace

if index_name not in pinecone.list_indexes():
    print("\n\033[96m The index name is not in the list of indexes associated with the provided Pinecone account.\n")
    # Hard exit
    exit()

with

    if index_name not in pinecone.list_indexes():
        raise ValueError("The index name is not in the list of indexes associated with the provided Pinecone account.")

This topic was automatically closed 24 hours after the last reply. New replies are no longer allowed.