0
## Vector Search DB In Pinecone
from pinecone import Pinecone, ServerlessSpec
import os

pc = Pinecone(api_key='a561dac3-3246-4aff-97fb-1f648d2ce750')
index_name = "text-embeddings"

if index_name not in pc.list_indexes().names():
    pc.create_index(
        name=index_name,
        dimension=384,
        metric="cosine",
        spec=ServerlessSpec(
            cloud='aws', 
            region='us-east-1'
        ) 
    ) 

from langchain_pinecone import PineconeVectorStore

namespace = "wondervector5000"

docsearch = PineconeVectorStore.from_documents(
    host="https://text-embeddings-nudmpai.svc.aped-4627-b74a.pinecone.io"
    documents=doc,
    index_name=index_name,
    embedding=embedding, 
    namespace=namespace 
)

Getting error as:

PineconeConfigurationError                Traceback (most recent call last)
Cell In[31], line 5
      1 from langchain_pinecone import PineconeVectorStore
      3 namespace = "wondervector5000"
----> 5 docsearch = PineconeVectorStore.from_documents(
      6     documents=doc,
      7     index_name=index_name,
      8     embedding=embedding, 
      9     namespace=namespace 
     10 )

    File c:\Users\Prerna\Desktop\gameReccomender\myenv\Lib\site-packages\langchain_core\vectorstores.py:550, in VectorStore.from_documents(cls, documents, embedding, **kwargs)
        548 texts = [d.page_content for d in documents]
        549 metadatas = [d.metadata for d in documents]
    --> 550 return cls.from_texts(texts, embedding, metadatas=metadatas, **kwargs)
    
    File c:\Users\Prerna\Desktop\gameReccomender\myenv\Lib\site-packages\langchain_pinecone\vectorstores.py:438, in PineconeVectorStore.from_texts(cls, texts, embedding, metadatas, ids, batch_size, text_key, namespace, index_name, upsert_kwargs, pool_threads, embeddings_chunk_size, **kwargs)
        395 @classmethod
        396 def from_texts(
        397     cls,
       (...)
        409     **kwargs: Any,
        410 ) -> PineconeVectorStore:
        411     """Construct Pinecone wrapper from raw documents.
    ...
    ---> 54     raise PineconeConfigurationError("You haven't specified an Api-Key.")
         55 if not host:
         56     raise PineconeConfigurationError("You haven't specified a host.")
    
         PineconeConfigurationError: You haven't specified an Api-Key.

I am working for a RAG model but not able to add embeddings to the Pinecone vectorDB. The code includes both host and apikey still I am getting error as api-key and host not defined. I am using pinecone vectorDB.The error in detail has been provided in the above question.

1 Answer 1

1

Try this

import os
os.environ['PINECONE_API_KEY'] = "<YOUR-API-KEY>"

this sets the environment variable that the API is looking for.

Then you can have

pc = Pinecone()
Sign up to request clarification or add additional context in comments.

Comments

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.