Are OpenAI API keys handled differently

Hmm, I think they still work the same? Maybe try a new key? Or whats the error?

Im getting this,


ValueError:
**
Could not load OpenAI embedding model. If you intended to use OpenAI, please check your OPENAI_API_KEY.
Original error:
No API key found for OpenAI.
Please set either the OPENAI_API_KEY environment variable or openai.api_key prior to initialization.
API keys can be found or created at https://platform.openai.com/account/api-keys

Consider using embed_model='local'.
Visit our documentation for more embedding options: https://docs.llamaindex.ai/en/stable/module_guides/models/embeddings.html#modules
**

Hmm, is the key in your env? You can also pas in the key directly

Yeah it is in my env as OPEN_API_KEY = ...

It should be OPENAI_API_KEY

my bad it is

i have it correctly

sent in discord incorrectly

You can do it like how @Logan M suggested. If env is not working for you

Kind of figured out the issue, it breaks when I try to use my PDF script

any idea why?

using vector store index, creating embeddings for easy indexing and query, similarity search pretty much

import os
from llama_index.core import StorageContext, VectorStoreIndex, load_index_from_storage

Change line 6 to different types of indexes

from llama_index.readers.file import PDFReader

def get_index(data, index_name):
index = None
if not os.path.exists(index_name):
print("building index", index_name)
index = VectorStoreIndex.from_documents(data,show_progress=True)
index.storage_context.persist(persist_dir=index_name)

else:
index = load_index_from_storage(
StorageContext.from_defaults(persist_dir=index_name)
)
pass

return index







pdf_path = os.path.join("data","dad.pdf")
dad_pdf = PDFReader().load_data(file=pdf_path)

dad_index = get_index(dad_pdf, "dad_info")
dad_engine = dad_index.as_query_engine()

I figured it out 🙂

it was I needed to import openai into the PDF reader file and now it works