Find answers from the community

Updated last year

Hi there When i try to run the following

Hi there. When i try to run the following example: https://gpt-index.readthedocs.io/en/latest/getting_started/starter_example.html#build-and-query-index I get the error that I doen't have the OPENAI_API_KEY configurated. I really need this key for this simple example??

9 comments

LLogan M

Yea it's needed because it's generating embeddings (which defaults to text-embedding-ada-002 from OpenAI)

If you upgrade to v0.8.0, there are some easy options for local stuff, but you need to install some extra dependencies (llama.cpp, sentence-transformers)
https://gpt-index.readthedocs.io/en/latest/getting_started/installation.html#local-environment-setup

LLogan M

Or you can manually configure a local embedding model as well

https://gpt-index.readthedocs.io/en/latest/core_modules/model_modules/embeddings/usage_pattern.html#embedding-model-integrations

eelmatero

I imported a open ai key and i get:
tenacity.RetryError: RetryError[<Future at 0x7fdac8ab62b0 state=finished raised RateLimitError>]

LLogan M

how did you set the openai key? My go-to method is this, especially for notebooks

Plain Text

import os
import openai

os.environ["OPENAI_API_KEY"] = "sk-..."
openai.api_key = os.environ["OPENAI_API_KEY"]

eelmatero

import os

import openai

from llama_index import SimpleDirectoryReader, VectorStoreIndex

os.environ["OPENAI_API_KEY"] = "sk-"
openai.api_key = "sk-"

documents = SimpleDirectoryReader('data').load_data()
index = VectorStoreIndex.from_documents(documents)

query_engine = index.as_query_engine()
response = query_engine.query("What did the author do growing up?")
print(response)

LLogan M

🤷‍♂️ Should be working

LLogan M

Although you did get a rate limit error I just noticed

LLogan M

Which happens if you have the free credits usually

eelmatero

Ahh okayy, thankss

Add a reply