Find answers from the community

Updated 6 months ago

OpenAI Platform

At a glance

The community member is trying to use a multi-index with different language models (LLMs), but is encountering an error when trying to use OpenAI or the Ollama model. The error message indicates that the OpenAI API key is not set correctly.

In the comments, another community member suggests that if the community member does not want to use OpenAI at all, they will need to pass an embedding model as well, and provides an example of how to set the service context with the Ollama model and a local embedding model.

Useful resources
i am trying the multi index but trying different llm
query_engine = summary_index.as_query_engine(
service_context=ServiceContext.from_defaults(
#llm=OpenAI(model="gpt-3.5-turbo")
#llm=Ollama("mistral")
llm=None
)
)
Still getting the below error (both None and Ollama)
-----
During handling of the above exception, another exception occurred:

ValueError Traceback (most recent call last)
/usr/local/lib/python3.10/dist-packages/llama_index/llms/utils.py in resolve_llm(llm)
29 validate_openai_api_key(llm.api_key)
30 except ValueError as e:
---> 31 raise ValueError(
32 "\n**\n"
33 "Could not load OpenAI model. "

ValueError:
**
Could not load OpenAI 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

To disable the LLM entirely, set llm=None.
**

Any suggestions?
W
2 comments
You want to use different llm?
If you dont want to use OpenAI at all, You'll need to pass the embedding model as well.


Plain Text
from llama_index import ServiceContext
from llama_index import set_global_service_context

# pass the llm of your choice, If dont want to use the llm set it to None
service_context = ServiceContext.from_defaults(embed_model="local",llm=Ollama("mistral"))

set_global_service_context(service_context)
Add a reply
Sign up and join the conversation on Discord