Find answers from the community

Updated last year

Custom llm

I am trying to run this piece of code, with my own custom LLM implementation instead of using OpenAI. https://gpt-index.readthedocs.io/en/latest/examples/index_structs/knowledge_graph/KnowledgeGraphIndex_vs_VectorStoreIndex_vs_CustomIndex_combined.html

2 comments

LLogan M

How did you setup the LLM? Just set a global service context with your LLM and it should be fine

Plain Text

from llama_index import ServiceContext, set_global_service_context 

service_context = ServiceContext.from_defaults(llm=llm)
set_global_service_context(service_context)

nnashugame

Thank you, it fixed the issue

Add a reply