hongyispace
hongyispace
> this is a temp hacked solution for ollama https://github.com/s106916/graphrag Thank you for replaying. I succeed in finishing the pipeline, but I am looking for solution for the bug when...
> Hi I have hacked it via changing the code in graphrag/query/llm/oai/openai.python "chunck_text" method: (remove token encode, because the local llm just can embed text instead of encoded ones) >...
> I tried using gemma2. It did help resolve the initial issue, but I encountered another one: > > ```json > {"type": "error", "data": "Error executing verb \"text_embed\" in create_final_entities:...
> > api_base: http://localhost:11434/api > > ```json > {"type": "error", "data": "...Error executing verb \"text_embed\" in create_final_entities: Error code: 404 - {'error': \"model 'nomic_embed_text' not found, try pulling it first\"}",...
similar here: -----------------------------------------------------------------------------------------+ | NVIDIA-SMI 555.42.02 Driver Version: 555.42.02 CUDA Version: 12.5 | |-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf...