petrojm's picture
changes to app and config
e18dfac
raw
history blame
1.17 kB
api: "sncloud" # set either sambastudio or sncloud
embedding_model:
"type": "sambastudio" # set either sambastudio or cpu
"batch_size": 1 #set depending of your endpoint configuration (1 if CoE embedding expert)
"coe": False #set true if using Sambastudio embeddings in a CoE endpoint
"select_expert": "e5-mistral-7b-instruct" #set if using SambaStudio CoE embedding expert
llm:
"temperature": 0.0
"do_sample": False
"max_tokens_to_generate": 1200
"coe": True #set as true if using Sambastudio CoE endpoint
"select_expert": "Meta-Llama-3.1-8B-Instruct" #set if using sncloud, SambaStudio CoE llm expert
#sncloud CoE expert name -> "llama3-8b"
retrieval:
"k_retrieved_documents": 15 #set if rerank enabled
"score_threshold": 0.2
"rerank": False # set if you want to rerank retriever results
"reranker": 'BAAI/bge-reranker-large' # set if you rerank enabled
"final_k_retrieved_documents": 5
pdf_only_mode: True # Set to true for PDF-only mode, false for all file types
prod_mode: False
prompts:
"qa_prompt": "prompts/qa_prompt.yaml"
"final_chain_prompt": "prompts/final_chain_prompt.yaml"