Files
GenAIExamples/EdgeCraftRAG/ui/gradio/default.yaml
Zhu Yongbo c9088eb824 Add EdgeCraftRag as a GenAIExample (#1072)
Signed-off-by: ZePan110 <ze.pan@intel.com>
Signed-off-by: chensuyue <suyue.chen@intel.com>
Signed-off-by: Zhu, Yongbo <yongbo.zhu@intel.com>
Signed-off-by: Wang, Xigui <xigui.wang@intel.com>
Co-authored-by: ZePan110 <ze.pan@intel.com>
Co-authored-by: chen, suyue <suyue.chen@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: xiguiw <111278656+xiguiw@users.noreply.github.com>
Co-authored-by: lvliang-intel <liang1.lv@intel.com>
2024-11-08 21:07:24 +08:00

50 lines
1.0 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
# Model language for LLM
model_language: "Chinese"
vector_db: "FAISS"
splitter_name: "RecursiveCharacter"
k_rerank: 5
search_method: "similarity"
score_threshold: 0.5
bm25_weight: 0
# Pipeline
name: "default"
# Node parser
node_parser: "simple"
chunk_size: 192
chunk_overlap: 48
# Indexer
indexer: "faiss_vector"
# Retriever
retriever: "vectorsimilarity"
k_retrieval: 30
# Post Processor
postprocessor: "reranker"
# Generator
generator: "local"
prompt_path: "./data/default_prompt.txt"
# Models
embedding_model_id: "BAAI/bge-small-en-v1.5"
embedding_model_path: "./bge_ov_embedding"
# Device for embedding model inference
embedding_device: "AUTO"
rerank_model_id: "BAAI/bge-reranker-large"
rerank_model_path: "./bge_ov_reranker"
# Device for reranking model inference
rerank_device: "AUTO"
llm_model_id: "qwen2-7b-instruct"
llm_model_path: "./qwen2-7b-instruct/INT4_compressed_weights"
# Device for LLM model inference
llm_device: "AUTO"