Files
GenAIExamples/ChatQnA/docker/gpu/set_env.sh
Letong Han 8ad7f36fe2 Update READMEs (#430)
* update readme gaudi part & add tei-gaudi params

Signed-off-by: letonghan <letong.han@intel.com>

* modify supported habana driver version

Signed-off-by: letonghan <letong.han@intel.com>

* update env set part

Signed-off-by: letonghan <letong.han@intel.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* add example for no_proxy

Signed-off-by: letonghan <letong.han@intel.com>

* add an example of public ip

Signed-off-by: letonghan <letong.han@intel.com>

---------

Signed-off-by: letonghan <letong.han@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2024-07-23 15:25:02 +08:00

24 lines
988 B
Bash

#!/usr/bin/env bash
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:8090"
export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
export TGI_LLM_ENDPOINT="http://${host_ip}:8008"
export REDIS_URL="redis://${host_ip}:6379"
export INDEX_NAME="rag-redis"
export MEGA_SERVICE_HOST_IP=${host_ip}
export EMBEDDING_SERVICE_HOST_IP=${host_ip}
export RETRIEVER_SERVICE_HOST_IP=${host_ip}
export RERANK_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${host_ip}
export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep"
export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6008/v1/dataprep/get_file"
export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6009/v1/dataprep/delete_file"