jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 5 Packages Projects Releases Wiki Activity

Revert "HUGGINGFACEHUB_API_TOKEN environment is change to HF_TOKEN (#… (#1521)

Browse Source 
Revert this PR since the test is not triggered properly due to the false merge of a WIP CI PR, 44a689b0bf, which block the CI test.

This change will be submitted in another PR.
This commit is contained in:
chen, suyue
2025-02-11 18:36:12 +08:00
committed by GitHub
parent 47069ac70c
commit 81b02bb947
69 changed files with 113 additions and 263 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
AudioQnA/docker_compose/intel/cpu/xeon/README.md
View File

@@ -49,7 +49,7 @@ Before starting the services with `docker compose`, you have to recheck the foll
```bash
export host_ip=<your External Public IP> # export host_ip=$(hostname -I | awk '{print $1}')
export HF_TOKEN=<your HF token>
export HUGGINGFACEHUB_API_TOKEN=<your HF token>
export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3

6
AudioQnA/docker_compose/intel/cpu/xeon/set_env.sh
View File

@@ -5,11 +5,7 @@
# export host_ip=<your External Public IP>
export host_ip=$(hostname -I | awk '{print $1}')
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
# <token>
export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3

2
AudioQnA/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -49,7 +49,7 @@ Before starting the services with `docker compose`, you have to recheck the foll
```bash
export host_ip=<your External Public IP> # export host_ip=$(hostname -I | awk '{print $1}')
export HF_TOKEN=<your HF token>
export HUGGINGFACEHUB_API_TOKEN=<your HF token>
export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3

3
AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -45,8 +45,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
HABANA_VISIBLE_DEVICES: all

8
AudioQnA/docker_compose/intel/hpu/gaudi/set_env.sh
View File

@@ -5,13 +5,7 @@
# export host_ip=<your External Public IP>
export host_ip=$(hostname -I | awk '{print $1}')
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export HF_TOKEN=${HF_TOKEN}
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
# <token>
export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3

4
AvatarChatbot/docker_compose/intel/cpu/xeon/README.md
View File

@@ -58,7 +58,7 @@ Then run the command `docker images`, you will have following images ready:
Before starting the services with `docker compose`, you have to recheck the following environment variables.
```bash
export HF_TOKEN=<your_hf_token>
export HUGGINGFACEHUB_API_TOKEN=<your_hf_token>
export host_ip=$(hostname -I | awk '{print $1}')
export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
@@ -173,7 +173,7 @@ In the current version v1.0, you need to set the avatar figure image/video and t
cd GenAIExamples/AvatarChatbot/tests
export IMAGE_REPO="opea"
export IMAGE_TAG="latest"
export HF_TOKEN=<your_hf_token>
export HUGGINGFACEHUB_API_TOKEN=<your_hf_token>
test_avatarchatbot_on_xeon.sh
```

2
AvatarChatbot/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -37,7 +37,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
healthcheck:
test: ["CMD-SHELL", "curl -f http://${host_ip}:3006/health || exit 1"]
interval: 10s

4
AvatarChatbot/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -58,7 +58,7 @@ Then run the command `docker images`, you will have following images ready:
Before starting the services with `docker compose`, you have to recheck the following environment variables.
```bash
export HF_TOKEN=<your_hf_token>
export HUGGINGFACEHUB_API_TOKEN=<your_hf_token>
export host_ip=$(hostname -I | awk '{print $1}')
export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
@@ -183,7 +183,7 @@ In the current version v1.0, you need to set the avatar figure image/video and t
cd GenAIExamples/AvatarChatbot/tests
export IMAGE_REPO="opea"
export IMAGE_TAG="latest"
export HF_TOKEN=<your_hf_token>
export HUGGINGFACEHUB_API_TOKEN=<your_hf_token>
test_avatarchatbot_on_gaudi.sh
```

5
AvatarChatbot/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -38,7 +38,7 @@ services:
- SYS_NICE
restart: unless-stopped
tgi-service:
image: ghcr.io/huggingface/tgi-gaudi:2.3.1
image: ghcr.io/huggingface/tgi-gaudi:2.0.6
container_name: tgi-gaudi-server
ports:
- "3006:80"
@@ -48,8 +48,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
HABANA_VISIBLE_DEVICES: all

4
ChatQnA/docker_compose/intel/cpu/aipc/README.md
View File

@@ -105,7 +105,7 @@ export https_proxy=${your_http_proxy}
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export INDEX_NAME="rag-redis"
export HF_TOKEN=${your_hf_api_token}
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export OLLAMA_HOST=${host_ip}
export OLLAMA_MODEL="llama3.2"
```
@@ -116,7 +116,7 @@ export OLLAMA_MODEL="llama3.2"
set EMBEDDING_MODEL_ID=BAAI/bge-base-en-v1.5
set RERANK_MODEL_ID=BAAI/bge-reranker-base
set INDEX_NAME=rag-redis
set HF_TOKEN=%your_hf_api_token%
set HUGGINGFACEHUB_API_TOKEN=%your_hf_api_token%
set OLLAMA_HOST=host.docker.internal
set OLLAMA_MODEL="llama3.2"
```

9
ChatQnA/docker_compose/intel/cpu/aipc/compose.yaml
View File

@@ -24,8 +24,7 @@ services:
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
container_name: tei-embedding-server
@@ -55,8 +54,7 @@ services:
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped
@@ -72,8 +70,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate

10
ChatQnA/docker_compose/intel/cpu/aipc/set_env.sh
View File

@@ -7,11 +7,15 @@ pushd "../../../../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "${HF_TOKEN}" ]; then
echo "Error: HF_TOKEN is not set. Please set HF_TOKEN."
if [ -z "${your_hf_api_token}" ]; then
echo "Error: HUGGINGFACEHUB_API_TOKEN is not set. Please set your_hf_api_token."
fi
export host_ip=$(hostname -I | awk '{print $1}')
if [ -z "${host_ip}" ]; then
echo "Error: host_ip is not set. Please set host_ip first."
fi
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export INDEX_NAME="rag-redis"

4
ChatQnA/docker_compose/intel/cpu/xeon/README.md
View File

@@ -21,7 +21,7 @@ To set up environment variables for deploying ChatQnA services, follow these ste
```bash
# Example: host_ip="192.168.1.1"
export host_ip="External_Public_IP"
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
```
2. If you are in a proxy environment, also set the proxy-related environment variables:
@@ -236,7 +236,7 @@ For users in China who are unable to download models directly from Huggingface,
```bash
# Example: host_ip="192.168.1.1"
export host_ip="External_Public_IP"
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
# Example: NGINX_PORT=80
export NGINX_PORT=${your_nginx_port}
```

9
ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -24,8 +24,7 @@ services:
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
container_name: tei-embedding-server
@@ -55,8 +54,7 @@ services:
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
restart: unless-stopped
@@ -72,8 +70,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${RERANK_MODEL_ID} --auto-truncate

5
ChatQnA/docker_compose/intel/cpu/xeon/set_env.sh
View File

@@ -7,11 +7,6 @@ pushd "../../../../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"

12
ChatQnA/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -21,7 +21,7 @@ To set up environment variables for deploying ChatQnA services, follow these ste
```bash
# Example: host_ip="192.168.1.1"
export host_ip="External_Public_IP"
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
```
2. If you are in a proxy environment, also set the proxy-related environment variables:
@@ -203,9 +203,9 @@ For users in China who are unable to download models directly from Huggingface,
export HF_ENDPOINT="https://hf-mirror.com"
model_name="meta-llama/Meta-Llama-3-8B-Instruct"
# Start vLLM LLM Service
docker run -p 8007:80 -v ./data:/data --name vllm-gaudi-server -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e HF_TOKEN=$HF_TOKEN -e VLLM_TORCH_PROFILER_DIR="/mnt" --cap-add=sys_nice --ipc=host opea/vllm-gaudi:latest --model $model_name --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
docker run -p 8007:80 -v ./data:/data --name vllm-gaudi-server -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e VLLM_TORCH_PROFILER_DIR="/mnt" --cap-add=sys_nice --ipc=host opea/vllm-gaudi:latest --model $model_name --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
# Start TGI LLM Service
docker run -p 8005:80 -v ./data:/data --name tgi-gaudi-server -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e HF_TOKEN=$HF_TOKEN -e ENABLE_HPU_GRAPH=true -e LIMIT_HPU_GRAPH=true -e USE_FLASH_ATTENTION=true -e FLASH_ATTENTION_RECOMPUTE=true --cap-add=sys_nice --ipc=host ghcr.io/huggingface/tgi-gaudi:2.0.6 --model-id $model_name --max-input-tokens 1024 --max-total-tokens 2048
docker run -p 8005:80 -v ./data:/data --name tgi-gaudi-server -e HF_ENDPOINT=$HF_ENDPOINT -e http_proxy=$http_proxy -e https_proxy=$https_proxy --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e ENABLE_HPU_GRAPH=true -e LIMIT_HPU_GRAPH=true -e USE_FLASH_ATTENTION=true -e FLASH_ATTENTION_RECOMPUTE=true --cap-add=sys_nice --ipc=host ghcr.io/huggingface/tgi-gaudi:2.0.6 --model-id $model_name --max-input-tokens 1024 --max-total-tokens 2048
```
2. Offline
@@ -220,9 +220,9 @@ For users in China who are unable to download models directly from Huggingface,
export HF_TOKEN=${your_hf_token}
export model_path="/path/to/model"
# Start vLLM LLM Service
docker run -p 8007:80 -v $model_path:/data --name vllm-gaudi-server --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e HF_TOKEN=$HF_TOKEN -e VLLM_TORCH_PROFILER_DIR="/mnt" --cap-add=sys_nice --ipc=host opea/vllm-gaudi:latest --model /data --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
docker run -p 8007:80 -v $model_path:/data --name vllm-gaudi-server --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e VLLM_TORCH_PROFILER_DIR="/mnt" --cap-add=sys_nice --ipc=host opea/vllm-gaudi:latest --model /data --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048
# Start TGI LLM Service
docker run -p 8005:80 -v $model_path:/data --name tgi-gaudi-server --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e HF_TOKEN=$HF_TOKEN -e ENABLE_HPU_GRAPH=true -e LIMIT_HPU_GRAPH=true -e USE_FLASH_ATTENTION=true -e FLASH_ATTENTION_RECOMPUTE=true --cap-add=sys_nice --ipc=host ghcr.io/huggingface/tgi-gaudi:2.0.6 --model-id /data --max-input-tokens 1024 --max-total-tokens 2048
docker run -p 8005:80 -v $model_path:/data --name tgi-gaudi-server --runtime=habana -e HABANA_VISIBLE_DEVICES=all -e OMPI_MCA_btl_vader_single_copy_mechanism=none -e HUGGING_FACE_HUB_TOKEN=$HF_TOKEN -e ENABLE_HPU_GRAPH=true -e LIMIT_HPU_GRAPH=true -e USE_FLASH_ATTENTION=true -e FLASH_ATTENTION_RECOMPUTE=true --cap-add=sys_nice --ipc=host ghcr.io/huggingface/tgi-gaudi:2.0.6 --model-id /data --max-input-tokens 1024 --max-total-tokens 2048
```
### Setup Environment Variables
@@ -232,7 +232,7 @@ For users in China who are unable to download models directly from Huggingface,
```bash
# Example: host_ip="192.168.1.1"
export host_ip="External_Public_IP"
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
# Example: NGINX_PORT=80
export NGINX_PORT=${your_nginx_port}
```

8
ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -24,8 +24,7 @@ services:
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
container_name: tei-embedding-gaudi-server
@@ -55,8 +54,7 @@ services:
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tei-reranking-service:
image: ghcr.io/huggingface/tei-gaudi:1.5.0
@@ -90,7 +88,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HABANA_VISIBLE_DEVICES: all
OMPI_MCA_btl_vader_single_copy_mechanism: none
LLM_MODEL_ID: ${LLM_MODEL_ID}

4
ChatQnA/docker_compose/intel/hpu/gaudi/set_env.sh
View File

@@ -6,10 +6,6 @@ pushd "../../../../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"

2
CodeGen/docker_compose/intel/cpu/xeon/README.md
View File

@@ -101,7 +101,7 @@ export http_proxy=${your_http_proxy}
export https_proxy=${your_http_proxy}
export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
export TGI_LLM_ENDPOINT="http://${host_ip}:8028"
export HF_TOKEN=${your_hf_api_token}
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export MEGA_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${host_ip}
export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:7778/v1/codegen"

5
CodeGen/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -14,7 +14,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
host_ip: ${host_ip}
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:8028/health || exit 1"]
@@ -37,8 +37,7 @@ services:
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
codegen-xeon-backend-server:
image: ${REGISTRY:-opea}/codegen:${TAG:-latest}

2
CodeGen/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -87,7 +87,7 @@ export http_proxy=${your_http_proxy}
export https_proxy=${your_http_proxy}
export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
export TGI_LLM_ENDPOINT="http://${host_ip}:8028"
export HF_TOKEN=${your_hf_api_token}
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export MEGA_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${host_ip}
export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:7778/v1/codegen"

6
CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -15,8 +15,7 @@ services:
https_proxy: ${https_proxy}
HABANA_VISIBLE_DEVICES: all
OMPI_MCA_btl_vader_single_copy_mechanism: none
HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
ENABLE_HPU_GRAPH: true
LIMIT_HPU_GRAPH: true
USE_FLASH_ATTENTION: true
@@ -46,8 +45,7 @@ services:
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
codegen-gaudi-backend-server:
image: ${REGISTRY:-opea}/codegen:${TAG:-latest}

5
CodeGen/docker_compose/set_env.sh
View File

@@ -6,12 +6,7 @@ pushd "../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export host_ip=$(hostname -I | awk '{print $1}')
export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
export TGI_LLM_ENDPOINT="http://${host_ip}:8028"
export MEGA_SERVICE_HOST_IP=${host_ip}

2
CodeTrans/docker_compose/intel/cpu/xeon/README.md
View File

@@ -72,7 +72,7 @@ Change the `LLM_MODEL_ID` below for your needs.
export host_ip="External_Public_IP"
# Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
export no_proxy="Your_No_Proxy"
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
# Example: NGINX_PORT=80
export NGINX_PORT=${your_nginx_port}
```

5
CodeTrans/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -14,7 +14,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
host_ip: ${host_ip}
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:8008/health || exit 1"]
@@ -37,8 +37,7 @@ services:
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
codetrans-xeon-backend-server:
image: ${REGISTRY:-opea}/codetrans:${TAG:-latest}

2
CodeTrans/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -64,7 +64,7 @@ Change the `LLM_MODEL_ID` below for your needs.
export host_ip="External_Public_IP"
# Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
export no_proxy="Your_No_Proxy"
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
# Example: NGINX_PORT=80
export NGINX_PORT=${your_nginx_port}
```

8
CodeTrans/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -3,7 +3,7 @@
services:
tgi-service:
image: ghcr.io/huggingface/tgi-gaudi:2.3.1
image: ghcr.io/huggingface/tgi-gaudi:2.0.6
container_name: codetrans-tgi-service
ports:
- "8008:80"
@@ -15,8 +15,7 @@ services:
https_proxy: ${https_proxy}
HABANA_VISIBLE_DEVICES: all
OMPI_MCA_btl_vader_single_copy_mechanism: none
HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
ENABLE_HPU_GRAPH: true
LIMIT_HPU_GRAPH: true
USE_FLASH_ATTENTION: true
@@ -46,8 +45,7 @@ services:
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
codetrans-gaudi-backend-server:
image: ${REGISTRY:-opea}/codetrans:${TAG:-latest}

4
CodeTrans/docker_compose/set_env.sh
View File

@@ -6,10 +6,6 @@ pushd "../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
export TGI_LLM_ENDPOINT="http://${host_ip}:8008"

6
DBQnA/docker_compose/intel/cpu/xeon/README.md
View File

@@ -36,7 +36,7 @@ Then run the command `docker images`, you will have the following Docker Images:
We set default model as "mistralai/Mistral-7B-Instruct-v0.3", change "LLM_MODEL_ID" in following Environment Variables setting if you want to use other models.
If use gated models, you also need to provide [huggingface token](https://huggingface.co/docs/hub/security-tokens) to "HF_TOKEN" environment variable.
If use gated models, you also need to provide [huggingface token](https://huggingface.co/docs/hub/security-tokens) to "HUGGINGFACEHUB_API_TOKEN" environment variable.
### 2.1 Setup Environment Variables
@@ -57,7 +57,7 @@ export https_proxy=${your_http_proxy}
export TGI_PORT=8008
export TGI_LLM_ENDPOINT=http://${your_ip}:${TGI_PORT}
export HF_TOKEN=${HF_TOKEN}
export HF_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"
export POSTGRES_USER=postgres
export POSTGRES_PASSWORD=testpwd
@@ -97,7 +97,7 @@ docker run --name test-text2sql-postgres --ipc=host -e POSTGRES_USER=${POSTGRES_
```bash
docker run -d --name="test-text2sql-tgi-endpoint" --ipc=host -p $TGI_PORT:80 -v ./data:/data --shm-size 1g -e HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN} -e HF_TOKEN=${HF_TOKEN} -e model=${model} ghcr.io/huggingface/text-generation-inference:2.1.0 --model-id $model
docker run -d --name="test-text2sql-tgi-endpoint" --ipc=host -p $TGI_PORT:80 -v ./data:/data --shm-size 1g -e HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN} -e HF_TOKEN=${HF_TOKEN} -e model=${model} ghcr.io/huggingface/text-generation-inference:2.1.0 --model-id $model
```
- Start Text-to-SQL Service

4
DBQnA/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -15,8 +15,8 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
shm_size: 1g
command: --model-id ${LLM_MODEL_ID}

5
DBQnA/docker_compose/set_env.sh
View File

@@ -6,11 +6,6 @@ pushd "../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export TGI_PORT=8008
export TGI_LLM_ENDPOINT="http://${your_ip}:${TGI_PORT}"
export LLM_MODEL_ID="mistralai/Mistral-7B-Instruct-v0.3"

4
DocIndexRetriever/docker_compose/intel/cpu/xeon/README.md
View File

@@ -43,7 +43,7 @@ docker build --no-cache -t opea/doc-index-retriever:latest --build-arg https_pro
```bash
export host_ip="YOUR IP ADDR"
export HF_TOKEN=${your_hf_api_token}
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
@@ -67,7 +67,7 @@ In that case, start Docker Containers with compose_without_rerank.yaml
```bash
export host_ip="YOUR IP ADDR"
export HF_TOKEN=${your_hf_api_token}
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
cd GenAIExamples/DocIndexRetriever/intel/cpu/xoen/
docker compose -f compose_without_rerank.yaml up -d

17
DocIndexRetriever/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -27,8 +27,7 @@ services:
REDIS_HOST: ${REDIS_HOST}
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
tei-embedding-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -43,8 +42,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
host_ip: ${host_ip}
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:6006/health || exit 1"]
@@ -64,7 +62,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
LOGFLAG: ${LOGFLAG}
restart: unless-stopped
@@ -82,8 +80,7 @@ services:
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
INDEX_NAME: ${INDEX_NAME}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
LOGFLAG: ${LOGFLAG}
RETRIEVER_COMPONENT_NAME: "OPEA_RETRIEVER_REDIS"
@@ -101,8 +98,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
host_ip: ${host_ip}
@@ -126,8 +122,7 @@ services:
https_proxy: ${https_proxy}
RERANK_TYPE: ${RERANK_TYPE}
TEI_RERANKING_ENDPOINT: ${TEI_RERANKING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
LOGFLAG: ${LOGFLAG}

21
DocIndexRetriever/docker_compose/intel/cpu/xeon/set_env.sh
View File

@@ -5,24 +5,3 @@
pushd "../../../../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export host_ip=$(hostname -I | awk '{print $1}')
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export TEI_EMBEDDING_ENDPOINT="http://${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://${host_ip}:8000/v1/retrievaltool"
export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"

2
DocIndexRetriever/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -43,7 +43,7 @@ docker build --no-cache -t opea/doc-index-retriever:latest --build-arg https_pro
```bash
export host_ip="YOUR IP ADDR"
export HF_TOKEN=${your_hf_api_token}
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:8090"

13
DocIndexRetriever/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -26,10 +26,9 @@ services:
REDIS_URL: ${REDIS_URL}
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: ghcr.io/huggingface/tei-gaudi:1.5.2
image: ghcr.io/huggingface/tei-gaudi:1.5.0
entrypoint: /bin/sh -c "apt-get update && apt-get install -y curl && text-embeddings-router --json-output --model-id ${EMBEDDING_MODEL_ID} --auto-truncate"
container_name: tei-embedding-gaudi-server
ports:
@@ -69,7 +68,7 @@ services:
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HF_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
restart: unless-stopped
retriever:
@@ -102,8 +101,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HHF_TOKE: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
host_ip: ${host_ip}
@@ -127,8 +125,7 @@ services:
https_proxy: ${https_proxy}
RERANK_TYPE: ${RERANK_TYPE}
TEI_RERANKING_ENDPOINT: ${TEI_RERANKING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HHF_TOKE: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
LOGFLAG: ${LOGFLAG}

21
DocIndexRetriever/docker_compose/intel/hpu/gaudi/set_env.sh
View File

@@ -5,24 +5,3 @@
pushd "../../../../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export host_ip=$(hostname -I | awk '{print $1}')
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export TEI_EMBEDDING_ENDPOINT="http://${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://${host_ip}:8000/v1/retrievaltool"
export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/ingest"

4
DocSum/docker_compose/intel/cpu/xeon/README.md
View File

@@ -83,7 +83,7 @@ Default model is "Intel/neural-chat-7b-v3-3". Change "LLM_MODEL_ID" environment
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
```
When using gated models, you also need to provide [HuggingFace token](https://huggingface.co/docs/hub/security-tokens) to "HF_TOKEN" environment variable.
When using gated models, you also need to provide [HuggingFace token](https://huggingface.co/docs/hub/security-tokens) to "HUGGINGFACEHUB_API_TOKEN" environment variable.
### Setup Environment Variable
@@ -96,7 +96,7 @@ To set up environment variables for deploying Document Summarization services, f
export host_ip="External_Public_IP"
# Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
export no_proxy="Your_No_Proxy"
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
```
2. If you are in a proxy environment, also set the proxy-related environment variables:

6
DocSum/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -12,8 +12,7 @@ services:
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
host_ip: ${host_ip}
LLM_ENDPOINT_PORT: ${LLM_ENDPOINT_PORT}
healthcheck:
@@ -40,8 +39,7 @@ services:
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${LLM_ENDPOINT}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
MAX_INPUT_TOKENS: ${MAX_INPUT_TOKENS}
MAX_TOTAL_TOKENS: ${MAX_TOTAL_TOKENS}
LLM_MODEL_ID: ${LLM_MODEL_ID}

4
DocSum/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -75,7 +75,7 @@ Default model is "Intel/neural-chat-7b-v3-3". Change "LLM_MODEL_ID" environment
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
```
When using gated models, you also need to provide [HuggingFace token](https://huggingface.co/docs/hub/security-tokens) to "HF_TOKEN" environment variable.
When using gated models, you also need to provide [HuggingFace token](https://huggingface.co/docs/hub/security-tokens) to "HUGGINGFACEHUB_API_TOKEN" environment variable.
### Setup Environment Variable
@@ -88,7 +88,7 @@ To set up environment variables for deploying Document Summarization services, f
export host_ip="External_Public_IP"
# Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
export no_proxy="Your_No_Proxy"
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
```
2. If you are in a proxy environment, also set the proxy-related environment variables:

4
DocSum/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -13,7 +13,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
HABANA_VISIBLE_DEVICES: all
@@ -48,7 +48,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
MAX_INPUT_TOKENS: ${MAX_INPUT_TOKENS}
MAX_TOTAL_TOKENS: ${MAX_TOTAL_TOKENS}
LLM_ENDPOINT: ${LLM_ENDPOINT}

6
DocSum/docker_compose/set_env.sh
View File

@@ -9,12 +9,6 @@ popd > /dev/null
export MAX_INPUT_TOKENS=1024
export MAX_TOTAL_TOKENS=2048
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export host_ip=$(hostname -I | awk '{print $1}')
export no_proxy="${no_proxy},${host_ip}"
export MEGA_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${host_ip}

2
DocSum/tests/test_compose_on_gaudi.sh
View File

@@ -17,7 +17,7 @@ export TAG=${IMAGE_TAG}
export MAX_INPUT_TOKENS=2048
export MAX_TOTAL_TOKENS=4096
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
export HF_TOKEN=${HF_TOKEN}
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${host_ip}
export ASR_SERVICE_HOST_IP=${host_ip}

2
DocSum/tests/test_compose_on_xeon.sh
View File

@@ -17,7 +17,7 @@ export TAG=${IMAGE_TAG}
export MAX_INPUT_TOKENS=2048
export MAX_TOTAL_TOKENS=4096
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
export HF_TOKEN=${HF_TOKEN}
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${host_ip}
export ASR_SERVICE_HOST_IP=${host_ip}

4
FaqGen/docker_compose/intel/cpu/xeon/README.md
View File

@@ -64,7 +64,7 @@ Then run the command `docker images`, you will have the following Docker Images:
We set default model as "meta-llama/Meta-Llama-3-8B-Instruct", change "LLM_MODEL_ID" in following Environment Variables setting if you want to use other models.
If use gated models, you also need to provide [huggingface token](https://huggingface.co/docs/hub/security-tokens) to "HF_TOKEN" environment variable.
If use gated models, you also need to provide [huggingface token](https://huggingface.co/docs/hub/security-tokens) to "HUGGINGFACEHUB_API_TOKEN" environment variable.
### Setup Environment Variables
@@ -79,7 +79,7 @@ export LLM_ENDPOINT_PORT=8008
export LLM_SERVICE_PORT=9000
export FAQGen_COMPONENT_NAME="OpeaFaqGenTgi"
export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
export HF_TOKEN=${your_hf_api_token}
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export MEGA_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${host_ip}
export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"

6
FaqGen/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -14,8 +14,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
host_ip: ${host_ip}
LLM_ENDPOINT_PORT: ${LLM_ENDPOINT_PORT}
healthcheck:
@@ -39,8 +38,7 @@ services:
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
FAQGen_COMPONENT_NAME: ${FAQGen_COMPONENT_NAME}
LOGFLAG: ${LOGFLAG:-False}
restart: unless-stopped

6
FaqGen/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -17,7 +17,7 @@ To set up environment variables for deploying ChatQnA services, follow these ste
```bash
# Example: host_ip="192.168.1.1"
export host_ip=$(hostname -I | awk '{print $1}')
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
```
2. If you are in a proxy environment, also set the proxy-related environment variables:
@@ -144,7 +144,7 @@ Then run the command `docker images`, you will have the following Docker Images:
We set default model as "meta-llama/Meta-Llama-3-8B-Instruct", change "LLM_MODEL_ID" in following Environment Variables setting if you want to use other models.
If use gated models, you also need to provide [huggingface token](https://huggingface.co/docs/hub/security-tokens) to "HF_TOKEN" environment variable.
If use gated models, you also need to provide [huggingface token](https://huggingface.co/docs/hub/security-tokens) to "HUGGINGFACEHUB_API_TOKEN" environment variable.
### Setup Environment Variables
@@ -159,7 +159,7 @@ export LLM_ENDPOINT_PORT=8008
export LLM_SERVICE_PORT=9000
export FAQGen_COMPONENT_NAME="OpeaFaqGenTgi"
export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
export HF_TOKEN=${your_hf_api_token}
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export MEGA_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${host_ip}
export LLM_ENDPOINT="http://${host_ip}:${LLM_ENDPOINT_PORT}"

6
FaqGen/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -13,8 +13,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
HABANA_VISIBLE_DEVICES: all
@@ -52,8 +51,7 @@ services:
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
FAQGen_COMPONENT_NAME: ${FAQGen_COMPONENT_NAME}
LOGFLAG: ${LOGFLAG:-False}
restart: unless-stopped

5
GraphRAG/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -35,12 +35,11 @@ services:
NO_PROXY: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
ipc: host
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
tgi-gaudi-service:
image: ghcr.io/huggingface/tgi-gaudi:2.3.1
image: ghcr.io/huggingface/tgi-gaudi:2.0.6
container_name: tgi-gaudi-server
ports:
- "6005:80"

6
GraphRAG/docker_compose/intel/hpu/gaudi/set_env.sh
View File

@@ -10,12 +10,6 @@ pushd "../../../../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export host_ip=$(hostname -I | awk '{print $1}')
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export OPENAI_EMBEDDING_MODEL="text-embedding-3-small"
export LLM_MODEL_ID="meta-llama/Meta-Llama-3.1-8B-Instruct"

3
MultimodalQnA/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -36,8 +36,7 @@ services:
DATAPREP_MMR_PORT: ${DATAPREP_MMR_PORT}
INDEX_NAME: ${INDEX_NAME}
LVM_ENDPOINT: "http://${LVM_SERVICE_HOST_IP}:${LVM_PORT}/v1/lvm"
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
MULTIMODAL_DATAPREP: true
DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_MULTIMODALREDIS"
restart: unless-stopped

5
MultimodalQnA/docker_compose/intel/cpu/xeon/set_env.sh
View File

@@ -6,11 +6,6 @@ pushd "../../../../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export host_ip=$(hostname -I | awk '{print $1}')
export no_proxy=${your_no_proxy}

3
MultimodalQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -38,8 +38,7 @@ services:
DATAPREP_MMR_PORT: ${DATAPREP_MMR_PORT}
INDEX_NAME: ${INDEX_NAME}
LVM_ENDPOINT: "http://${LVM_SERVICE_HOST_IP}:${LVM_PORT}/v1/lvm"
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
MULTIMODAL_DATAPREP: true
DATAPREP_COMPONENT_NAME: "OPEA_DATAPREP_MULTIMODALREDIS"
restart: unless-stopped

5
MultimodalQnA/docker_compose/intel/hpu/gaudi/set_env.sh
View File

@@ -6,11 +6,6 @@ pushd "../../../../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export host_ip=$(hostname -I | awk '{print $1}')
export MM_EMBEDDING_SERVICE_HOST_IP=${host_ip}

2
ProductivitySuite/docker_compose/intel/cpu/xeon/README.md
View File

@@ -143,7 +143,7 @@ export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
export TGI_LLM_ENDPOINT="http://${host_ip}:9009"
export REDIS_URL="redis://${host_ip}:6379"
export INDEX_NAME="rag-redis"
export HF_TOKEN=${your_hf_api_token}
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export MEGA_SERVICE_HOST_IP=${host_ip}
export EMBEDDING_SERVICE_HOST_IP=${host_ip}
export RETRIEVER_SERVICE_HOST_IP=${host_ip}

2
ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -65,7 +65,7 @@ services:
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HF_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
restart: unless-stopped
retriever:

2
SearchQnA/docker_compose/intel/cpu/xeon/README.md
View File

@@ -66,7 +66,7 @@ Before starting the services with `docker compose`, you have to recheck the foll
export host_ip=<your External Public IP> # export host_ip=$(hostname -I | awk '{print $1}')
export GOOGLE_CSE_ID=<your cse id>
export GOOGLE_API_KEY=<your google api key>
export HF_TOKEN=<your HF token>
export HUGGINGFACEHUB_API_TOKEN=<your HF token>
export EMBEDDING_MODEL_ID=BAAI/bge-base-en-v1.5
export TEI_EMBEDDING_ENDPOINT=http://${host_ip}:3001

8
SearchQnA/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -35,7 +35,7 @@ services:
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HF_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
restart: unless-stopped
web-retriever:
@@ -87,7 +87,7 @@ services:
https_proxy: ${https_proxy}
RERANK_TYPE: ${RERANK_TYPE}
TEI_RERANKING_ENDPOINT: ${TEI_RERANKING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
restart: unless-stopped
tgi-service:
@@ -102,7 +102,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
host_ip: ${host_ip}
healthcheck:
test: ["CMD-SHELL", "curl -f http://$host_ip:3006/health || exit 1"]
@@ -125,7 +125,7 @@ services:
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
restart: unless-stopped
searchqna-xeon-backend-server:

2
SearchQnA/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -65,7 +65,7 @@ Before starting the services with `docker compose`, you have to recheck the foll
export host_ip=<your External Public IP>
export GOOGLE_CSE_ID=<your cse id>
export GOOGLE_API_KEY=<your google api key>
export HF_TOKEN=<your HF token>
export HUGGINGFACEHUB_API_TOKEN=<your HF token>
export EMBEDDING_MODEL_ID=BAAI/bge-base-en-v1.5
export TEI_EMBEDDING_ENDPOINT=http://$host_ip:3001

11
SearchQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -43,7 +43,7 @@ services:
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
HF_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
restart: unless-stopped
web-retriever:
@@ -94,8 +94,7 @@ services:
https_proxy: ${https_proxy}
RERANK_TYPE: ${RERANK_TYPE}
TEI_RERANKING_ENDPOINT: ${TEI_RERANKING_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LOGFLAG: ${LOGFLAG}
restart: unless-stopped
tgi-service:
@@ -109,8 +108,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
HABANA_VISIBLE_DEVICES: all
@@ -144,8 +142,7 @@ services:
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
LOGFLAG: ${LOGFLAG}

4
SearchQnA/docker_compose/set_env.sh
View File

@@ -6,10 +6,6 @@ pushd "../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export EMBEDDING_MODEL_ID=BAAI/bge-base-en-v1.5
export TEI_EMBEDDING_ENDPOINT=http://${host_ip}:3001

2
Translation/docker_compose/intel/cpu/xeon/README.md
View File

@@ -91,7 +91,7 @@ Change the `LLM_MODEL_ID` below for your needs.
export host_ip="External_Public_IP"
# Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
export no_proxy="Your_No_Proxy"
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
# Example: NGINX_PORT=80
export NGINX_PORT=${your_nginx_port}
```

5
Translation/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -11,7 +11,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HF_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
host_ip: ${host_ip}
@@ -39,8 +39,7 @@ services:
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped

2
Translation/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -83,7 +83,7 @@ Change the `LLM_MODEL_ID` below for your needs.
export host_ip="External_Public_IP"
# Example: no_proxy="localhost, 127.0.0.1, 192.168.1.1"
export no_proxy="Your_No_Proxy"
export HF_TOKEN="Your_Huggingface_API_Token"
export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
# Example: NGINX_PORT=80
export NGINX_PORT=${your_nginx_port}
```

6
Translation/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -11,8 +11,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
HABANA_VISIBLE_DEVICES: all
@@ -48,8 +47,7 @@ services:
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
LLM_MODEL_ID: ${LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
restart: unless-stopped

5
Translation/docker_compose/set_env.sh
View File

@@ -6,13 +6,10 @@ pushd "../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export LLM_MODEL_ID="haoranxu/ALMA-13B"
export TGI_LLM_ENDPOINT="http://${host_ip}:8008"
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export MEGA_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${host_ip}
export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/translation"

4
VisualQnA/docker_compose/intel/cpu/xeon/set_env.sh
View File

@@ -6,10 +6,6 @@ pushd "../../../../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export LVM_MODEL_ID="llava-hf/llava-v1.6-mistral-7b-hf"
export LVM_ENDPOINT="http://${host_ip}:8399"

3
VisualQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -17,8 +17,7 @@ services:
HF_HUB_ENABLE_HF_TRANSFER: 0
HABANA_VISIBLE_DEVICES: all
OMPI_MCA_btl_vader_single_copy_mechanism: none
HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
HF_TOKEN: ${HF_TOKEN}
HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
ENABLE_HPU_GRAPH: true
LIMIT_HPU_GRAPH: true
USE_FLASH_ATTENTION: true

6
VisualQnA/docker_compose/intel/hpu/gaudi/set_env.sh
View File

@@ -6,12 +6,6 @@ pushd "../../../../../" > /dev/null
source .set_env.sh
popd > /dev/null
if [ -z "$HF_TOKEN" ]; then
echo "Error: The HF_TOKEN environment variable is **NOT** set. Please set it"
return -1
fi
export host_ip=$(hostname -I | awk '{print $1}')
export LVM_MODEL_ID="llava-hf/llava-v1.6-mistral-7b-hf"
export LVM_ENDPOINT="http://${host_ip}:8399"
export LVM_SERVICE_PORT=9399