jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 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

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"