update secrets token name for AudioQnA. (#2024)

ZePan110 · web-flow · commit 6949dbc1d1ed · 2025-06-05T14:58:43.000+08:00
Signed-off-by: ZePan110 &lt;ze.pan@intel.com&gt;
diff --git a/AudioQnA/benchmark/accuracy/run_acc.sh b/AudioQnA/benchmark/accuracy/run_acc.sh
@@ -1,4 +1,4 @@
-
+#!/bin/bash
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/README.md b/AudioQnA/docker_compose/amd/gpu/rocm/README.md
@@ -72,7 +72,7 @@ For TGI inference usage:
 
 ```bash
 export host_ip="External_Public_IP"           # ip address of the node
-export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token"
+export HF_TOKEN="Your_HuggingFace_API_Token"
 export http_proxy="Your_HTTP_Proxy"           # http proxy if any
 export https_proxy="Your_HTTPs_Proxy"         # https proxy if any
 export no_proxy=localhost,127.0.0.1,$host_ip,whisper-service,speecht5-service,vllm-service,tgi-service,audioqna-xeon-backend-server,audioqna-xeon-ui-server  # additional no proxies if needed
@@ -84,7 +84,7 @@ For vLLM inference usage
 
 ```bash
 export host_ip="External_Public_IP"           # ip address of the node
-export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token"
+export HF_TOKEN="Your_HuggingFace_API_Token"
 export http_proxy="Your_HTTP_Proxy"           # http proxy if any
 export https_proxy="Your_HTTPs_Proxy"         # https proxy if any
 export no_proxy=localhost,127.0.0.1,$host_ip,whisper-service,speecht5-service,vllm-service,tgi-service,audioqna-xeon-backend-server,audioqna-xeon-ui-server  # additional no proxies if needed
diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/compose.yaml b/AudioQnA/docker_compose/amd/gpu/rocm/compose.yaml
@@ -40,7 +40,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
     command: --model-id ${LLM_MODEL_ID}
diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml b/AudioQnA/docker_compose/amd/gpu/rocm/compose_vllm.yaml
@@ -35,8 +35,8 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
       WILM_USE_TRITON_FLASH_ATTENTION: 0
diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/set_env.sh b/AudioQnA/docker_compose/amd/gpu/rocm/set_env.sh
@@ -1,13 +1,12 @@
-#!/usr/bin/env bash                                                                                                           set_env.sh
-
+#!/usr/bin/env bash
 # Copyright (C) 2024 Advanced Micro Devices, Inc.
 # SPDX-License-Identifier: Apache-2.0
 
 
 # export host_ip=<your External Public IP>    # export host_ip=$(hostname -I | awk '{print $1}')
 
 export host_ip=${ip_address}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HF_TOKEN=${HF_TOKEN}
 # <token>
 
 export LLM_MODEL_ID=Intel/neural-chat-7b-v3-3
diff --git a/AudioQnA/docker_compose/amd/gpu/rocm/set_env_vllm.sh b/AudioQnA/docker_compose/amd/gpu/rocm/set_env_vllm.sh
@@ -1,4 +1,4 @@
-#!/usr/bin/env bash                                                                                                           set_env.sh
+#!/usr/bin/env bash
 
 # Copyright (C) 2024 Advanced Micro Devices, Inc.
 # SPDX-License-Identifier: Apache-2.0
@@ -8,7 +8,7 @@
 
 export host_ip=${ip_address}
 export external_host_ip=${ip_address}
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HF_TOKEN=${HF_TOKEN}
 export HF_CACHE_DIR="./data"
 export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
 export VLLM_SERVICE_PORT="8081"
diff --git a/AudioQnA/docker_compose/intel/cpu/xeon/README.md b/AudioQnA/docker_compose/intel/cpu/xeon/README.md
@@ -43,7 +43,7 @@ To set up environment variables for deploying AudioQnA services, set up some par
 
 ```bash
 export host_ip="External_Public_IP"           # ip address of the node
-export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token"
+export HF_TOKEN="Your_HuggingFace_API_Token"
 export http_proxy="Your_HTTP_Proxy"           # http proxy if any
 export https_proxy="Your_HTTPs_Proxy"         # https proxy if any
 export no_proxy=localhost,127.0.0.1,$host_ip,whisper-service,speecht5-service,vllm-service,tgi-service,audioqna-xeon-backend-server,audioqna-xeon-ui-server  # additional no proxies if needed
diff --git a/AudioQnA/docker_compose/intel/cpu/xeon/README_vllm.md b/AudioQnA/docker_compose/intel/cpu/xeon/README_vllm.md
@@ -68,7 +68,7 @@ The output of the command should contain images:
 
 ```bash
 ### Replace the string 'your_huggingfacehub_token' with your HuggingFacehub repository access token.
-export HUGGINGFACEHUB_API_TOKEN='your_huggingfacehub_token'
+export HF_TOKEN='your_huggingfacehub_token'
 ```
 
 ### Setting variables in the file set_env_vllm.sh
diff --git a/AudioQnA/docker_compose/intel/cpu/xeon/compose.yaml b/AudioQnA/docker_compose/intel/cpu/xeon/compose.yaml
@@ -36,7 +36,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
       LLM_SERVER_PORT: ${LLM_SERVER_PORT}
diff --git a/AudioQnA/docker_compose/intel/cpu/xeon/compose_multilang.yaml b/AudioQnA/docker_compose/intel/cpu/xeon/compose_multilang.yaml
@@ -40,7 +40,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       VLLM_TORCH_PROFILER_DIR: "/mnt"
       LLM_SERVER_PORT: ${LLM_SERVER_PORT}
diff --git a/AudioQnA/docker_compose/intel/cpu/xeon/compose_tgi.yaml b/AudioQnA/docker_compose/intel/cpu/xeon/compose_tgi.yaml
@@ -36,7 +36,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LLM_SERVER_PORT: ${LLM_SERVER_PORT}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://$host_ip:${LLM_SERVER_PORT}/health || exit 1"]
diff --git a/AudioQnA/docker_compose/intel/cpu/xeon/set_env.sh b/AudioQnA/docker_compose/intel/cpu/xeon/set_env.sh
@@ -5,7 +5,7 @@
 
 # export host_ip=<your External Public IP>
 export host_ip=$(hostname -I | awk '{print $1}')
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HF_TOKEN=${HF_TOKEN}
 # <token>
 
 export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
diff --git a/AudioQnA/docker_compose/intel/hpu/gaudi/README.md b/AudioQnA/docker_compose/intel/hpu/gaudi/README.md
@@ -43,7 +43,7 @@ To set up environment variables for deploying AudioQnA services, set up some par
 
 ```bash
 export host_ip="External_Public_IP"           # ip address of the node
-export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token"
+export HF_TOKEN="Your_HuggingFace_API_Token"
 export http_proxy="Your_HTTP_Proxy"           # http proxy if any
 export https_proxy="Your_HTTPs_Proxy"         # https proxy if any
 export no_proxy=localhost,127.0.0.1,$host_ip,whisper-service,speecht5-service,vllm-service,tgi-service,audioqna-gaudi-backend-server,audioqna-gaudi-ui-server  # additional no proxies if needed
diff --git a/AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml b/AudioQnA/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -45,7 +45,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
       HABANA_VISIBLE_DEVICES: all
diff --git a/AudioQnA/docker_compose/intel/hpu/gaudi/compose_tgi.yaml b/AudioQnA/docker_compose/intel/hpu/gaudi/compose_tgi.yaml
@@ -45,7 +45,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HF_HUB_DISABLE_PROGRESS_BARS: 1
       HF_HUB_ENABLE_HF_TRANSFER: 0
       HABANA_VISIBLE_DEVICES: all
diff --git a/AudioQnA/docker_compose/intel/hpu/gaudi/set_env.sh b/AudioQnA/docker_compose/intel/hpu/gaudi/set_env.sh
@@ -5,7 +5,7 @@
 
 # export host_ip=<your External Public IP>
 export host_ip=$(hostname -I | awk '{print $1}')
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export HF_TOKEN=${HF_TOKEN}
 # <token>
 
 export LLM_MODEL_ID="meta-llama/Meta-Llama-3-8B-Instruct"
diff --git a/AudioQnA/tests/README.md b/AudioQnA/tests/README.md
@@ -3,7 +3,7 @@
 ## Set the required environment variable
 
 ```bash
-export HUGGINGFACEHUB_API_TOKEN="Your_Huggingface_API_Token"
+export HF_TOKEN="Your_Huggingface_API_Token"
 ```
 
 ## Run test
diff --git a/README-deploy-benchmark.md b/README-deploy-benchmark.md
@@ -30,7 +30,7 @@ Before running the benchmarks, ensure you have:
    - (Optional) [Kubernetes set up guide on Intel Gaudi product](https://github.com/opea-project/GenAIInfra/blob/main/README.md#setup-kubernetes-cluster)
 
 2. **Configuration YAML**  
-   The configuration file (e.g., `./ChatQnA/benchmark_chatqna.yaml`) consists of two main sections: deployment and benchmarking. Required fields with `# mandatory` comment must be filled with valid values, such as `HUGGINGFACEHUB_API_TOKEN`. For all other fields, you can either customize them according to our needs or leave them empty ("") to use the default values from the [helm charts](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts).
+   The configuration file (e.g., `./ChatQnA/benchmark_chatqna.yaml`) consists of two main sections: deployment and benchmarking. Required fields with `# mandatory` comment must be filled with valid values, such as `HF_TOKEN`. For all other fields, you can either customize them according to our needs or leave them empty ("") to use the default values from the [helm charts](https://github.com/opea-project/GenAIInfra/tree/main/helm-charts).
 
    **Default Models**:
 
diff --git a/deploy.py b/deploy.py
@@ -220,11 +220,11 @@ def generate_helm_values(example_type, deploy_config, chart_dir, action_type, no
     # Initialize base values
     values = {
         "global": {
-            "HUGGINGFACEHUB_API_TOKEN": deploy_config.get("HUGGINGFACEHUB_API_TOKEN", ""),
+            "HF_TOKEN": deploy_config.get("HF_TOKEN", ""),
             "modelUseHostPath": deploy_config.get("modelUseHostPath", ""),
         }
     }
-    os.environ["HF_TOKEN"] = deploy_config.get("HUGGINGFACEHUB_API_TOKEN", "")
+    os.environ["HF_TOKEN"] = deploy_config.get("HF_TOKEN", "")
 
     # Configure components
     values = configure_node_selectors(values, node_selector or {}, deploy_config)
diff --git a/deploy_and_benchmark.py b/deploy_and_benchmark.py
@@ -187,7 +187,7 @@ def main(yaml_file, target_node=None, test_mode="oob", clean_up=True):
         return
 
     # Set HF_TOKEN
-    HF_TOKEN = deploy_config.get("HUGGINGFACEHUB_API_TOKEN", "")
+    HF_TOKEN = deploy_config.get("HF_TOKEN", "")
     os.environ["HF_TOKEN"] = HF_TOKEN
     os.environ["HUGGINGFACEHUB_API_TOKEN"] = HF_TOKEN
 

Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-`
	`1`	`+#!/bin/bash`
`2`	`2`	`# Copyright (C) 2024 Intel Corporation`
`3`	`3`	`# SPDX-License-Identifier: Apache-2.0`
`4`	`4`