Fix huggingface hub token environment variable (#214)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

DocSum/deprecated/README.md

@@ -29,12 +29,12 @@ bash ./serving/tgi_gaudi/build_docker.sh
 bash ./serving/tgi_gaudi/launch_tgi_service.sh
 ```
 
-For gated models such as `LLAMA-2`, you will have to pass -e HUGGING_FACE_HUB_TOKEN=\<token\> to the docker run command above with a valid Hugging Face Hub read token.
+For gated models such as `LLAMA-2`, you will have to pass -e HF_TOKEN=\<token\> to the docker run command above with a valid Hugging Face Hub read token.
 
-Please follow this link [huggingface token](https://huggingface.co/docs/hub/security-tokens) to get the access token and export `HUGGINGFACEHUB_API_TOKEN` environment with the token.
+Please follow this link [huggingface token](https://huggingface.co/docs/hub/security-tokens) to get the access token and export `HF_TOKEN` environment with the token.
 
 ```bash
-export HUGGINGFACEHUB_API_TOKEN=<token>
+export HF_TOKEN=<token>
 ```
 
 ### Launch a local server instance on 8 Gaudi cards:
@@ -80,7 +80,7 @@ docker run -it --net=host --ipc=host -e http_proxy=${http_proxy} -e https_proxy=
 Make sure TGI-Gaudi service is running. Launch the backend service:
 
 ```bash
-export HUGGINGFACEHUB_API_TOKEN=<token>
+export HF_TOKEN=<token>
 nohup python app/server.py &
 ```
 

DocSum/deprecated/tests/test_langchain_inference.sh

@@ -63,7 +63,7 @@ function launch_server() {
 
     # Start the Backend Service
     docker exec $DOCUMENT_SUMMARY_CONTAINER_NAME \
-        bash -c "export HUGGINGFACEHUB_API_TOKEN=$HUGGINGFACEHUB_API_TOKEN;nohup python app/server.py &"
+        bash -c "export HF_TOKEN=$HF_TOKEN;nohup python app/server.py &"
     sleep 1m
 }
 

DocSum/docker/gaudi/README.md

@@ -62,7 +62,7 @@ export http_proxy=${your_http_proxy}
 export https_proxy=${your_http_proxy}
 export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
 export TGI_LLM_ENDPOINT="http://${your_ip}:8008"
-export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
+export HF_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/docsum"

DocSum/docker/gaudi/docker_compose.yaml

@@ -24,7 +24,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
     volumes:
       - "./data:/data"
     runtime: habana
@@ -44,7 +44,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
       LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
       LANGCHAIN_PROJECT: "opea-llm-service"

DocSum/docker/xeon/README.md

@@ -63,7 +63,7 @@ export http_proxy=${your_http_proxy}
 export https_proxy=${your_http_proxy}
 export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
 export TGI_LLM_ENDPOINT="http://${your_ip}:8008"
-export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
+export HF_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/docsum"

DocSum/docker/xeon/docker_compose.yaml

@@ -24,7 +24,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
     volumes:
       - "./data:/data"
     shm_size: 1g
@@ -41,7 +41,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
       LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
       LANGCHAIN_PROJECT: "opea-llm-service"

DocSum/docsum.yaml

@@ -24,7 +24,7 @@ opea_micro_services:
       - SYS_NICE
     ipc: host
     environment:
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
     model-id: ${LLM_MODEL_ID}
@@ -35,7 +35,7 @@ opea_micro_services:
     endpoint: /v1/chat/completions
     environment:
       TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
   ui:
     host: ${UI_SERVICE_HOST_IP}
     ports:

DocSum/tests/test_docsum_on_gaudi.sh

@@ -31,7 +31,7 @@ function start_services() {
 
     export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
     export TGI_LLM_ENDPOINT="http://${ip_address}:8008"
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export HF_TOKEN=${HF_TOKEN}
     export MEGA_SERVICE_HOST_IP=${ip_address}
     export LLM_SERVICE_HOST_IP=${ip_address}
     export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/docsum"

DocSum/tests/test_docsum_on_xeon.sh

@@ -29,7 +29,7 @@ function start_services() {
 
     export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
     export TGI_LLM_ENDPOINT="http://${ip_address}:8008"
-    export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+    export HF_TOKEN=${HF_TOKEN}
     export MEGA_SERVICE_HOST_IP=${ip_address}
     export LLM_SERVICE_HOST_IP=${ip_address}
     export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/docsum"