update secrets token name for CodeGen and CodeTrans

CodeGen/benchmark/accuracy/run_acc.sh

@@ -1,4 +1,4 @@
-
+#!/bin/bash
 
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0

CodeGen/docker_compose/amd/gpu/rocm/README.md

@@ -109,7 +109,7 @@ Key parameters are configured via environment variables set before running `dock
 | Environment Variable                    | Description                                                                                                         | Default (Set Externally)                                                                         |
 | :-------------------------------------- | :------------------------------------------------------------------------------------------------------------------ | :----------------------------------------------------------------------------------------------- |
 | `HOST_IP`                               | External IP address of the host machine. **Required.**                                                              | `your_external_ip_address`                                                                       |
-| `HUGGINGFACEHUB_API_TOKEN`              | Your Hugging Face Hub token for model access. **Required.**                                                         | `your_huggingface_token`                                                                         |
+| `HF_TOKEN`                              | Your Hugging Face Hub token for model access. **Required.**                                                         | `your_huggingface_token`                                                                         |
 | `LLM_MODEL_ID`                          | Hugging Face model ID for the CodeGen LLM (used by TGI/vLLM service). Configured within `compose.yaml` environment. | `Qwen/Qwen2.5-Coder-7B-Instruct`                                                                 |
 | `EMBEDDING_MODEL_ID`                    | Hugging Face model ID for the embedding model (used by TEI service). Configured within `compose.yaml` environment.  | `BAAI/bge-base-en-v1.5`                                                                          |
 | `LLM_ENDPOINT`                          | Internal URL for the LLM serving endpoint (used by `codegen-llm-server`). Configured in `compose.yaml`.             | `http://codegen-tgi-server:80/generate` or `http://codegen-vllm-server:8000/v1/chat/completions` |
@@ -125,7 +125,7 @@ For TGI
 
 ```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  #additional no proxies if needed
@@ -137,7 +137,7 @@ For vLLM
 
 ```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  #additional no proxies if needed
@@ -422,7 +422,7 @@ Users can interact with the backend service using the `Neural Copilot` VS Code e
 
 ## Troubleshooting
 
-- **Model Download Issues:** Check `HUGGINGFACEHUB_API_TOKEN`. Ensure internet connectivity or correct proxy settings. Check logs of `tgi-service`/`vllm-service` and `tei-embedding-server`. Gated models need prior Hugging Face access.
+- **Model Download Issues:** Check `HF_TOKEN`. Ensure internet connectivity or correct proxy settings. Check logs of `tgi-service`/`vllm-service` and `tei-embedding-server`. Gated models need prior Hugging Face access.
 - **Connection Errors:** Verify `HOST_IP` is correct and accessible. Check `docker ps` for port mappings. Ensure `no_proxy` includes `HOST_IP` if using a proxy. Check logs of the service failing to connect (e.g., `codegen-backend-server` logs if it can't reach `codegen-llm-server`).
 - **"Container name is in use"**: Stop existing containers (`docker compose down`) or change `container_name` in `compose.yaml`.
 - **Resource Issues:** CodeGen models can be memory-intensive. Monitor host RAM usage. Increase Docker resources if needed.

CodeGen/docker_compose/amd/gpu/rocm/set_env.sh

@@ -12,7 +12,7 @@ export EXTERNAL_HOST_IP=${ip_address}
 export CODEGEN_TGI_SERVICE_PORT=8028
 
 ### A token for accessing repositories with models
-export CODEGEN_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export CODEGEN_HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 
 ### Model ID
 export CODEGEN_LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"

CodeGen/docker_compose/amd/gpu/rocm/set_env_vllm.sh

@@ -13,7 +13,7 @@ export CODEGEN_VLLM_SERVICE_PORT=8028
 export CODEGEN_VLLM_ENDPOINT="http://${HOST_IP}:${CODEGEN_VLLM_SERVICE_PORT}"
 
 ### A token for accessing repositories with models
-export CODEGEN_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export CODEGEN_HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 
 ### Model ID
 export CODEGEN_LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"

CodeGen/docker_compose/intel/cpu/xeon/README.md

@@ -42,7 +42,7 @@ This uses the default vLLM-based deployment profile (`codegen-xeon-vllm`).
         # Replace with your host's external IP address (do not use localhost or 127.0.0.1)
         export HOST_IP="your_external_ip_address"
         # Replace with your Hugging Face Hub API token
-        export HUGGINGFACEHUB_API_TOKEN="your_huggingface_token"
+        export HF_TOKEN="your_huggingface_token"
 
         # Optional: Configure proxy if needed
         # export http_proxy="your_http_proxy"
@@ -90,7 +90,7 @@ The `compose.yaml` file uses Docker Compose profiles to select the LLM serving b
 - **Services Deployed:** `codegen-tgi-server`, `codegen-llm-server`, `codegen-tei-embedding-server`, `codegen-retriever-server`, `redis-vector-db`, `codegen-dataprep-server`, `codegen-backend-server`, `codegen-gradio-ui-server`.
 - **To Run:**
   ```bash
-  # Ensure environment variables (HOST_IP, HUGGINGFACEHUB_API_TOKEN) are set
+  # Ensure environment variables (HOST_IP, HF_TOKEN) are set
   docker compose --profile codegen-xeon-tgi up -d
   ```
 
@@ -103,7 +103,7 @@ Key parameters are configured via environment variables set before running `dock
 | Environment Variable                    | Description                                                                                                         | Default (Set Externally)                       |
 | :-------------------------------------- | :------------------------------------------------------------------------------------------------------------------ | :--------------------------------------------- | ------------------------------------ |
 | `HOST_IP`                               | External IP address of the host machine. **Required.**                                                              | `your_external_ip_address`                     |
-| `HUGGINGFACEHUB_API_TOKEN`              | Your Hugging Face Hub token for model access. **Required.**                                                         | `your_huggingface_token`                       |
+| `HF_TOKEN`                              | Your Hugging Face Hub token for model access. **Required.**                                                         | `your_huggingface_token`                       |
 | `LLM_MODEL_ID`                          | Hugging Face model ID for the CodeGen LLM (used by TGI/vLLM service). Configured within `compose.yaml` environment. | `Qwen/Qwen2.5-Coder-7B-Instruct`               |
 | `EMBEDDING_MODEL_ID`                    | Hugging Face model ID for the embedding model (used by TEI service). Configured within `compose.yaml` environment.  | `BAAI/bge-base-en-v1.5`                        |
 | `LLM_ENDPOINT`                          | Internal URL for the LLM serving endpoint (used by `codegen-llm-server`). Configured in `compose.yaml`.             | `http://codegen-vllm                           | tgi-server:9000/v1/chat/completions` |
@@ -216,7 +216,7 @@ Users can interact with the backend service using the `Neural Copilot` VS Code e
 
 ## Troubleshooting
 
-- **Model Download Issues:** Check `HUGGINGFACEHUB_API_TOKEN`. Ensure internet connectivity or correct proxy settings. Check logs of `tgi-service`/`vllm-service` and `tei-embedding-server`. Gated models need prior Hugging Face access.
+- **Model Download Issues:** Check `HF_TOKEN`. Ensure internet connectivity or correct proxy settings. Check logs of `tgi-service`/`vllm-service` and `tei-embedding-server`. Gated models need prior Hugging Face access.
 - **Connection Errors:** Verify `HOST_IP` is correct and accessible. Check `docker ps` for port mappings. Ensure `no_proxy` includes `HOST_IP` if using a proxy. Check logs of the service failing to connect (e.g., `codegen-backend-server` logs if it can't reach `codegen-llm-server`).
 - **"Container name is in use"**: Stop existing containers (`docker compose down`) or change `container_name` in `compose.yaml`.
 - **Resource Issues:** CodeGen models can be memory-intensive. Monitor host RAM usage. Increase Docker resources if needed.

CodeGen/docker_compose/intel/cpu/xeon/compose.yaml

@@ -17,7 +17,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       host_ip: ${host_ip}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
@@ -39,7 +39,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       host_ip: ${host_ip}
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
@@ -56,7 +56,7 @@ services:
       https_proxy: ${https_proxy}
       LLM_ENDPOINT: ${LLM_ENDPOINT}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     restart: unless-stopped
   llm-tgi-service:
     extends: llm-base
@@ -140,7 +140,7 @@ services:
       REDIS_URL: ${REDIS_URL}
       REDIS_HOST: ${host_ip}
       INDEX_NAME: ${INDEX_NAME}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: true
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
@@ -162,7 +162,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       host_ip: ${host_ip}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:80/health"]
       interval: 10s
@@ -202,7 +202,7 @@ services:
       REDIS_RETRIEVER_PORT: ${REDIS_RETRIEVER_PORT}
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: ${RETRIEVER_COMPONENT_NAME:-OPEA_RETRIEVER_REDIS}
     restart: unless-stopped

CodeGen/docker_compose/intel/cpu/xeon/compose_remote.yaml

@@ -59,7 +59,7 @@ services:
       REDIS_URL: ${REDIS_URL}
       REDIS_HOST: ${host_ip}
       INDEX_NAME: ${INDEX_NAME}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: true
     restart: unless-stopped
   tei-embedding-serving:
@@ -76,7 +76,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       host_ip: ${host_ip}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD", "curl", "-f", "http://${host_ip}:${TEI_EMBEDDER_PORT}/health"]
       interval: 10s
@@ -116,7 +116,7 @@ services:
       REDIS_RETRIEVER_PORT: ${REDIS_RETRIEVER_PORT}
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: ${RETRIEVER_COMPONENT_NAME:-OPEA_RETRIEVER_REDIS}
     restart: unless-stopped

CodeGen/docker_compose/intel/hpu/gaudi/README.md

@@ -42,7 +42,7 @@ This uses the default vLLM-based deployment profile (`codegen-gaudi-vllm`).
     # Replace with your host's external IP address (do not use localhost or 127.0.0.1)
     export HOST_IP="your_external_ip_address"
     # Replace with your Hugging Face Hub API token
-    export HUGGINGFACEHUB_API_TOKEN="your_huggingface_token"
+    export HF_TOKEN="your_huggingface_token"
 
     # Optional: Configure proxy if needed
     # export http_proxy="your_http_proxy"
@@ -93,7 +93,7 @@ The `compose.yaml` file uses Docker Compose profiles to select the LLM serving b
 - **Other Services:** Same CPU-based services as the vLLM profile.
 - **To Run:**
   ```bash
-  # Ensure environment variables (HOST_IP, HUGGINGFACEHUB_API_TOKEN) are set
+  # Ensure environment variables (HOST_IP, HF_TOKEN) are set
   docker compose --profile codegen-gaudi-tgi up -d
   ```
 
@@ -106,7 +106,7 @@ Key parameters are configured via environment variables set before running `dock
 | Environment Variable                    | Description                                                                                                         | Default (Set Externally)                       |
 | :-------------------------------------- | :------------------------------------------------------------------------------------------------------------------ | :--------------------------------------------- | ------------------------------------ |
 | `HOST_IP`                               | External IP address of the host machine. **Required.**                                                              | `your_external_ip_address`                     |
-| `HUGGINGFACEHUB_API_TOKEN`              | Your Hugging Face Hub token for model access. **Required.**                                                         | `your_huggingface_token`                       |
+| `HF_TOKEN`                              | Your Hugging Face Hub token for model access. **Required.**                                                         | `your_huggingface_token`                       |
 | `LLM_MODEL_ID`                          | Hugging Face model ID for the CodeGen LLM (used by TGI/vLLM service). Configured within `compose.yaml` environment. | `Qwen/Qwen2.5-Coder-7B-Instruct`               |
 | `EMBEDDING_MODEL_ID`                    | Hugging Face model ID for the embedding model (used by TEI service). Configured within `compose.yaml` environment.  | `BAAI/bge-base-en-v1.5`                        |
 | `LLM_ENDPOINT`                          | Internal URL for the LLM serving endpoint (used by `llm-codegen-vllm-server`). Configured in `compose.yaml`.        | http://codegen-vllm                            | tgi-server:9000/v1/chat/completions` |
@@ -224,7 +224,7 @@ Use the `Neural Copilot` extension configured with the CodeGen backend URL: `htt
   - Ensure host drivers and Habana Docker runtime are installed and working (`habana-container-runtime`).
   - Verify `runtime: habana` and volume mounts in `compose.yaml`.
   - Gaudi initialization can take significant time and memory. Monitor resource usage.
-- **Model Download Issues:** Check `HUGGINGFACEHUB_API_TOKEN`, internet access, proxy settings. Check LLM service logs.
+- **Model Download Issues:** Check `HF_TOKEN`, internet access, proxy settings. Check LLM service logs.
 - **Connection Errors:** Verify `HOST_IP`, ports, and proxy settings. Use `docker ps` and check service logs.
 
 ## Stopping the Application

CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -17,7 +17,7 @@ services:
       https_proxy: ${https_proxy}
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
-      HUGGING_FACE_HUB_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN}
       ENABLE_HPU_GRAPH: true
       LIMIT_HPU_GRAPH: true
       USE_FLASH_ATTENTION: true
@@ -46,7 +46,7 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
       HABANA_VISIBLE_DEVICES: all
       OMPI_MCA_btl_vader_single_copy_mechanism: none
       VLLM_SKIP_WARMUP: ${VLLM_SKIP_WARMUP:-false}
@@ -71,7 +71,7 @@ services:
       https_proxy: ${https_proxy}
       LLM_ENDPOINT: ${LLM_ENDPOINT}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
     restart: unless-stopped
   llm-tgi-service:
     extends: llm-base
@@ -156,7 +156,7 @@ services:
       REDIS_URL: ${REDIS_URL}
       REDIS_HOST: ${host_ip}
       INDEX_NAME: ${INDEX_NAME}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: true
     healthcheck:
       test: ["CMD-SHELL", "curl -f http://localhost:5000/v1/health_check || exit 1"]
@@ -178,7 +178,7 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       host_ip: ${host_ip}
-      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HF_TOKEN: ${HF_TOKEN}
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:80/health"]
       interval: 10s
@@ -218,7 +218,7 @@ services:
       REDIS_RETRIEVER_PORT: ${REDIS_RETRIEVER_PORT}
       INDEX_NAME: ${INDEX_NAME}
       TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${HF_TOKEN}
       LOGFLAG: ${LOGFLAG}
       RETRIEVER_COMPONENT_NAME: ${RETRIEVER_COMPONENT_NAME:-OPEA_RETRIEVER_REDIS}
     restart: unless-stopped

CodeGen/docker_compose/intel/set_env.sh

@@ -7,9 +7,9 @@ source .set_env.sh
 popd > /dev/null
 
 export HOST_IP=$(hostname -I | awk '{print $1}')
-export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
-if [ -z "${HUGGINGFACEHUB_API_TOKEN}" ]; then
-    echo "Error: HUGGINGFACEHUB_API_TOKEN is not set. Please set HUGGINGFACEHUB_API_TOKEN"
+export HF_TOKEN=${HF_TOKEN}
+if [ -z "${HF_TOKEN}" ]; then
+    echo "Error: HF_TOKEN is not set. Please set HF_TOKEN"
 fi
 
 if [ -z "${HOST_IP}" ]; then

CodeGen/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

CodeGen/tests/test_compose_on_gaudi.sh

@@ -1,4 +1,4 @@
-
+#!/bin/bashs
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 

CodeTrans/docker_compose/amd/gpu/rocm/README.md

@@ -62,7 +62,7 @@ Set the values of the variables:
 Setting variables in the operating system environment:
 
 ```bash
-export HUGGINGFACEHUB_API_TOKEN="Your_HuggingFace_API_Token"
+export HF_TOKEN="Your_HuggingFace_API_Token"
 source ./set_env_*.sh # replace the script name with the appropriate one
 ```
 

CodeTrans/docker_compose/amd/gpu/rocm/set_env.sh

@@ -21,7 +21,7 @@ export CODETRANS_TGI_SERVICE_PORT=8008
 export CODETRANS_TGI_LLM_ENDPOINT="http://${HOST_IP}:${CODETRANS_TGI_SERVICE_PORT}"
 
 ### A token for accessing repositories with models
-export CODETRANS_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export CODETRANS_HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 
 ### The port of the LLM service. On this port, the LLM service will accept connections
 export CODETRANS_LLM_SERVICE_PORT=9000

CodeTrans/docker_compose/amd/gpu/rocm/set_env_vllm.sh

@@ -21,7 +21,7 @@ export CODETRANS_VLLM_SERVICE_PORT=8008
 export CODETRANS_LLM_ENDPOINT="http://${HOST_IP}:${CODETRANS_VLLM_SERVICE_PORT}"
 
 ### A token for accessing repositories with models
-export CODETRANS_HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
+export CODETRANS_HUGGINGFACEHUB_API_TOKEN=${HF_TOKEN}
 
 ### The port of the LLM service. On this port, the LLM service will accept connections
 export CODETRANS_LLM_SERVICE_PORT=9000