jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Replace environment variables with service name for ChatQnA (#977)

Browse Source 
Signed-off-by: lvliang-intel <liang1.lv@intel.com>
This commit is contained in:
lvliang-intel
2024-10-18 11:31:24 +08:00
committed by GitHub
parent 3c3a5bed67
commit 256b58c07e
27 changed files with 330 additions and 562 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
ChatQnA/docker_compose/intel/hpu/gaudi/README.md
View File

@@ -454,7 +454,7 @@ curl http://${host_ip}:9090/v1/guardrails\
To access the frontend, open the following URL in your browser: http://{host_ip}:5173. By default, the UI runs on port 5173 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `compose.yaml` file as shown below:
```yaml
chaqna-gaudi-ui-server:
chatqna-gaudi-ui-server:
image: opea/chatqna-ui:latest
...
ports:
@@ -467,10 +467,10 @@ If you want to launch the UI using Nginx, open this URL: `http://${host_ip}:${NG
## 🚀 Launch the Conversational UI (Optional)
To access the Conversational UI (react based) frontend, modify the UI service in the `compose.yaml` file. Replace `chaqna-gaudi-ui-server` service with the `chatqna-gaudi-conversation-ui-server` service as per the config below:
To access the Conversational UI (react based) frontend, modify the UI service in the `compose.yaml` file. Replace `chatqna-gaudi-ui-server` service with the `chatqna-gaudi-conversation-ui-server` service as per the config below:
```yaml
chaqna-gaudi-conversation-ui-server:
chatqna-gaudi-conversation-ui-server:
image: opea/chatqna-conversation-ui:latest
container_name: chatqna-gaudi-conversation-ui-server
environment:
@@ -479,7 +479,7 @@ chaqna-gaudi-conversation-ui-server:
ports:
- "5174:80"
depends_on:
- chaqna-gaudi-backend-server
- chatqna-gaudi-backend-server
ipc: host
restart: always
```
@@ -487,7 +487,7 @@ chaqna-gaudi-conversation-ui-server:
Once the services are up, open the following URL in your browser: http://{host_ip}:5174. By default, the UI runs on port 80 internally. If you prefer to use a different host port to access the frontend, you can modify the port mapping in the `compose.yaml` file as shown below:
```yaml
chaqna-gaudi-conversation-ui-server:
chatqna-gaudi-conversation-ui-server:
image: opea/chatqna-conversation-ui:latest
...
ports:

57
ChatQnA/docker_compose/intel/hpu/gaudi/compose.yaml
View File

@@ -20,9 +20,10 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_URL: redis://redis-vector-db:6379
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: ghcr.io/huggingface/tei-gaudi:latest
@@ -57,9 +58,11 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_URL: redis://redis-vector-db:6379
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -102,7 +105,7 @@ services:
- SYS_NICE
ipc: host
command: --model-id ${LLM_MODEL_ID} --max-input-length 2048 --max-total-tokens 4096
chaqna-gaudi-backend-server:
chatqna-gaudi-backend-server:
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-gaudi-backend-server
depends_on:
@@ -117,51 +120,49 @@ services:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- EMBEDDING_SERVER_HOST_IP=${EMBEDDING_SERVER_HOST_IP}
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-8090}
- RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
- RERANK_SERVER_HOST_IP=${RERANK_SERVER_HOST_IP}
- RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-8808}
- LLM_SERVER_HOST_IP=${LLM_SERVER_HOST_IP}
- LLM_SERVER_PORT=${LLM_SERVER_PORT:-8005}
- MEGA_SERVICE_HOST_IP=chatqna-gaudi-backend-server
- EMBEDDING_SERVER_HOST_IP=tei-embedding-service
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80}
- RETRIEVER_SERVICE_HOST_IP=retriever
- RERANK_SERVER_HOST_IP=tei-reranking-service
- RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-80}
- LLM_SERVER_HOST_IP=tgi-service
- LLM_SERVER_PORT=${LLM_SERVER_PORT:-80}
- LOGFLAG=${LOGFLAG}
ipc: host
restart: always
chaqna-gaudi-ui-server:
chatqna-gaudi-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-gaudi-ui-server
depends_on:
- chaqna-gaudi-backend-server
- chatqna-gaudi-backend-server
ports:
- "5173:5173"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
- UPLOAD_FILE_BASE_URL=${DATAPREP_SERVICE_ENDPOINT}
- GET_FILE=${DATAPREP_GET_FILE_ENDPOINT}
- DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
ipc: host
restart: always
chaqna-gaudi-nginx-server:
chatqna-gaudi-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: chaqna-gaudi-nginx-server
container_name: chatqna-gaudi-nginx-server
depends_on:
- chaqna-gaudi-backend-server
- chaqna-gaudi-ui-server
- chatqna-gaudi-backend-server
- chatqna-gaudi-ui-server
ports:
- "${NGINX_PORT:-80}:80"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- FRONTEND_SERVICE_IP=${FRONTEND_SERVICE_IP}
- FRONTEND_SERVICE_PORT=${FRONTEND_SERVICE_PORT}
- BACKEND_SERVICE_NAME=${BACKEND_SERVICE_NAME}
- BACKEND_SERVICE_IP=${BACKEND_SERVICE_IP}
- BACKEND_SERVICE_PORT=${BACKEND_SERVICE_PORT}
- FRONTEND_SERVICE_IP=chatqna-gaudi-ui-server
- FRONTEND_SERVICE_PORT=5173
- BACKEND_SERVICE_NAME=chatqna
- BACKEND_SERVICE_IP=chatqna-gaudi-backend-server
- BACKEND_SERVICE_PORT=8888
- DATAPREP_SERVICE_IP=dataprep-redis-service
- DATAPREP_SERVICE_PORT=6007
ipc: host
restart: always

63
ChatQnA/docker_compose/intel/hpu/gaudi/compose_guardrails.yaml
View File

@@ -20,9 +20,10 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_URL: redis://redis-vector-db:6379
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tgi-guardrails-service:
image: ghcr.io/huggingface/tgi-gaudi:2.0.5
@@ -59,8 +60,8 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
SAFETY_GUARD_MODEL_ID: ${SAFETY_GUARD_MODEL_ID}
SAFETY_GUARD_ENDPOINT: ${SAFETY_GUARD_ENDPOINT}
SAFETY_GUARD_MODEL_ID: ${GURADRAILS_MODEL_ID}
SAFETY_GUARD_ENDPOINT: http://tgi-guardrails-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tei-embedding-service:
@@ -94,9 +95,11 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_URL: redis://redis-vector-db:6379
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -139,7 +142,7 @@ services:
- SYS_NICE
ipc: host
command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
chaqna-gaudi-backend-server:
chatqna-gaudi-backend-server:
image: ${REGISTRY:-opea}/chatqna-guardrails:${TAG:-latest}
container_name: chatqna-gaudi-guardrails-server
depends_on:
@@ -156,53 +159,51 @@ services:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- GUARDRAIL_SERVICE_HOST_IP=${GUARDRAIL_SERVICE_HOST_IP}
- MEGA_SERVICE_HOST_IP=chatqna-gaudi-backend-server
- GUARDRAIL_SERVICE_HOST_IP=guardrails
- GUARDRAIL_SERVICE_PORT=${GUARDRAIL_SERVICE_PORT:-9090}
- EMBEDDING_SERVER_HOST_IP=${EMBEDDING_SERVER_HOST_IP}
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-8090}
- RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
- RERANK_SERVER_HOST_IP=${RERANK_SERVER_HOST_IP}
- RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-8808}
- LLM_SERVER_HOST_IP=${LLM_SERVER_HOST_IP}
- LLM_SERVER_PORT=${LLM_SERVER_PORT:-8005}
- EMBEDDING_SERVER_HOST_IP=tei-embedding-service
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80}
- RETRIEVER_SERVICE_HOST_IP=retriever
- RERANK_SERVER_HOST_IP=tei-reranking-service
- RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-80}
- LLM_SERVER_HOST_IP=tgi-service
- LLM_SERVER_PORT=${LLM_SERVER_PORT:-80}
- LOGFLAG=${LOGFLAG}
ipc: host
restart: always
chaqna-gaudi-ui-server:
chatqna-gaudi-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-gaudi-ui-server
depends_on:
- chaqna-gaudi-backend-server
- chatqna-gaudi-backend-server
ports:
- "5173:5173"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
- UPLOAD_FILE_BASE_URL=${DATAPREP_SERVICE_ENDPOINT}
- GET_FILE=${DATAPREP_GET_FILE_ENDPOINT}
- DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
ipc: host
restart: always
chaqna-gaudi-nginx-server:
chatqna-gaudi-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: chaqna-gaudi-nginx-server
container_name: chatqna-gaudi-nginx-server
depends_on:
- chaqna-gaudi-backend-server
- chaqna-gaudi-ui-server
- chatqna-gaudi-backend-server
- chatqna-gaudi-ui-server
ports:
- "${NGINX_PORT:-80}:80"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- FRONTEND_SERVICE_IP=${FRONTEND_SERVICE_IP}
- FRONTEND_SERVICE_PORT=${FRONTEND_SERVICE_PORT}
- BACKEND_SERVICE_NAME=${BACKEND_SERVICE_NAME}
- BACKEND_SERVICE_IP=${BACKEND_SERVICE_IP}
- BACKEND_SERVICE_PORT=${BACKEND_SERVICE_PORT}
- FRONTEND_SERVICE_IP=chatqna-gaudi-ui-server
- FRONTEND_SERVICE_PORT=5173
- BACKEND_SERVICE_NAME=chatqna
- BACKEND_SERVICE_IP=chatqna-gaudi-backend-server
- BACKEND_SERVICE_PORT=8888
- DATAPREP_SERVICE_IP=dataprep-redis-service
- DATAPREP_SERVICE_PORT=6007
ipc: host
restart: always

59
ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm.yaml
View File

@@ -20,9 +20,10 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_URL: redis://redis-vector-db:6379
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: ghcr.io/huggingface/tei-gaudi:latest
@@ -42,7 +43,7 @@ services:
HABANA_VISIBLE_DEVICES: all
OMPI_MCA_btl_vader_single_copy_mechanism: none
MAX_WARMUP_SEQUENCE_LENGTH: 512
command: --model-id ${EMBEDDING_MODEL_ID}
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
retriever:
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
container_name: retriever-redis-server
@@ -55,9 +56,11 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_URL: redis://redis-vector-db:6379
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -95,7 +98,7 @@ services:
- SYS_NICE
ipc: host
command: /bin/bash -c "export VLLM_CPU_KVCACHE_SPACE=40 && python3 -m vllm.entrypoints.openai.api_server --enforce-eager --model $LLM_MODEL_ID --tensor-parallel-size 1 --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256 --max-seq_len-to-capture 2048"
chaqna-gaudi-backend-server:
chatqna-gaudi-backend-server:
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-gaudi-backend-server
depends_on:
@@ -110,51 +113,49 @@ services:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- EMBEDDING_SERVER_HOST_IP=${EMBEDDING_SERVER_HOST_IP}
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-8090}
- RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
- RERANK_SERVER_HOST_IP=${RERANK_SERVER_HOST_IP}
- RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-8808}
- LLM_SERVER_HOST_IP=${LLM_SERVER_HOST_IP}
- LLM_SERVER_PORT=${LLM_SERVER_PORT:-8007}
- MEGA_SERVICE_HOST_IP=chatqna-gaudi-backend-server
- EMBEDDING_SERVER_HOST_IP=tei-embedding-service
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80}
- RETRIEVER_SERVICE_HOST_IP=retriever
- RERANK_SERVER_HOST_IP=tei-reranking-service
- RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-80}
- LLM_SERVER_HOST_IP=vllm-service
- LLM_SERVER_PORT=${LLM_SERVER_PORT:-80}
- LOGFLAG=${LOGFLAG}
ipc: host
restart: always
chaqna-gaudi-ui-server:
chatqna-gaudi-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-gaudi-ui-server
depends_on:
- chaqna-gaudi-backend-server
- chatqna-gaudi-backend-server
ports:
- "5173:5173"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
- UPLOAD_FILE_BASE_URL=${DATAPREP_SERVICE_ENDPOINT}
- GET_FILE=${DATAPREP_GET_FILE_ENDPOINT}
- DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
ipc: host
restart: always
chaqna-gaudi-nginx-server:
chatqna-gaudi-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: chaqna-gaudi-nginx-server
container_name: chatqna-gaudi-nginx-server
depends_on:
- chaqna-gaudi-backend-server
- chaqna-gaudi-ui-server
- chatqna-gaudi-backend-server
- chatqna-gaudi-ui-server
ports:
- "${NGINX_PORT:-80}:80"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- FRONTEND_SERVICE_IP=${FRONTEND_SERVICE_IP}
- FRONTEND_SERVICE_PORT=${FRONTEND_SERVICE_PORT}
- BACKEND_SERVICE_NAME=${BACKEND_SERVICE_NAME}
- BACKEND_SERVICE_IP=${BACKEND_SERVICE_IP}
- BACKEND_SERVICE_PORT=${BACKEND_SERVICE_PORT}
- FRONTEND_SERVICE_IP=chatqna-gaudi-ui-server
- FRONTEND_SERVICE_PORT=5173
- BACKEND_SERVICE_NAME=chatqna
- BACKEND_SERVICE_IP=chatqna-gaudi-backend-server
- BACKEND_SERVICE_PORT=8888
- DATAPREP_SERVICE_IP=dataprep-redis-service
- DATAPREP_SERVICE_PORT=6007
ipc: host
restart: always

59
ChatQnA/docker_compose/intel/hpu/gaudi/compose_vllm_ray.yaml
View File

@@ -20,9 +20,10 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_URL: redis://redis-vector-db:6379
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: ghcr.io/huggingface/tei-gaudi:latest
@@ -42,7 +43,7 @@ services:
HABANA_VISIBLE_DEVICES: all
OMPI_MCA_btl_vader_single_copy_mechanism: none
MAX_WARMUP_SEQUENCE_LENGTH: 512
command: --model-id ${EMBEDDING_MODEL_ID}
command: --model-id ${EMBEDDING_MODEL_ID} --auto-truncate
retriever:
image: ${REGISTRY:-opea}/retriever-redis:${TAG:-latest}
container_name: retriever-redis-server
@@ -55,9 +56,11 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_URL: redis://redis-vector-db:6379
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tei-reranking-service:
image: ghcr.io/huggingface/text-embeddings-inference:cpu-1.5
@@ -95,7 +98,7 @@ services:
- SYS_NICE
ipc: host
command: /bin/bash -c "ray start --head && python vllm_ray_openai.py --port_number 8000 --model_id_or_path $LLM_MODEL_ID --tensor_parallel_size 2 --enforce_eager True"
chaqna-gaudi-backend-server:
chatqna-gaudi-backend-server:
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-gaudi-backend-server
depends_on:
@@ -110,51 +113,49 @@ services:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- EMBEDDING_SERVER_HOST_IP=${EMBEDDING_SERVER_HOST_IP}
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-8090}
- RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
- RERANK_SERVER_HOST_IP=${RERANK_SERVER_HOST_IP}
- RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-8808}
- LLM_SERVER_HOST_IP=${LLM_SERVER_HOST_IP}
- LLM_SERVER_PORT=${LLM_SERVER_PORT:-8006}
- MEGA_SERVICE_HOST_IP=chatqna-gaudi-backend-server
- EMBEDDING_SERVER_HOST_IP=tei-embedding-service
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80}
- RETRIEVER_SERVICE_HOST_IP=retriever
- RERANK_SERVER_HOST_IP=tei-reranking-service
- RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-80}
- LLM_SERVER_HOST_IP=vllm-ray-service
- LLM_SERVER_PORT=${LLM_SERVER_PORT:-8000}
- LOGFLAG=${LOGFLAG}
ipc: host
restart: always
chaqna-gaudi-ui-server:
chatqna-gaudi-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-gaudi-ui-server
depends_on:
- chaqna-gaudi-backend-server
- chatqna-gaudi-backend-server
ports:
- "5173:5173"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
- UPLOAD_FILE_BASE_URL=${DATAPREP_SERVICE_ENDPOINT}
- GET_FILE=${DATAPREP_GET_FILE_ENDPOINT}
- DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
ipc: host
restart: always
chaqna-gaudi-nginx-server:
chatqna-gaudi-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: chaqna-gaudi-nginx-server
container_name: chatqna-gaudi-nginx-server
depends_on:
- chaqna-gaudi-backend-server
- chaqna-gaudi-ui-server
- chatqna-gaudi-backend-server
- chatqna-gaudi-ui-server
ports:
- "${NGINX_PORT:-80}:80"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- FRONTEND_SERVICE_IP=${FRONTEND_SERVICE_IP}
- FRONTEND_SERVICE_PORT=${FRONTEND_SERVICE_PORT}
- BACKEND_SERVICE_NAME=${BACKEND_SERVICE_NAME}
- BACKEND_SERVICE_IP=${BACKEND_SERVICE_IP}
- BACKEND_SERVICE_PORT=${BACKEND_SERVICE_PORT}
- FRONTEND_SERVICE_IP=chatqna-gaudi-ui-server
- FRONTEND_SERVICE_PORT=5173
- BACKEND_SERVICE_NAME=chatqna
- BACKEND_SERVICE_IP=chatqna-gaudi-backend-server
- BACKEND_SERVICE_PORT=8888
- DATAPREP_SERVICE_IP=dataprep-redis-service
- DATAPREP_SERVICE_PORT=6007
ipc: host
restart: always

53
ChatQnA/docker_compose/intel/hpu/gaudi/compose_without_rerank.yaml
View File

@@ -20,9 +20,10 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_URL: redis://redis-vector-db:6379
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
TEI_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
tei-embedding-service:
image: ghcr.io/huggingface/tei-gaudi:latest
@@ -57,9 +58,11 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_URL: redis://redis-vector-db:6379
REDIS_HOST: redis-vector-db
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tgi-service:
image: ghcr.io/huggingface/tgi-gaudi:2.0.5
@@ -86,7 +89,7 @@ services:
- SYS_NICE
ipc: host
command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
chaqna-gaudi-backend-server:
chatqna-gaudi-backend-server:
image: ${REGISTRY:-opea}/chatqna-without-rerank:${TAG:-latest}
container_name: chatqna-gaudi-backend-server
depends_on:
@@ -100,49 +103,47 @@ services:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- EMBEDDING_SERVER_HOST_IP=${EMBEDDING_SERVER_HOST_IP}
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-8090}
- RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
- LLM_SERVER_HOST_IP=${LLM_SERVER_HOST_IP}
- LLM_SERVER_PORT=${LLM_SERVER_PORT:-8005}
- MEGA_SERVICE_HOST_IP=chatqna-gaudi-backend-server
- EMBEDDING_SERVER_HOST_IP=tei-embedding-service
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80}
- RETRIEVER_SERVICE_HOST_IP=retriever
- LLM_SERVER_HOST_IP=tgi-service
- LLM_SERVER_PORT=${LLM_SERVER_PORT:-80}
- LOGFLAG=${LOGFLAG}
ipc: host
restart: always
chaqna-gaudi-ui-server:
chatqna-gaudi-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-gaudi-ui-server
depends_on:
- chaqna-gaudi-backend-server
- chatqna-gaudi-backend-server
ports:
- "5173:5173"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- CHAT_BASE_URL=${BACKEND_SERVICE_ENDPOINT}
- UPLOAD_FILE_BASE_URL=${DATAPREP_SERVICE_ENDPOINT}
- GET_FILE=${DATAPREP_GET_FILE_ENDPOINT}
- DELETE_FILE=${DATAPREP_DELETE_FILE_ENDPOINT}
ipc: host
restart: always
chaqna-gaudi-nginx-server:
chatqna-gaudi-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: chaqna-gaudi-nginx-server
container_name: chatqna-gaudi-nginx-server
depends_on:
- chaqna-gaudi-backend-server
- chaqna-gaudi-ui-server
- chatqna-gaudi-backend-server
- chatqna-gaudi-ui-server
ports:
- "${NGINX_PORT:-80}:80"
environment:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- FRONTEND_SERVICE_IP=${FRONTEND_SERVICE_IP}
- FRONTEND_SERVICE_PORT=${FRONTEND_SERVICE_PORT}
- BACKEND_SERVICE_NAME=${BACKEND_SERVICE_NAME}
- BACKEND_SERVICE_IP=${BACKEND_SERVICE_IP}
- BACKEND_SERVICE_PORT=${BACKEND_SERVICE_PORT}
- FRONTEND_SERVICE_IP=chatqna-gaudi-ui-server
- FRONTEND_SERVICE_PORT=5173
- BACKEND_SERVICE_NAME=chatqna
- BACKEND_SERVICE_IP=chatqna-gaudi-backend-server
- BACKEND_SERVICE_PORT=8888
- DATAPREP_SERVICE_IP=dataprep-redis-service
- DATAPREP_SERVICE_PORT=6007
ipc: host
restart: always

16
ChatQnA/docker_compose/intel/hpu/gaudi/set_env.sh
View File

@@ -7,20 +7,4 @@
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:8090"
export REDIS_URL="redis://${host_ip}:6379"
export INDEX_NAME="rag-redis"
export MEGA_SERVICE_HOST_IP=${host_ip}
export EMBEDDING_SERVER_HOST_IP=${host_ip}
export RETRIEVER_SERVICE_HOST_IP=${host_ip}
export RERANK_SERVER_HOST_IP=${host_ip}
export LLM_SERVER_HOST_IP=${host_ip}
export BACKEND_SERVICE_ENDPOINT="http://${host_ip}:8888/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6007/v1/dataprep"
export DATAPREP_GET_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/get_file"
export DATAPREP_DELETE_FILE_ENDPOINT="http://${host_ip}:6007/v1/dataprep/delete_file"
export FRONTEND_SERVICE_IP=${host_ip}
export FRONTEND_SERVICE_PORT=5173
export BACKEND_SERVICE_NAME=chatqna
export BACKEND_SERVICE_IP=${host_ip}
export BACKEND_SERVICE_PORT=8888