jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 5 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

8
ChatQnA/chatqna.py
View File

@@ -38,15 +38,15 @@ If you don't know the answer to a question, please don't share false information
MEGA_SERVICE_HOST_IP = os.getenv("MEGA_SERVICE_HOST_IP", "0.0.0.0")
MEGA_SERVICE_PORT = int(os.getenv("MEGA_SERVICE_PORT", 8888))
GUARDRAIL_SERVICE_HOST_IP = os.getenv("GUARDRAIL_SERVICE_HOST_IP", "0.0.0.0")
GUARDRAIL_SERVICE_PORT = int(os.getenv("GUARDRAIL_SERVICE_PORT", 9090))
GUARDRAIL_SERVICE_PORT = int(os.getenv("GUARDRAIL_SERVICE_PORT", 80))
EMBEDDING_SERVER_HOST_IP = os.getenv("EMBEDDING_SERVER_HOST_IP", "0.0.0.0")
EMBEDDING_SERVER_PORT = int(os.getenv("EMBEDDING_SERVER_PORT", 6006))
EMBEDDING_SERVER_PORT = int(os.getenv("EMBEDDING_SERVER_PORT", 80))
RETRIEVER_SERVICE_HOST_IP = os.getenv("RETRIEVER_SERVICE_HOST_IP", "0.0.0.0")
RETRIEVER_SERVICE_PORT = int(os.getenv("RETRIEVER_SERVICE_PORT", 7000))
RERANK_SERVER_HOST_IP = os.getenv("RERANK_SERVER_HOST_IP", "0.0.0.0")
RERANK_SERVER_PORT = int(os.getenv("RERANK_SERVER_PORT", 8808))
RERANK_SERVER_PORT = int(os.getenv("RERANK_SERVER_PORT", 80))
LLM_SERVER_HOST_IP = os.getenv("LLM_SERVER_HOST_IP", "0.0.0.0")
LLM_SERVER_PORT = int(os.getenv("LLM_SERVER_PORT", 9009))
LLM_SERVER_PORT = int(os.getenv("LLM_SERVER_PORT", 80))
def align_inputs(self, inputs, cur_node, runtime_graph, llm_parameters_dict, **kwargs):

93
ChatQnA/docker_compose/intel/cpu/aipc/README.md
View File

@@ -61,7 +61,7 @@ Run the command to download LLM models. The <host_ip> is the one set in [Ollama
```
export host_ip=<host_ip>
export OLLAMA_HOST=http://${host_ip}:11434
ollama pull llama3
ollama pull llama3.2
```
After downloaded the models, you can list the models by `ollama list`.
@@ -70,7 +70,7 @@ The output should be similar to the following:
```
NAME ID SIZE MODIFIED
llama3:latest 365c0bd3c000 4.7 GB 5 days ago
llama3.2:latest a80c4f17acd5 2.0 GB 2 minutes ago
```
### Consume Ollama LLM Service
@@ -78,25 +78,25 @@ llama3:latest 365c0bd3c000 4.7 GB 5 days ago
Access ollama service to verify that the ollama is functioning correctly.
```bash
curl http://${host_ip}:11434/api/generate -d '{"model": "llama3", "prompt":"What is Deep Learning?"}'
curl http://${host_ip}:11434/api/generate -d '{"model": "llama3.2", "prompt":"What is Deep Learning?"}'
```
The outputs are similar to these:
```
{"model":"llama3","created_at":"2024-10-11T07:58:38.949268562Z","response":"Deep","done":false}
{"model":"llama3","created_at":"2024-10-11T07:58:39.017625351Z","response":" learning","done":false}
{"model":"llama3","created_at":"2024-10-11T07:58:39.102848076Z","response":" is","done":false}
{"model":"llama3","created_at":"2024-10-11T07:58:39.171037991Z","response":" a","done":false}
{"model":"llama3","created_at":"2024-10-11T07:58:39.243757952Z","response":" subset","done":false}
{"model":"llama3","created_at":"2024-10-11T07:58:39.328708084Z","response":" of","done":false}
{"model":"llama3","created_at":"2024-10-11T07:58:39.413844974Z","response":" machine","done":false}
{"model":"llama3","created_at":"2024-10-11T07:58:39.486239329Z","response":" learning","done":false}
{"model":"llama3","created_at":"2024-10-11T07:58:39.555960842Z","response":" that","done":false}
{"model":"llama3","created_at":"2024-10-11T07:58:39.642418238Z","response":" involves","done":false}
{"model":"llama3","created_at":"2024-10-11T07:58:39.714137478Z","response":" the","done":false}
{"model":"llama3","created_at":"2024-10-11T07:58:39.798776679Z","response":" use","done":false}
{"model":"llama3","created_at":"2024-10-11T07:58:39.883747938Z","response":" of","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.098813868Z","response":"Deep","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.124514468Z","response":" learning","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.149754216Z","response":" is","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.180420784Z","response":" a","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.229185873Z","response":" subset","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.263956118Z","response":" of","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.289097354Z","response":" machine","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.316838918Z","response":" learning","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.342309506Z","response":" that","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.367221264Z","response":" involves","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.39205893Z","response":" the","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.417933974Z","response":" use","done":false}
{"model":"llama3.2","created_at":"2024-10-12T12:55:28.443110388Z","response":" of","done":false}
...
```
@@ -155,13 +155,21 @@ cd ~/OPEA/GenAIExamples/ChatQnA/ui
docker build --no-cache -t opea/chatqna-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile .
```
Then run the command `docker images`, you will have the following 5 Docker Images:
### 6. Build Nginx Docker Image
```bash
cd GenAIComps
docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/nginx/Dockerfile .
```
Then run the command `docker images`, you will have the following 6 Docker Images:
1. `opea/dataprep-redis:latest`
2. `opea/retriever-redis:latest`
3. `opea/llm-ollama:latest`
4. `opea/chatqna:latest`
5. `opea/chatqna-ui:latest`
6. `opea/nginx:latest`
## 🚀 Start Microservices
@@ -201,27 +209,10 @@ export http_proxy=${your_http_proxy}
export https_proxy=${your_http_proxy}
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
export REDIS_URL="redis://${host_ip}:6379"
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
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=${host_ip}
export BACKEND_SERVICE_PORT=8888
export OLLAMA_ENDPOINT=http://${host_ip}:11434
export OLLAMA_MODEL="llama3"
export OLLAMA_MODEL="llama3.2"
```
- Windows PC
@@ -229,27 +220,10 @@ export OLLAMA_MODEL="llama3"
```bash
set EMBEDDING_MODEL_ID=BAAI/bge-base-en-v1.5
set RERANK_MODEL_ID=BAAI/bge-reranker-base
set TEI_EMBEDDING_ENDPOINT=http://%host_ip%:6006
set REDIS_URL=redis://%host_ip%:6379
set INDEX_NAME=rag-redis
set HUGGINGFACEHUB_API_TOKEN=%your_hf_api_token%
set MEGA_SERVICE_HOST_IP=%host_ip%
set EMBEDDING_SERVER_HOST_IP=%host_ip%
set RETRIEVER_SERVICE_HOST_IP=%host_ip%
set RERANK_SERVER_HOST_IP=%host_ip%
set LLM_SERVER_HOST_IP=%host_ip%
set BACKEND_SERVICE_ENDPOINT=http://%host_ip%:8888/v1/chatqna
set DATAPREP_SERVICE_ENDPOINT=http://%host_ip%:6007/v1/dataprep
set DATAPREP_GET_FILE_ENDPOINT="http://%host_ip%:6007/v1/dataprep/get_file"
set DATAPREP_DELETE_FILE_ENDPOINT="http://%host_ip%:6007/v1/dataprep/delete_file"
set FRONTEND_SERVICE_IP=%host_ip%
set FRONTEND_SERVICE_PORT=5173
set BACKEND_SERVICE_NAME=chatqna
set BACKEND_SERVICE_IP=%host_ip%
set BACKEND_SERVICE_PORT=8888
set OLLAMA_ENDPOINT=http://host.docker.internal:11434
set OLLAMA_MODEL="llama3"
set OLLAMA_MODEL="llama3.2"
```
Note: Please replace with `host_ip` with you external IP address, do not use localhost.
@@ -263,15 +237,6 @@ cd ~/OPEA/GenAIExamples/ChatQnA/docker_compose/intel/cpu/aipc/
docker compose up -d
```
Let ollama service runs (if you have started ollama service in [Prerequisites](#Prerequisites), skip this step)
```bash
# e.g. ollama run llama3
OLLAMA_HOST=${host_ip}:11434 ollama run $OLLAMA_MODEL
# for windows
# ollama run %OLLAMA_MODEL%
```
### Validate Microservices
Follow the instructions to validate MicroServices.
@@ -309,7 +274,7 @@ For details on how to verify the correctness of the response, refer to [how-to-v
4. Ollama Service
```bash
curl http://${host_ip}:11434/api/generate -d '{"model": "llama3", "prompt":"What is Deep Learning?"}'
curl http://${host_ip}:11434/api/generate -d '{"model": "llama3.2", "prompt":"What is Deep Learning?"}'
```
5. LLM Microservice
@@ -325,7 +290,7 @@ For details on how to verify the correctness of the response, refer to [how-to-v
```bash
curl http://${host_ip}:8888/v1/chatqna -H "Content-Type: application/json" -d '{
"messages": "What is the revenue of Nike in 2023?", "model": "'"${OLLAMA_MODEL}"'"
"messages": "What is the revenue of Nike in 2023?"
}'
```

45
ChatQnA/docker_compose/intel/cpu/aipc/compose.yaml
View File

@@ -13,15 +13,17 @@ services:
container_name: dataprep-redis-server
depends_on:
- redis-vector-db
- tei-embedding-service
ports:
- "6007:6007"
environment:
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/text-embeddings-inference:cpu-1.5
@@ -48,9 +50,10 @@ 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_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:
@@ -79,7 +82,6 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
@@ -90,6 +92,7 @@ services:
container_name: chatqna-aipc-backend-server
depends_on:
- redis-vector-db
- dataprep-redis-service
- tei-embedding-service
- retriever
- tei-reranking-service
@@ -100,14 +103,14 @@ services:
- no_proxy=${no_proxy}
- https_proxy=${https_proxy}
- http_proxy=${http_proxy}
- MEGA_SERVICE_HOST_IP=${MEGA_SERVICE_HOST_IP}
- EMBEDDING_SERVER_HOST_IP=${EMBEDDING_SERVICE_HOST_IP}
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVICE_PORT:-6006}
- RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
- RERANK_SERVER_HOST_IP=${RERANK_SERVICE_HOST_IP}
- RERANK_SERVER_PORT=${RERANK_SERVICE_PORT:-8808}
- LLM_SERVER_HOST_IP=${LLM_SERVICE_HOST_IP}
- LLM_SERVER_PORT=${LLM_SERVICE_PORT:-9000}
- MEGA_SERVICE_HOST_IP=chaqna-aipc-backend-server
- EMBEDDING_SERVER_HOST_IP=tei-embedding-service
- EMBEDDING_SERVER_PORT=80
- RETRIEVER_SERVICE_HOST_IP=retriever
- RERANK_SERVER_HOST_IP=tei-reranking-service
- RERANK_SERVER_PORT=80
- LLM_SERVER_HOST_IP=llm
- LLM_SERVER_PORT=9000
- LOGFLAG=${LOGFLAG}
ipc: host
restart: always
@@ -122,10 +125,6 @@ services:
- no_proxy=${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-aipc-nginx-server:
@@ -140,11 +139,13 @@ services:
- 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-xeon-ui-server
- FRONTEND_SERVICE_PORT=5173
- BACKEND_SERVICE_NAME=chatqna
- BACKEND_SERVICE_IP=chatqna-xeon-backend-server
- BACKEND_SERVICE_PORT=8888
- DATAPREP_SERVICE_IP=dataprep-redis-service
- DATAPREP_SERVICE_PORT=6007
ipc: host
restart: always

21
ChatQnA/docker_compose/intel/cpu/aipc/set_env.sh
View File

@@ -15,25 +15,6 @@ fi
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006"
export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808"
export REDIS_URL="redis://${host_ip}:6379"
export INDEX_NAME="rag-redis"
export REDIS_HOST=${host_ip}
export MEGA_SERVICE_HOST_IP=${host_ip}
export EMBEDDING_SERVICE_HOST_IP=${host_ip}
export RETRIEVER_SERVICE_HOST_IP=${host_ip}
export RERANK_SERVICE_HOST_IP=${host_ip}
export LLM_SERVICE_HOST_IP=${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
export OLLAMA_ENDPOINT=http://${host_ip}:11434
export OLLAMA_MODEL="llama3"
export OLLAMA_MODEL="llama3.2"

21
ChatQnA/docker_compose/intel/cpu/xeon/README_qdrant.md
View File

@@ -118,12 +118,20 @@ docker build --no-cache -t opea/chatqna-conversation-ui:latest --build-arg https
cd ../../../..
```
Then run the command `docker images`, you will have the following 4 Docker Images:
### 6. Build Nginx Docker Image
```bash
cd GenAIComps
docker build -t opea/nginx:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/nginx/Dockerfile .
```
Then run the command `docker images`, you will have the following 5 Docker Images:
1. `opea/dataprep-qdrant:latest`
2. `opea/retriever-qdrant:latest`
3. `opea/chatqna:latest`
4. `opea/chatqna-ui:latest`
5. `opea/nginx:latest`
## 🚀 Start Microservices
@@ -172,18 +180,7 @@ export https_proxy=${your_http_proxy}
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export RERANK_MODEL_ID="BAAI/bge-reranker-base"
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6040"
export QDRANT_HOST=${host_ip}
export QDRANT_PORT=6333
export INDEX_NAME="rag-qdrant"
export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
export EMBEDDING_SERVER_HOST_IP=${host_ip}
export MEGA_SERVICE_HOST_IP=${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}:8912/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${host_ip}:6043/v1/dataprep"
```
Note: Please replace with `host_ip` with you external IP address, do not use localhost.

57
ChatQnA/docker_compose/intel/cpu/xeon/compose.yaml
View File

@@ -20,10 +20,10 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_HOST: ${REDIS_HOST}
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/text-embeddings-inference:cpu-1.5
@@ -50,9 +50,10 @@ 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_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:
@@ -87,7 +88,7 @@ services:
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
chaqna-xeon-backend-server:
chatqna-xeon-backend-server:
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-xeon-backend-server
depends_on:
@@ -103,51 +104,49 @@ 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:-6006}
- 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=${LLM_SERVER_PORT:-9009}
- MEGA_SERVICE_HOST_IP=chatqna-xeon-backend-server
- EMBEDDING_SERVER_HOST_IP=tei-embedding-service
- EMBEDDING_SERVER_PORT=${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-xeon-ui-server:
chatqna-xeon-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-xeon-ui-server
depends_on:
- chaqna-xeon-backend-server
- chatqna-xeon-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-xeon-nginx-server:
chatqna-xeon-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: chaqna-xeon-nginx-server
container_name: chatqna-xeon-nginx-server
depends_on:
- chaqna-xeon-backend-server
- chaqna-xeon-ui-server
- chatqna-xeon-backend-server
- chatqna-xeon-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-xeon-ui-server
- FRONTEND_SERVICE_PORT=5173
- BACKEND_SERVICE_NAME=chatqna
- BACKEND_SERVICE_IP=chatqna-xeon-backend-server
- BACKEND_SERVICE_PORT=8888
- DATAPREP_SERVICE_IP=dataprep-redis-service
- DATAPREP_SERVICE_PORT=6007
ipc: host
restart: always

54
ChatQnA/docker_compose/intel/cpu/xeon/compose_qdrant.yaml
View File

@@ -20,10 +20,10 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
QDRANT_HOST: ${QDRANT_HOST}
QDRANT_HOST: qdrant-vector-db
QDRANT_PORT: 6333
COLLECTION_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/text-embeddings-inference:cpu-1.5
@@ -50,7 +50,7 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
QDRANT_HOST: ${QDRANT_HOST}
QDRANT_HOST: qdrant-vector-db
QDRANT_PORT: 6333
INDEX_NAME: ${INDEX_NAME}
TEI_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
@@ -87,7 +87,7 @@ services:
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
chaqna-xeon-backend-server:
chatqna-xeon-backend-server:
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-xeon-backend-server
depends_on:
@@ -102,52 +102,50 @@ 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:-6040}
- RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
- RETRIEVER_SERVICE_PORT=${RETRIEVER_SERVICE_PORT:-6045}
- RERANK_SERVER_HOST_IP=${RERANK_SERVER_HOST_IP}
- RERANK_SERVER_PORT=${RERANK_SERVER_PORT:-6041}
- LLM_SERVER_HOST_IP=${LLM_SERVER_HOST_IP}
- LLM_SERVER_PORT=${LLM_SERVER_PORT:-6042}
- MEGA_SERVICE_HOST_IP=chatqna-xeon-backend-server
- EMBEDDING_SERVER_HOST_IP=tei-embedding-service
- EMBEDDING_SERVER_PORT=${EMBEDDING_SERVER_PORT:-80}
- RETRIEVER_SERVICE_HOST_IP=retriever
- RETRIEVER_SERVICE_PORT=${RETRIEVER_SERVICE_PORT:-7000}
- 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-xeon-ui-server:
chatqna-xeon-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-xeon-ui-server
depends_on:
- chaqna-xeon-backend-server
- chatqna-xeon-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-xeon-nginx-server:
chatqna-xeon-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: chaqna-xeon-nginx-server
container_name: chatqna-xeon-nginx-server
depends_on:
- chaqna-xeon-backend-server
- chaqna-xeon-ui-server
- chatqna-xeon-backend-server
- chatqna-xeon-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-xeon-ui-server
- FRONTEND_SERVICE_PORT=5173
- BACKEND_SERVICE_NAME=chatqna
- BACKEND_SERVICE_IP=chatqna-xeon-backend-server
- BACKEND_SERVICE_PORT=8888
- DATAPREP_SERVICE_IP=dataprep-qdrant-service
- DATAPREP_SERVICE_PORT=6007
ipc: host
restart: always

59
ChatQnA/docker_compose/intel/cpu/xeon/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/text-embeddings-inference:cpu-1.5
@@ -49,12 +50,10 @@ 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_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
LANGCHAIN_API_KEY: ${LANGCHAIN_API_KEY}
LANGCHAIN_TRACING_V2: ${LANGCHAIN_TRACING_V2}
LANGCHAIN_PROJECT: "opea-retriever-service"
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tei-reranking-service:
@@ -88,7 +87,7 @@ services:
HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
LLM_MODEL_ID: ${LLM_MODEL_ID}
command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80
chaqna-xeon-backend-server:
chatqna-xeon-backend-server:
image: ${REGISTRY:-opea}/chatqna:${TAG:-latest}
container_name: chatqna-xeon-backend-server
depends_on:
@@ -103,51 +102,49 @@ 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:-6006}
- 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=${LLM_SERVER_PORT:-9009}
- MEGA_SERVICE_HOST_IP=chatqna-xeon-backend-server
- EMBEDDING_SERVER_HOST_IP=tei-embedding-service
- EMBEDDING_SERVER_PORT=${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-xeon-ui-server:
chatqna-xeon-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-xeon-ui-server
depends_on:
- chaqna-xeon-backend-server
- chatqna-xeon-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-xeon-nginx-server:
chatqna-xeon-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: chaqna-xeon-nginx-server
container_name: chatqna-xeon-nginx-server
depends_on:
- chaqna-xeon-backend-server
- chaqna-xeon-ui-server
- chatqna-xeon-backend-server
- chatqna-xeon-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-xeon-ui-server
- FRONTEND_SERVICE_PORT=5173
- BACKEND_SERVICE_NAME=chatqna
- BACKEND_SERVICE_IP=chatqna-xeon-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/cpu/xeon/compose_without_rerank.yaml
View File

@@ -20,10 +20,10 @@ services:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
REDIS_URL: ${REDIS_URL}
REDIS_HOST: ${REDIS_HOST}
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/text-embeddings-inference:cpu-1.5
@@ -50,9 +50,10 @@ 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_EMBEDDING_ENDPOINT: ${TEI_EMBEDDING_ENDPOINT}
TEI_EMBEDDING_ENDPOINT: http://tei-embedding-service:80
HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
restart: unless-stopped
tgi-service:
@@ -71,7 +72,7 @@ services:
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
chaqna-xeon-backend-server:
chatqna-xeon-backend-server:
image: ${REGISTRY:-opea}/chatqna-without-rerank:${TAG:-latest}
container_name: chatqna-xeon-backend-server
depends_on:
@@ -86,49 +87,47 @@ 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:-6006}
- RETRIEVER_SERVICE_HOST_IP=${RETRIEVER_SERVICE_HOST_IP}
- LLM_SERVER_HOST_IP=${LLM_SERVER_HOST_IP}
- LLM_SERVER_PORT=${LLM_SERVER_PORT:-9009}
- MEGA_SERVICE_HOST_IP=chatqna-xeon-backend-server
- EMBEDDING_SERVER_HOST_IP=tei-embedding-service
- EMBEDDING_SERVER_PORT=${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-xeon-ui-server:
chatqna-xeon-ui-server:
image: ${REGISTRY:-opea}/chatqna-ui:${TAG:-latest}
container_name: chatqna-xeon-ui-server
depends_on:
- chaqna-xeon-backend-server
- chatqna-xeon-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-xeon-nginx-server:
chatqna-xeon-nginx-server:
image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
container_name: chaqna-xeon-nginx-server
container_name: chatqna-xeon-nginx-server
depends_on:
- chaqna-xeon-backend-server
- chaqna-xeon-ui-server
- chatqna-xeon-backend-server
- chatqna-xeon-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-xeon-ui-server
- FRONTEND_SERVICE_PORT=5173
- BACKEND_SERVICE_NAME=chatqna
- BACKEND_SERVICE_IP=chatqna-xeon-backend-server
- BACKEND_SERVICE_PORT=8888
- DATAPREP_SERVICE_IP=dataprep-redis-service
- DATAPREP_SERVICE_PORT=6007
ipc: host
restart: always

17
ChatQnA/docker_compose/intel/cpu/xeon/set_env.sh
View File

@@ -7,21 +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://${host_ip}:6006"
export REDIS_URL="redis://${host_ip}:6379"
export INDEX_NAME="rag-redis"
export REDIS_HOST=${host_ip}
export MEGA_SERVICE_HOST_IP=${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

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

18
ChatQnA/tests/test_compose_guardrails_on_gaudi.sh
View File

@@ -34,27 +34,9 @@ function start_services() {
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://${ip_address}:8090"
export REDIS_URL="redis://${ip_address}:6379"
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${ip_address}
export EMBEDDING_SERVER_HOST_IP=${ip_address}
export RETRIEVER_SERVICE_HOST_IP=${ip_address}
export RERANK_SERVER_HOST_IP=${ip_address}
export LLM_SERVER_HOST_IP=${ip_address}
export GUARDRAIL_SERVICE_HOST_IP=${ip_address}
export EMBEDDING_SERVER_PORT=8090
export RERANK_SERVER_PORT=8808
export LLM_SERVER_PORT=8008
export GUARDRAIL_SERVICE_PORT=9090
export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
export GURADRAILS_MODEL_ID="meta-llama/Meta-Llama-Guard-2-8B"
export SAFETY_GUARD_MODEL_ID="meta-llama/Meta-Llama-Guard-2-8B"
export SAFETY_GUARD_ENDPOINT="http://${ip_address}:8088"
sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
# Start Docker Containers
docker compose -f compose_guardrails.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

19
ChatQnA/tests/test_compose_on_gaudi.sh
View File

@@ -34,27 +34,8 @@ function start_services() {
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"
export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:8090"
export TEI_RERANKING_ENDPOINT="http://${ip_address}:8808"
export TGI_LLM_ENDPOINT="http://${ip_address}:8005"
export REDIS_URL="redis://${ip_address}:6379"
export REDIS_HOST=${ip_address}
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${ip_address}
export EMBEDDING_SERVER_HOST_IP=${ip_address}
export RETRIEVER_SERVICE_HOST_IP=${ip_address}
export RERANK_SERVER_HOST_IP=${ip_address}
export LLM_SERVER_HOST_IP=${ip_address}
export EMBEDDING_SERVER_PORT=8090
export RERANK_SERVER_PORT=8808
export LLM_SERVER_PORT=8005
export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
export DATAPREP_GET_FILE_ENDPOINT="http://${ip_address}:6008/v1/dataprep/get_file"
export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:6009/v1/dataprep/delete_file"
sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
# Start Docker Containers
docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

17
ChatQnA/tests/test_compose_on_xeon.sh
View File

@@ -34,25 +34,8 @@ function start_services() {
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"
export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:6006"
export REDIS_URL="redis://${ip_address}:6379"
export REDIS_HOST=${ip_address}
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${ip_address}
export EMBEDDING_SERVER_HOST_IP=${ip_address}
export RETRIEVER_SERVICE_HOST_IP=${ip_address}
export RERANK_SERVER_HOST_IP=${ip_address}
export LLM_SERVER_HOST_IP=${ip_address}
export EMBEDDING_SERVER_PORT=6006
export RERANK_SERVER_PORT=8808
export LLM_SERVER_PORT=9009
export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
export DATAPREP_GET_FILE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/get_file"
export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/delete_file"
sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
# Start Docker Containers
docker compose -f compose.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

15
ChatQnA/tests/test_compose_qdrant_on_xeon.sh
View File

@@ -31,23 +31,8 @@ function start_services() {
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://${ip_address}:6040"
export QDRANT_HOST=${ip_address}
export QDRANT_PORT=6333
export INDEX_NAME="rag-qdrant"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${ip_address}
export EMBEDDING_SERVER_HOST_IP=${ip_address}
export RETRIEVER_SERVICE_HOST_IP=${ip_address}
export RERANK_SERVER_HOST_IP=${ip_address}
export LLM_SERVER_HOST_IP=${ip_address}
export MEGA_SERVICE_PORT=8912
export EMBEDDING_SERVER_PORT=6040
export RETRIEVER_SERVICE_PORT=6045
export RERANK_SERVER_PORT=6041
export LLM_SERVER_PORT=6042
export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8912/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6043/v1/dataprep"
sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env

14
ChatQnA/tests/test_compose_vllm_on_gaudi.sh
View File

@@ -32,22 +32,8 @@ function start_services() {
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://${ip_address}:8090"
export REDIS_URL="redis://${ip_address}:6379"
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${ip_address}
export EMBEDDING_SERVER_HOST_IP=${ip_address}
export RETRIEVER_SERVICE_HOST_IP=${ip_address}
export RERANK_SERVER_HOST_IP=${ip_address}
export LLM_SERVER_HOST_IP=${ip_address}
export EMBEDDING_SERVER_PORT=8090
export RERANK_SERVER_PORT=8808
export LLM_SERVER_PORT=8007
export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
# Start Docker Containers
docker compose -f compose_vllm.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

16
ChatQnA/tests/test_compose_vllm_on_xeon.sh
View File

@@ -35,22 +35,8 @@ function start_services() {
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://${ip_address}:6006"
export REDIS_URL="redis://${ip_address}:6379"
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${ip_address}
export EMBEDDING_SERVER_HOST_IP=${ip_address}
export RETRIEVER_SERVICE_HOST_IP=${ip_address}
export RERANK_SERVER_HOST_IP=${ip_address}
export LLM_SERVER_HOST_IP=${ip_address}
export EMBEDDING_SERVER_PORT=6006
export RERANK_SERVER_PORT=8808
export LLM_SERVER_PORT=9009
export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
# Start Docker Containers
docker compose -f compose_vllm.yaml up -d > ${LOG_PATH}/start_services_with_compose.log
@@ -192,7 +178,7 @@ function main() {
elif [ "${mode}" == "" ]; then
validate_microservices
validate_megaservice
#validate_frontend
# validate_frontend
fi
stop_docker

14
ChatQnA/tests/test_compose_vllm_ray_on_gaudi.sh
View File

@@ -33,22 +33,8 @@ function start_services() {
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://${ip_address}:8090"
export REDIS_URL="redis://${ip_address}:6379"
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${ip_address}
export EMBEDDING_SERVER_HOST_IP=${ip_address}
export RETRIEVER_SERVICE_HOST_IP=${ip_address}
export RERANK_SERVER_HOST_IP=${ip_address}
export LLM_SERVER_HOST_IP=${ip_address}
export EMBEDDING_SERVER_PORT=8090
export RERANK_SERVER_PORT=8808
export LLM_SERVER_PORT=8006
export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
# Start Docker Containers
docker compose -f compose_vllm_ray.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

15
ChatQnA/tests/test_compose_without_rerank_on_gaudi.sh
View File

@@ -33,23 +33,8 @@ function start_services() {
cd $WORKPATH/docker_compose/intel/hpu/gaudi
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:8090"
export REDIS_URL="redis://${ip_address}:6379"
export REDIS_HOST=${ip_address}
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${ip_address}
export EMBEDDING_SERVER_HOST_IP=${ip_address}
export RETRIEVER_SERVICE_HOST_IP=${ip_address}
export LLM_SERVER_HOST_IP=${ip_address}
export EMBEDDING_SERVER_PORT=8090
export LLM_SERVER_PORT=8005
export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
export DATAPREP_GET_FILE_ENDPOINT="http://${ip_address}:6008/v1/dataprep/get_file"
export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:6009/v1/dataprep/delete_file"
sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
# Start Docker Containers
docker compose -f compose_without_rerank.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

15
ChatQnA/tests/test_compose_without_rerank_on_xeon.sh
View File

@@ -33,23 +33,8 @@ function start_services() {
export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5"
export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3"
export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:6006"
export REDIS_URL="redis://${ip_address}:6379"
export REDIS_HOST=${ip_address}
export INDEX_NAME="rag-redis"
export HUGGINGFACEHUB_API_TOKEN=${HUGGINGFACEHUB_API_TOKEN}
export MEGA_SERVICE_HOST_IP=${ip_address}
export EMBEDDING_SERVER_HOST_IP=${ip_address}
export RETRIEVER_SERVICE_HOST_IP=${ip_address}
export LLM_SERVER_HOST_IP=${ip_address}
export EMBEDDING_SERVER_PORT=6006
export LLM_SERVER_PORT=9009
export BACKEND_SERVICE_ENDPOINT="http://${ip_address}:8888/v1/chatqna"
export DATAPREP_SERVICE_ENDPOINT="http://${ip_address}:6007/v1/dataprep"
export DATAPREP_GET_FILE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/get_file"
export DATAPREP_DELETE_FILE_ENDPOINT="http://${ip_address}:6007/v1/dataprep/delete_file"
sed -i "s/backend_address/$ip_address/g" $WORKPATH/ui/svelte/.env
# Start Docker Containers
docker compose -f compose_without_rerank.yaml up -d > ${LOG_PATH}/start_services_with_compose.log

2
ChatQnA/ui/svelte/playwright.config.ts
View File

@@ -38,7 +38,7 @@ export default defineConfig({
/* Maximum time each action such as `click()` can take. Defaults to 0 (no limit). */
actionTimeout: 0,
/* Base URL to use in actions like `await page.goto('/')`. */
baseURL: "http://localhost:5173",
baseURL: "http://localhost:80",
/* Collect trace when retrying the failed test. See https://playwright.dev/docs/trace-viewer */
trace: "on-first-retry",