update tgi version (#378)

* try with tgi-gaudi:2.0.0

Signed-off-by: chensuyue <[email protected]>

* try with text-generation-inference:2.1.0

Signed-off-by: chensuyue <[email protected]>

* add params for tgi-gaudi:2.0.0

Signed-off-by: chensuyue <[email protected]>

---------

Signed-off-by: chensuyue <[email protected]>

Author: chensuyue

ChatQnA/docker/gaudi/docker_compose.yaml

@@ -114,7 +114,7 @@ services:
       LANGCHAIN_PROJECT: "opea-reranking-service"
     restart: unless-stopped
   tgi-service:
-    image: ghcr.io/huggingface/tgi-gaudi:1.2.1
+    image: ghcr.io/huggingface/tgi-gaudi:2.0.0
     container_name: tgi-gaudi-server
     ports:
       - "8008:80"
@@ -133,7 +133,7 @@ services:
     cap_add:
       - SYS_NICE
     ipc: host
-    command: --model-id ${LLM_MODEL_ID}
+    command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
   llm:
     image: opea/llm-tgi:latest
     container_name: llm-tgi-gaudi-server

ChatQnA/docker/xeon/docker_compose.yaml

@@ -110,7 +110,7 @@ services:
       LANGCHAIN_PROJECT: "opea-reranking-service"
     restart: unless-stopped
   tgi_service:
-    image: ghcr.io/huggingface/text-generation-inference:1.4
+    image: ghcr.io/huggingface/text-generation-inference:2.1.0
     container_name: tgi-service
     ports:
       - "9009:80"

ChatQnA/tests/test_chatqna_on_gaudi.sh

@@ -25,7 +25,7 @@ function build_docker_images() {
     cd tei-gaudi/
     docker build --no-cache -f Dockerfile-hpu -t opea/tei-gaudi:latest .
 
-    docker pull ghcr.io/huggingface/tgi-gaudi:1.2.1
+    docker pull ghcr.io/huggingface/tgi-gaudi:2.0.0
     docker pull ghcr.io/huggingface/text-embeddings-inference:cpu-1.2
 
     cd $WORKPATH/docker