Fix wrong endpoint for tei embedding gaudi wrapper (#1043)

* fix doc index retriever embed issue on gaudi

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* align test router with examples

* align readme

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

comps/embeddings/tei/langchain/README.md

@@ -42,7 +42,7 @@ curl localhost:$your_port/v1/embeddings \
 Start the embedding service with the TEI_EMBEDDING_ENDPOINT.
 
 ```bash
-export TEI_EMBEDDING_ENDPOINT="http://localhost:$yourport/v1/embeddings"
+export TEI_EMBEDDING_ENDPOINT="http://localhost:$yourport"
 export TEI_EMBEDDING_MODEL_NAME="BAAI/bge-large-en-v1.5"
 python embedding_tei.py
 ```
@@ -71,7 +71,7 @@ curl localhost:$your_port/embed/v1/embeddings \
 Export the `TEI_EMBEDDING_ENDPOINT` for later usage:
 
 ```bash
-export TEI_EMBEDDING_ENDPOINT="http://localhost:$yourport/v1/embeddings"
+export TEI_EMBEDDING_ENDPOINT="http://localhost:$yourport"
 export TEI_EMBEDDING_MODEL_NAME="BAAI/bge-large-en-v1.5"
 ```
 

comps/embeddings/tei/langchain/embedding_tei.py

@@ -74,7 +74,9 @@ async def aembed_query(request: Dict, async_client: AsyncInferenceClient) -> Uni
 
 def get_async_inference_client(access_token: str) -> AsyncInferenceClient:
     headers = {"Authorization": f"Bearer {access_token}"} if access_token else {}
-    return AsyncInferenceClient(model=TEI_EMBEDDING_ENDPOINT, token=HUGGINGFACEHUB_API_TOKEN, headers=headers)
+    return AsyncInferenceClient(
+        model=f"{TEI_EMBEDDING_ENDPOINT}/v1/embeddings", token=HUGGINGFACEHUB_API_TOKEN, headers=headers
+    )
 
 
 if __name__ == "__main__":

tests/embeddings/test_embeddings_tei_langchain.sh

@@ -24,7 +24,7 @@ function start_service() {
     model="BAAI/bge-base-en-v1.5"
     unset http_proxy
     docker run -d --name="test-comps-embedding-tei-endpoint" -p $tei_endpoint:80 -v ./data:/data --pull always ghcr.io/huggingface/text-embeddings-inference:cpu-1.5 --model-id $model
-    export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:${tei_endpoint}/v1/embeddings"
+    export TEI_EMBEDDING_ENDPOINT="http://${ip_address}:${tei_endpoint}"
     tei_service_port=5002
     docker run -d --name="test-comps-embedding-tei-server" -e LOGFLAG=True -e http_proxy=$http_proxy -e https_proxy=$https_proxy -p ${tei_service_port}:6000 --ipc=host -e TEI_EMBEDDING_ENDPOINT=$TEI_EMBEDDING_ENDPOINT  opea/embedding-tei:comps
     sleep 3m