Rename embedding microservice and fix typos (#224)

* add preload env in run.sh

Signed-off-by: lvliang-intel <[email protected]>

* make tei ms generic for both cpu and hpu

Signed-off-by: lvliang-intel <[email protected]>

---------

Signed-off-by: lvliang-intel <[email protected]>

Author: lvliang-intel

comps/embeddings/README.md

@@ -69,7 +69,7 @@ export TEI_EMBEDDING_MODEL_NAME="BAAI/bge-large-en-v1.5"
 export LANGCHAIN_TRACING_V2=true
 export LANGCHAIN_API_KEY=${your_langchain_api_key}
 export LANGCHAIN_PROJECT="opea/gen-ai-comps:embeddings"
-python embedding_tei_gaudi.py
+python embedding_tei.py
 ```
 
 ### Start Embedding Service with Local Model

comps/embeddings/langchain/docker/Dockerfile

@@ -24,5 +24,5 @@ ENV PYTHONPATH=$PYTHONPATH:/home/user
 
 WORKDIR /home/user/comps/embeddings/langchain
 
-ENTRYPOINT ["python", "embedding_tei_gaudi.py"]
+ENTRYPOINT ["python", "embedding_tei.py"]
 

comps/embeddings/langchain/embedding_tei_gaudi.py renamed to comps/embeddings/langchain/embedding_tei.py

@@ -19,7 +19,7 @@
 
 
 @register_microservice(
-    name="opea_service@embedding_tgi_gaudi",
+    name="opea_service@embedding_tei_langchain",
     service_type=ServiceType.EMBEDDING,
     endpoint="/v1/embeddings",
     host="0.0.0.0",
@@ -28,18 +28,18 @@
     output_datatype=EmbedDoc768,
 )
 @traceable(run_type="embedding")
-@register_statistics(names=["opea_service@embedding_tgi_gaudi"])
+@register_statistics(names=["opea_service@embedding_tei_langchain"])
 def embedding(input: TextDoc) -> EmbedDoc768:
     start = time.time()
     embed_vector = embeddings.embed_query(input.text)
     embed_vector = embed_vector[:768]  # Keep only the first 768 elements
     res = EmbedDoc768(text=input.text, embedding=embed_vector)
-    statistics_dict["opea_service@embedding_tgi_gaudi"].append_latency(time.time() - start, None)
+    statistics_dict["opea_service@embedding_tei_langchain"].append_latency(time.time() - start, None)
     return res
 
 
 if __name__ == "__main__":
     tei_embedding_endpoint = os.getenv("TEI_EMBEDDING_ENDPOINT", "http://localhost:8080")
     embeddings = HuggingFaceHubEmbeddings(model=tei_embedding_endpoint)
     print("TEI Gaudi Embedding initialized.")
-    opea_microservices["opea_service@embedding_tgi_gaudi"].start()
+    opea_microservices["opea_service@embedding_tei_langchain"].start()

comps/embeddings/llama_index/docker/Dockerfile

@@ -26,5 +26,5 @@ ENV PYTHONPATH=$PYTHONPATH:/home/user
 
 WORKDIR /home/user/comps/embeddings/llama_index
 
-ENTRYPOINT ["python3", "embedding_tei_gaudi.py"]
+ENTRYPOINT ["python3", "embedding_tei.py"]
 

comps/embeddings/llama_index/embedding_tei_gaudi.py renamed to comps/embeddings/llama_index/embedding_tei.py

@@ -10,7 +10,7 @@
 
 
 @register_microservice(
-    name="opea_service@embedding_tgi_gaudi",
+    name="opea_service@embedding_tei_llamaindex",
     service_type=ServiceType.EMBEDDING,
     endpoint="/v1/embeddings",
     host="0.0.0.0",
@@ -31,4 +31,4 @@ def embedding(input: TextDoc) -> EmbedDoc768:
     tei_embedding_endpoint = os.getenv("TEI_EMBEDDING_ENDPOINT", "http://localhost:8090")
     embeddings = TextEmbeddingsInference(model_name=tei_embedding_model_name, base_url=tei_embedding_endpoint)
     print("TEI Gaudi Embedding initialized.")
-    opea_microservices["opea_service@embedding_tgi_gaudi"].start()
+    opea_microservices["opea_service@embedding_tei_llamaindex"].start()