Update ChatQnA Guadi microservice (#126)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

ChatQnA/microservice/gaudi/README.md

@@ -95,6 +95,8 @@ export INDEX_NAME="rag-redis"
 export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token}
 ```
 
+Note: Please replace with `your_ip` with you external IP address, do not use localhost.
+
 Note: Please replace with `host_ip` with you external IP address, do not use localhost.
 
 ### Start Microservice Docker Containers
@@ -125,10 +127,21 @@ curl http://${host_ip}:6000/v1/embeddings\
 
 3. Retriever Microservice
 
+To consume the retriever microservice, you need to generate a mock embedding vector of length 768 in Python script:
+
+```python
+import random
+
+embedding = [random.uniform(-1, 1) for _ in range(768)]
+print(embedding)
+```
+
+Then substitute your mock embedding vector for the `${your_embedding}` in the following cURL command:
+
 ```bash
 curl http://${host_ip}:7000/v1/retrieval\
   -X POST \
-  -d '{"text":"test", "embedding":[1,1,...1]}' \
+  -d '{"text":"test", "embedding":${your_embedding}}' \
   -H 'Content-Type: application/json'
 ```
 

ChatQnA/microservice/gaudi/chatqna.py

@@ -13,31 +13,39 @@
 # limitations under the License.
 
 
-from comps import RemoteMicroService, ServiceOrchestrator
+from comps import MicroService, ServiceOrchestrator
 
 
 class ChatQnAService:
     def __init__(self, port=8000):
-        self.service_builder = ServiceOrchestrator(port=port)
+        self.service_builder = ServiceOrchestrator(host="0.0.0.0", port=port, endpoint="/v1/chatqna")
 
     def add_remote_service(self):
-        embedding = RemoteMicroService(name="embedding", host="0.0.0.0", port=6000, expose_endpoint="/v1/embeddings")
-        retriever = RemoteMicroService(name="retriever", host="0.0.0.0", port=7000, expose_endpoint="/v1/retrieval")
-        rerank = RemoteMicroService(name="rerank", host="0.0.0.0", port=8000, expose_endpoint="/v1/reranking")
-        llm = RemoteMicroService(name="llm", host="0.0.0.0", port=9000, expose_endpoint="/v1/chat/completions")
+        embedding = MicroService(
+            name="embedding", host="0.0.0.0", port=6000, expose_endpoint="/v1/embeddings", use_remote_service=True
+        )
+        retriever = MicroService(
+            name="retriever", host="0.0.0.0", port=7000, expose_endpoint="/v1/retrieval", use_remote_service=True
+        )
+        rerank = MicroService(
+            name="rerank", host="0.0.0.0", port=8000, expose_endpoint="/v1/reranking", use_remote_service=True
+        )
+        llm = MicroService(
+            name="llm", host="0.0.0.0", port=9000, expose_endpoint="/v1/chat/completions", use_remote_service=True
+        )
         self.service_builder.add(embedding).add(retriever).add(rerank).add(llm)
         self.service_builder.flow_to(embedding, retriever)
         self.service_builder.flow_to(retriever, rerank)
         self.service_builder.flow_to(rerank, llm)
 
     def schedule(self):
-        self.service_builder.schedule(initial_inputs={"text": "What is the revenue of Nike?"})
+        self.service_builder.schedule(initial_inputs={"text": "What is the revenue of Nike in 2023?"})
         self.service_builder.get_all_final_outputs()
         result_dict = self.service_builder.result_dict
         print(result_dict)
 
 
 if __name__ == "__main__":
-    chatqna = ChatQnAService(port=9001)
+    chatqna = ChatQnAService(port=8888)
     chatqna.add_remote_service()
     chatqna.schedule()

ChatQnA/microservice/xeon/chatqna.py

@@ -13,18 +13,26 @@
 # limitations under the License.
 
 
-from comps import RemoteMicroService, ServiceOrchestrator
+from comps import MicroService, ServiceOrchestrator
 
 
-class MyServiceOrchestrator:
+class ChatQnAService:
     def __init__(self, port=8000):
-        self.service_builder = ServiceOrchestrator(port=port)
+        self.service_builder = ServiceOrchestrator(host="0.0.0.0", port=port, endpoint="/v1/chatqna")
 
     def add_remote_service(self):
-        embedding = RemoteMicroService(name="embedding", host="0.0.0.0", port=6000, expose_endpoint="/v1/embeddings")
-        retriever = RemoteMicroService(name="retriever", host="0.0.0.0", port=7000, expose_endpoint="/v1/retrieval")
-        rerank = RemoteMicroService(name="rerank", host="0.0.0.0", port=8000, expose_endpoint="/v1/reranking")
-        llm = RemoteMicroService(name="llm", host="0.0.0.0", port=9000, expose_endpoint="/v1/chat/completions")
+        embedding = MicroService(
+            name="embedding", host="0.0.0.0", port=6000, expose_endpoint="/v1/embeddings", use_remote_service=True
+        )
+        retriever = MicroService(
+            name="retriever", host="0.0.0.0", port=7000, expose_endpoint="/v1/retrieval", use_remote_service=True
+        )
+        rerank = MicroService(
+            name="rerank", host="0.0.0.0", port=8000, expose_endpoint="/v1/reranking", use_remote_service=True
+        )
+        llm = MicroService(
+            name="llm", host="0.0.0.0", port=9000, expose_endpoint="/v1/chat/completions", use_remote_service=True
+        )
         self.service_builder.add(embedding).add(retriever).add(rerank).add(llm)
         self.service_builder.flow_to(embedding, retriever)
         self.service_builder.flow_to(retriever, rerank)
@@ -38,6 +46,6 @@ def schedule(self):
 
 
 if __name__ == "__main__":
-    service_ochestrator = MyServiceOrchestrator(port=9001)
-    service_ochestrator.add_remote_service()
-    service_ochestrator.schedule()
+    chatqna = ChatQnAService(port=8888)
+    chatqna.add_remote_service()
+    chatqna.schedule()