Fixes for MultimodalQnA with the Milvus vector db (#1859)

Signed-off-by: Dina Suehiro Jones <[email protected]>

Author: dmsuehir

MultimodalQnA/docker_compose/intel/cpu/xeon/README.md

@@ -241,7 +241,7 @@ docker compose -f compose.yaml up -d
 export MILVUS_HOST=${host_ip}
 export MILVUS_PORT=19530
 export MILVUS_RETRIEVER_PORT=7000
-export COLLECTION_NAME=mm_rag_milvus
+export COLLECTION_NAME=LangChainCollection
 cd GenAIExamples/MultimodalQnA/docker_compose/intel/cpu/xeon/
 docker compose -f compose_milvus.yaml up -d
 ```
@@ -385,6 +385,8 @@ curl --silent --write-out "HTTPSTATUS:%{http_code}" \
 
 Now, test the microservice with posting a custom caption along with an image and a PDF containing images and text. The image caption can be provided as a text (`.txt`) or as spoken audio (`.wav` or `.mp3`).
 
+> Note: Audio captions for images are currently only supported when using the Redis data prep backend.
+
 ```bash
 curl --silent --write-out "HTTPSTATUS:%{http_code}" \
     ${DATAPREP_INGEST_SERVICE_ENDPOINT} \

MultimodalQnA/docker_compose/intel/cpu/xeon/compose_milvus.yaml

@@ -226,6 +226,8 @@ services:
       - DATAPREP_INGEST_SERVICE_ENDPOINT=${DATAPREP_INGEST_SERVICE_ENDPOINT}
       - DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT=${DATAPREP_GEN_TRANSCRIPT_SERVICE_ENDPOINT}
       - DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT=${DATAPREP_GEN_CAPTION_SERVICE_ENDPOINT}
+      - DATAPREP_GET_FILE_ENDPOINT=${DATAPREP_GET_FILE_ENDPOINT}
+      - DATAPREP_DELETE_FILE_ENDPOINT=${DATAPREP_DELETE_FILE_ENDPOINT}
       - MEGA_SERVICE_PORT:=${MEGA_SERVICE_PORT}
       - UI_PORT=${UI_PORT}
       - DATAPREP_MMR_PORT=${DATAPREP_MMR_PORT}