[Doc] Refine READMEs (#841)

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

Author: letonghan

ChatQnA/README.md

@@ -245,7 +245,9 @@ Refer to the [AI PC Guide](./docker_compose/intel/cpu/aipc/README.md) for instru
 
 Refer to the [Intel Technology enabling for Openshift readme](https://github.com/intel/intel-technology-enabling-for-openshift/blob/main/workloads/opea/chatqna/README.md) for instructions to deploy ChatQnA prototype on RHOCP with [Red Hat OpenShift AI (RHOAI)](https://www.redhat.com/en/technologies/cloud-computing/openshift/openshift-ai).
 
-## Consume ChatQnA Service
+## Consume ChatQnA Service with RAG
+
+### Check Service Status
 
 Before consuming ChatQnA Service, make sure the TGI/vLLM service is ready (which takes up to 2 minutes to start).
 
@@ -260,6 +262,23 @@ Consume ChatQnA service until you get the TGI response like below.
 2024-09-03T02:47:53.402023Z  INFO text_generation_router::server: router/src/server.rs:2311: Connected
 ```
 
+### Upload RAG Files (Optional)
+
+To chat with retrieved information, you need to upload a file using `Dataprep` service.
+
+Here is an example of `Nike 2023` pdf.
+
+```bash
+# download pdf file
+wget https://raw.githubusercontent.com/opea-project/GenAIComps/main/comps/retrievers/redis/data/nke-10k-2023.pdf
+# upload pdf file with dataprep
+curl -X POST "http://${host_ip}:6007/v1/dataprep" \
+    -H "Content-Type: multipart/form-data" \
+    -F "files=@./nke-10k-2023.pdf"
+```
+
+### Consume Chat Service
+
 Two ways of consuming ChatQnA Service:
 
 1. Use cURL command on terminal

DocSum/README.md

@@ -147,7 +147,7 @@ Two ways of consuming Document Summarization Service:
 
    ```bash
    http_proxy=""
-   curl http://${your_ip}:8008/generate \
+   curl http://${host_ip}:8008/generate \
      -X POST \
      -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \
      -H 'Content-Type: application/json'

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

@@ -105,7 +105,7 @@ docker compose up -d
 1. TGI Service
 
    ```bash
-   curl http://${your_ip}:8008/generate \
+   curl http://${host_ip}:8008/generate \
      -X POST \
      -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \
      -H 'Content-Type: application/json'
@@ -114,7 +114,7 @@ docker compose up -d
 2. LLM Microservice
 
    ```bash
-   curl http://${your_ip}:9000/v1/chat/docsum \
+   curl http://${host_ip}:9000/v1/chat/docsum \
      -X POST \
      -d '{"query":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}' \
      -H 'Content-Type: application/json'

DocSum/docker_compose/intel/hpu/gaudi/README.md

@@ -96,7 +96,7 @@ docker compose up -d
 1. TGI Service
 
    ```bash
-   curl http://${your_ip}:8008/generate \
+   curl http://${host_ip}:8008/generate \
      -X POST \
      -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":64, "do_sample": true}}' \
      -H 'Content-Type: application/json'
@@ -105,7 +105,7 @@ docker compose up -d
 2. LLM Microservice
 
    ```bash
-   curl http://${your_ip}:9000/v1/chat/docsum \
+   curl http://${host_ip}:9000/v1/chat/docsum \
      -X POST \
      -d '{"query":"Text Embeddings Inference (TEI) is a toolkit for deploying and serving open source text embeddings and sequence classification models. TEI enables high-performance extraction for the most popular models, including FlagEmbedding, Ember, GTE and E5."}' \
      -H 'Content-Type: application/json'