First, I use the method from @HenryJammes ,It's good for my prod env to use PVA ChatBot to answer Employee questions,But sometime someone input key words it not good, and will get not good answer from my bot.
Two weeks ago,I read Azure OpenAI on your data (preview)This way support semantic search.
Maybe, It's a better way for use PVA chatBot answer your Employee questions.
Here is my Step to use Azure OpenAI on your data (preview) in my PVA:
1. I follow Quickstart: Chat with Azure OpenAI models using your own data complete the setting and upload my data.
2. I Create an Topic named "Cognitive search"

3. I create Power automate flow in step 2's action

4.I trigger the flow and got output from Azure Cognitive search
{
"id": "12345678-1a2b-3c4e5f-a123-12345678abcd",
"model": "",
"created": 1684304924,
"object": "chat.completion",
"choices": [
{
"index": 0,
"messages": [
{
"role": "tool",
"content": "{\"citations\": [{\"content\": \"\\nCognitive Services are cloud-based artificial intelligence (AI) services...\", \"id\": null, \"title\": \"What is Cognitive Services\", \"filepath\": null, \"url\": null, \"metadata\": {\"chunking\": \"orignal document size=250. Scores=0.4314117431640625 and 1.72564697265625.Org Highlight count=4.\"}, \"chunk_id\": \"0\"}], \"intent\": \"[\\\"Learn about Azure Cognitive Services.\\\"]\"}",
"end_turn": false
},
{
"role": "assistant",
"content": " \nAzure Cognitive Services are cloud-based artificial intelligence (AI) services that help developers build cognitive intelligence into applications without having direct AI or data science skills or knowledge. [doc1]. Azure Machine Learning is a cloud service for accelerating and managing the machine learning project lifecycle. [doc1].",
"end_turn": true
}
]
}
]
}
not complete yet, and will update.