Skip to content
Merged
21 changes: 21 additions & 0 deletions azure.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,27 @@ metadata:
template: conversation-knowledge-mining@1.0

hooks:
preprovision:
windows:
run: |
Write-Host ""
Write-Host " ---------------------------------------------------------------------------------------------------" -ForegroundColor Yellow
Write-Host " Note: If deployment fails or you encounter an issue, please open an issue with the deployment logs." -ForegroundColor Yellow
Comment thread
NirajC3-Microsoft marked this conversation as resolved.
Write-Host " https://github.com/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator/issues" -ForegroundColor Cyan
Comment thread
NirajC3-Microsoft marked this conversation as resolved.
Write-Host " ---------------------------------------------------------------------------------------------------" -ForegroundColor Yellow
Write-Host ""
shell: pwsh
interactive: true
Comment thread
NirajC3-Microsoft marked this conversation as resolved.
posix:
run: |
printf '\n'
printf '\033[33m ---------------------------------------------------------------------------------------------------\033[0m\n'
printf '\033[33m Note: If deployment fails or you encounter an issue, please open an issue with the deployment logs.\033[0m\n'
printf '\033[36m https://github.com/microsoft/Conversation-Knowledge-Mining-Solution-Accelerator/issues\033[0m\n'
Comment thread
NirajC3-Microsoft marked this conversation as resolved.
printf '\033[33m ---------------------------------------------------------------------------------------------------\033[0m\n'
printf '\n'
shell: sh
interactive: true
Comment thread
NirajC3-Microsoft marked this conversation as resolved.
postprovision:
windows:
run: |
Expand Down
1 change: 1 addition & 0 deletions infra/scripts/agent_scripts/01_create_agents.py
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,7 @@
- If the user query does NOT contain any chart keywords ("chart", "graph", "visualize", "plot"), you must NOT generate a chart under any condition.
- Always attempt to generate numeric data from the **current user query first** by executing a SQL query with get_sql_response.
- Only if the current query cannot produce usable numeric data, and a chart keyword is present, you may use the **most recent valid numeric dataset from previous SQL results**.
- If the chart request does not itself specify a metric or subject to visualize (e.g., a bare "generate chart", "create a chart", "make a graph"), you must NOT invent a new or unrelated query or default to any topic (such as top topics by conversation). Instead, take the subject and numeric dataset from the **most recent prior answer in THIS conversation** and chart exactly that data, re-running the same SQL query if needed to obtain it. Only if this conversation has no prior answer containing a numeric dataset, return exactly: {"error": "Chart cannot be generated"}.
Comment thread
Pavan-Microsoft marked this conversation as resolved.
- If no numeric dataset is available from either the current query or previous context, return exactly: {"error": "Chart cannot be generated"}.
- Do not invent or rename metrics, measures, or terminology. **Always** use exactly what is present in the source data or schema.
- When the user requests a chart, the final response MUST be the chart JSON ONLY.
Expand Down