Skip to content

when using keyword search use proper queries with /q #47

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Sep 12, 2025
Merged

when using keyword search use proper queries with /q #47

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
56a4e28
when using keyword search use proper queries with \q
alexsku Sep 9, 2025
c3d8608
prompt simplifications
alexsku Sep 10, 2025
db060c1
removed unused import
alexsku Sep 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 16 additions & 9 deletions src/mcp_server_datahub/mcp_server.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -371,16 +371,21 @@ def enhanced_search(
- Will match: tables named "user_behavior", "client_metrics", "consumer_data" for "customer analytics"

KEYWORD SEARCH (search_strategy="keyword" or default):
- Traditional full-text search matching exact words and phrases
- Fast and precise when you know specific names or technical terms
- Best for: exact entity names, technical identifiers, known column names
- Examples: "user_transactions", "revenue_2024", "customer_id"
- Will match: exact text appearances of these terms
- Structured full-text search - **always start queries with "/q "**
- Supports full boolean logic: AND (default), OR, NOT, parentheses, field searches
Copy link
Contributor

@mayurinehate mayurinehate Sep 9, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This would be good addition for simple search as well, once we establish this works as expected in majority of cases.

Copy link
Contributor Author

@alexsku alexsku Sep 9, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

what do you think the process o releasing it for the simple search should be? should we try updating it for the slackbot and run evals?

Copy link
Contributor

@mayurinehate mayurinehate Sep 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes.

- Examples:
• "/q user_transactions" → exact terms (AND is default)
• "/q wizard OR pet" → entities containing either term
• "/q revenue_*" → wildcard matching (revenue_2023, revenue_2024, revenue_monthly, etc.)
• "/q \"user data table\"" → exact phrase matching
• "/q (sales OR revenue) AND quarterly" → complex boolean combinations
- Fast and precise for exact matching, technical terms, and complex queries
- Best for: entity names, identifiers, column names, or any search needing boolean logic

WHEN TO USE EACH:
- Use semantic when: user asks conceptual questions ("show me sales data", "find customer information")
- Use keyword when: user provides specific names ("find table user_events", "show dataset named revenue_jan_2024")
- Use keyword when: searching for technical terms, column names, or exact identifiers
- Use keyword when: user provides specific names ("/q user_events", "/q revenue_jan_2024")
- Use keyword when: searching for technical terms, boolean logic, or exact identifiers

Returns both a truncated list of results and facets/aggregations that can be used to iteratively refine the search filters.
To explore the data catalog and get aggregate statistics, use the wildcard '*' as the query and set `filters: null`. This provides
Expand Down Expand Up @@ -417,9 +422,11 @@ def enhanced_search(

SEARCH STRATEGY EXAMPLES:
- Semantic: "customer behavior data" → finds user_analytics, client_metrics, consumer_tracking
- Keyword: "customer_behavior" → finds tables with exact name "customer_behavior"
- Keyword: "/q customer_behavior" → finds tables with exact name "customer_behavior"
- Keyword: "/q customer OR user" → finds tables with either term
- Semantic: "financial performance metrics" → finds revenue_kpis, profit_analysis, financial_dashboards
- Keyword: "financial_performance_metrics" → finds exact table name matches
- Keyword: "/q financial_performance_metrics" → finds exact table name matches
- Keyword: "/q (financial OR revenue) AND metrics" → complex boolean logic
"""
return _search_implementation(query, filters, num_results, search_strategy)

Expand Down