}

    /**
     * Returns whether relevant results were found.
     *
     * @return true if relevant results exist
     */
    public boolean isHasRelevantResults() {
        return hasRelevantResults;
    }

    /**
     * Creates a result with relevant documents found.
     *
     * @param relevantDocIds list of relevant document IDs
     * @param relevantIndexes list of relevant indexes (1-based) from search results

        return detectIntent(userMessage);
    }

    /**
     * Evaluates search results for relevance to the user's question.
     *
     * @param userMessage the original user message
     * @param query the search query used
     * @param searchResults the search results to evaluate
     * @return evaluation result with relevant document IDs
     */

* To explain *rejected solutions*, for now, and future development, in case they are proposed again.

ADRs can be written by any team.
Like code, they should be reviewed by any other relevant teams.
The goal is not to *own* a decision, but to *share* it with other teams, and improve the build tool together.

### Format

The format for ADR should follow this template:

```markdown
# ADR-000X - Title

	dir := filepath.Dir(file)
	dir = filepath.Dir(dir)

	s := filepath.Dir(dir)
	if filepath.Base(s) != "gorm.io" {
		s = dir
	}
	return filepath.ToSlash(s) + "/"
}

// CallerFrame retrieves the first relevant stack frame outside of GORM's internal implementation files.
// It skips:
//   - GORM's core source files (identified by gormSourceDir prefix)
//   - Exclude test files (*_test.go)
//   - go-gorm/gen's Generated files (*.gen.go)

{* ../../docs_src/handling_errors/tutorial001_py310.py hl[1] *}

### Raise an `HTTPException` in your code { #raise-an-httpexception-in-your-code }

`HTTPException` is a normal Python exception with additional data relevant for APIs.

Because it's a Python exception, you don't `return` it, you `raise` it.

    }

    /**
     * Creates a new Maven-like repository system session by initializing the session with values typical for
     * Maven-based resolution. In more detail, this method configures settings relevant for the processing of dependency
     * graphs, most other settings remain at their generic default value. Use the various setters to further configure

    }

    /**
     * Evaluates search results for relevance using the configured LLM client.
     *
     * @param userMessage the original user message
     * @param query the search query used
     * @param searchResults the search results to evaluate
     * @return evaluation result with relevant document IDs
     * @throws LlmException if LLM is not available
     */

## OpenAPI Extra { #openapi-extra }

When you declare a *path operation* in your application, **FastAPI** automatically generates the relevant metadata about that *path operation* to be included in the OpenAPI schema.

/// note | Technical details

                                System.currentTimeMillis() - phaseStartTime);
                    }

                    // Fallback: regenerate query if no relevant results
                    if (!evalResult.isHasRelevantResults()) {
                        logger.info("[RAG] No relevant results in evaluation, regenerating query. originalQuery={}", query);

  private static final Splitter DOT_SPLITTER = Splitter.on('.');

  /**
   * Value of {@link #publicSuffixIndex()} or {@link #registrySuffixIndex()} which indicates that no
   * relevant suffix was found.
   */
  private static final int NO_SUFFIX_FOUND = -1;

  /**
   * Value of {@link #publicSuffixIndexCache} or {@link #registrySuffixIndexCache} which indicates
   * that they were not initialized yet.