- Legacy API will be deprecated in v0.4
- Complete removal planned for v1.0
- Added warning box to guide users to migrate

- Add new primary example using ragas.metrics.collections
- Show modern API with llm_factory and direct parameter passing
- Move legacy SingleTurnSample examples to Legacy section
- Add deprecation timeline (v0.4 deprecated, v1.0 removed)
- New example tested and verified to work correctly

Updated BleuScore section in traditional.md to:
- Show new collections-based API as primary example
- Add synchronous usage note
- Include configuration example for kwargs parameter
- Move legacy SingleTurnSample example to dedicated Legacy API section
- Add deprecation warning for legacy API

The new example was tested and produces the expected output.

…s API

- Add new primary example using collections-based API with llm_factory
- Include synchronous usage note for .score() method
- Move legacy SingleTurnSample example to Legacy Metrics API section
- Add deprecation timeline warning (v0.4 deprecated, v1.0 removed)
- Preserve conceptual explanation and "How It's Calculated" section
- Tested new example and verified it produces expected output

- Migrate primary example to use AnswerSimilarity from ragas.metrics.collections
- Use modern OpenAIEmbeddings instead of deprecated embedding_factory
- Add synchronous usage note for .score() method
- Move legacy SingleTurnSample example to "Legacy Metrics API" section
- Add deprecation timeline warning (v0.4 deprecation, v1.0 removal)
- Update terminology from "answer" to "response" for consistency
- Add step 4 to calculation explanation showing final score output
- Tested example successfully with no deprecation warnings

Updated answer_relevance.md to follow the new pattern:
- Added collections-based API example as primary example
- Improved structure with clearer title and description
- Added synchronous usage note
- Moved legacy SingleTurnSample example to "Legacy Metrics API" section
- Tested new example successfully

- Add examples for ContextPrecision and ContextUtilization using collections API
- Simplify documentation to show only user-facing metrics (removed wrapper details)
- Move legacy examples to deprecated section
- All examples tested and verified

- Add new collections-based API example at the top
- Add synchronous usage note
- Move legacy API examples to deprecated section
- Tested example and verified it works correctly

- Add new collections-based API example at the top
- Add synchronous usage note
- Preserve configuration section (rouge_type and mode)
- Move legacy API examples to Legacy Metrics API section with deprecation warning
- Tested example code and verified it produces expected output

- Updated example to use SemanticSimilarity from collections API
- Changed title from 'Answer Similarity' to 'Semantic Similarity' for consistency
- Added synchronous usage note
- Preserved 'How It's Calculated' section
- Moved legacy API examples to bottom with deprecation warning
- Tested example and verified it produces expected output

- Add new collections-based API example using SummaryScore from ragas.metrics.collections
- Include synchronous usage note with .score() method
- Add custom configuration example for length_penalty and coeff parameters
- Move legacy example to Legacy Metrics API section with deprecation warning
- Preserve all conceptual explanations and formulas
- Tested example code and verified it produces expected output

- Add primary example using collections-based API from ragas.metrics.collections
- Include examples for both 'relevant' and 'irrelevant' modes with outputs
- Add synchronous usage note
- Move legacy examples to Legacy Metrics API section with deprecation warning
- Preserve 'How It's Calculated' section and credits
- Tested example code and verified it works correctly

- Add collections-based API example with LLM and embeddings setup
- Move legacy evaluate() example to Legacy Metrics API section
- Add deprecation warning for legacy API
- Include synchronous usage note
- Tested example code and verified it works correctly

Note: Embeddings are required because default weights [0.75, 0.25]
include semantic similarity. See issue #2408 for making embeddings
optional when weights[1] == 0.

…Similarity) to collections API

- Updated NonLLMStringSimilarity with collections API example and configuration section
- Updated ExactMatch with collections API example
- Updated StringPresence with collections API example
- Added synchronous usage notes for all three metrics
- Moved legacy examples to Legacy Metrics API section with deprecation warnings
- All examples tested and verified to work correctly