Llama-index-g

New Features
- Added native support for `HuggingFaceEmbedding`, `InstructorEmbedding`, and `OptimumEmbedding` (7795)
- Added metadata filtering and hybrid search to MyScale vector store (7780)
- Allowing custom text field name for Milvus (7790)
- Add support for `vector_store_query_mode` to `VectorIndexAutoRetriever` (7797)

Bug Fixes / Nits
- Update `LanceDBVectorStore` to handle score and distance (7754)
- Pass LLM to `memory_cls` in `CondenseQuestionChatEngine` (7785)

New Features
- add pydantic metadata extractor (7778)
- Allow users to set the embedding dimensions in azure cognitive vector store (7734)
- Add semantic similarity evaluator (7770)

Bug Fixes / Nits
- 📝docs: Update Chatbot Tutorial and Notebook (7767)
- Fixed response synthesizers with empty nodes (7773)
- Fix `NotImplementedError` in auto vector retriever (7764)
- Multiple kwargs values in "KnowledgeGraphQueryEngine" bug-fix (7763)
- Allow setting azure cognitive search dimensionality (7734)
- Pass service context to index for dataset generator (7748)
- Fix output parsers for selector templates (7774)
- Update Chatbot_SEC.ipynb (7711)
- linter/typechecker-friendly improvements to cassandra test (7771)
- Expose debug option of `PgVectorStore` (7776)
- llms/openai: fix Azure OpenAI by considering `prompt_filter_results` field (7755)

New Features
- Add support for `gpt-3.5-turbo-instruct` (7729)
- Add support for `TimescaleVectorStore` (7727)
- Added `LongContextReorder` for lost-in-the-middle issues (7719)
- Add retrieval evals (7738)

Bug Fixes / Nits
- Added node post-processors to async context chat engine (7731)
- Added unique index name for postgres tsv column (7741)

Bug Fixes / Nits
- Fix langchain import error for embeddings (7714)

New Features
- Added metadata filtering to the base simple vector store (7564)
- add low-level router guide (7708)
- Add CustomQueryEngine class (7703)

Bug Fixes / Nits
- Fix context window metadata in lite-llm (7696)

New Features
- Add CorrectnessEvaluator (7661)
- Added support for `Ollama` LLMs (7635)
- Added `HWPReader` (7672)
- Simplified portkey LLM interface (7669)
- Added async operation support to `ElasticsearchStore` vector store (7613)
- Added support for `LiteLLM` (7600)
- Added batch evaluation runner (7692)

Bug Fixes / Nits
- Avoid `NotImplementedError` for async langchain embeddings (7668)
- Imrpoved reliability of LLM selectors (7678)
- Fixed `query_wrapper_prompt` and `system_prompt` for output parsers and completion models (7678)
- Fixed node attribute inheritance in citation query engine (7675)

Breaking Changes
- Refactor and update `BaseEvaluator` interface to be more consistent (7661)
- Use `evaluate` function for generic input
- Use `evaluate_response` function with `Response` objects from llama index query engine
- Update existing evaluators with more explicit naming
- `ResponseEvaluator` -> `FaithfulnessEvaluator`
- `QueryResponseEvaluator` -> `RelevancyEvaluator`
- old names are kept as class aliases for backwards compatibility