Jaankoppe-llama-index

New Features

- Redis support for index stores and docstores (6575)
- DuckDB + SQL query engine notebook (6628)
- add notebook showcasing deplot data loader (6638)

Bug Fixes / Nits

- More robust JSON parsing from LLM for `SelectionOutputParser` (6610)
- bring our loaders back in line with llama-hub (6630)
- Remove usage of SQLStructStoreIndex in notebooks (6585)
- MD reader: remove html tags and leave linebreaks alone (6618)
- bump min langchain version to latest version (6632)
- Fix metadata column name in postgres vector store (6622)
- Postgres metadata fixes (6626, 6634)
- fixed links to dataloaders in contribution.md (6636)
- fix: typo in docs in creating custom_llm huggingface example (6639)
- Updated SelectionOutputParser to handle JSON objects and arrays (6610)
- Fixed docstring argument typo (6652)

- refactor structured output + pydantic programs (6604)

Bug Fixes / Nits

- Fix serialization for OpenSearch vector stores (6612)
- patch docs relationships (6606)
- Bug fix for ignoring directories while parsing git repo (4196)
- updated Chroma notebook (6572)
- Backport old node name (6614)
- Add the ability to change chroma implementation (6601)

- Patch imports for Document obj for backwards compatibility (6597)

New Features

- New `TextNode`/`Document` object classes based on pydantic (6586)
- `TextNode`/`Document` objects support metadata customization (metadata templates, exclude metadata from LLM or embeddings) (6586)
- Nodes no longer require flat metadata dictionaries, unless the vector store you use requires it (6586)

Bug Fixes / Nits

- use `NLTK_DATA` env var to control NLTK download location (6579)
- [discord] save author as metadata in group_conversations.py (6592)
- bs4 -> beautifulsoup4 in requirements (6582)
- negate euclidean distance (6564)
- add df output parser notebook link to docs (6581)

Breaking/Deprecated API Changes

- `Node` has been renamed to `TextNode` and is imported from `llama_index.schema` (6586)
- `TextNode` and `Document` must be instansiated with kwargs: `Document(text=text)` (6586)
- `TextNode` (fka `Node`) has a `id_` or `node_id` property, rather than `doc_id` (6586)
- `TextNode` and `Document` have a metadata property, which replaces the extra_info property (6586)
- `TextNode` no longer has a `node_info` property (start/end indexes are accessed directly with `start/end_char_idx` attributes) (6586)

New Features

- Add typesense vector store (6561)
- add df output parser (6576)

Bug Fixes / Nits

- Track langchain dependency via bridge module. (6573)

New Features

- add object index (6548)
- add SQL Schema Node Mapping + SQLTableRetrieverQueryEngine + obj index fixes (6569)
- sql refactor (NLSQLTableQueryEngine) (6529)

Bug Fixes / Nits

- Update vector_stores.md (6562)
- Minor `BaseResponseBuilder` interface cleanup (6557)
- Refactor TreeSummarize (6550)