Jaankoppe-llama-index

Other Changes
- Reverted 7223 changes to defaults (7235)

New Features
- Default to pydantic selectors when possible (7154, 7223)
- Remove the need for langchain wrappers on `embed_model` in the service context (7157)
- Metadata extractors take an `LLM` object now, in addition to `LLMPredictor` (7202)
- Added local mode + fallback to llama.cpp + llama2 (7200)
- Added local fallback for embeddings to `BAAI/bge-small-en` (7200)
- Added `SentenceWindowNodeParser` + `MetadataReplacementPostProcessor` (7211)

Breaking Changes
- Change default LLM to gpt-3.5-turbo from text-davinci-003 (7223)
- Change prompts for compact/refine/tree_summarize to work better with gpt-3.5-turbo (7150, 7179, 7223)
- Increase default LLM temperature to 0.1 (7180)

Other Changes
- docs: Improvements to Mendable Search (7220)
- Refactor openai agent (7077)

Bug Fixes / Nits
- Use `1 - cosine_distance` for pgvector/postgres vector db (7217)
- fix metadata formatting and extraction (7216)
- fix(readers): Fix non-ASCII JSON Reader bug (7086)
- Chore: change PgVectorStore variable name from `sim` to `distance` for clarity (7226)

New Features
- Add "one click observability" page to docs (7183)
- Added Xorbits inference for local deployments (7151)
- Added Zep vector store integration (7203)
- feat/zep vectorstore (7203)

Bug Fixes / Nits
- Update the default `EntityExtractor` model (7209)
- Make `ChatMemoryBuffer` pickleable (7205)
- Refactored `BaseOpenAIAgent` (7077)

New Features
- add ensemble retriever notebook (7190)
- DOCS: added local llama2 notebook (7146)

Bug Fixes / Nits
- Fix for `AttributeError: 'OpenAIAgent' object has no attribute 'callback_manager'` by calling super constructor within `BaseOpenAIAgent`
- Remove backticks from nebula queries (7192)

New Features
- Added an `EntityExtractor` for metadata extraction (7163)

New Features
- add router module docs (7171)
- add retriever router (7166)

New Features
- Added a `RouterRetriever` for routing queries to specific retrievers (7166)

Bug Fixes / Nits
- Fix for issue where having multiple concurrent streamed responses from `OpenAIAgent` would result in interleaving of tokens across each response stream. (7164)
- fix llms callbacks issue (args[0] error) (7165)