Jaankoppe-llama-index

New Features

- Support function calling api for AzureOpenAI (7041)

Bug Fixes / Nits

- tune prompt to get rid of KeyError in SubQ engine (7039)
- Fix validation of Azure OpenAI keys (7042)

New Features

- Added `kwargs` to `ComposableGraph` for the underlying query engines (6990)
- Validate openai key on init (6940)
- Added async embeddings and async RetrieverQueryEngine (6587)
- Added async `aquery` and `async_add` to PGVectorStore (7031)
- Added `.source_nodes` attribute to chat engine and agent responses (7029)
- Added `OpenInferenceCallback` for storing generation data in OpenInference format (6998)

Bug Fixes / Nits

- Fix achat memory initialization for data agents (7000)
- Add `print_response_stream()` to agengt/chat engine response class (7018)

Bug Fixes / Nits

- Fix achat memory initialization for data agents (7000)
- Add `print_response_stream()` to agengt/chat engine response class (7018)

New Features

- Default to pydantic question generation when possible for sub-question query engine (6979)

Bug Fixes / Nits

- Fix returned order of messages in large chat memory (6979)

New Features

- Added a `SentenceTransformerRerank` node post-processor for fast local re-ranking (6934)
- Add numpy support for evaluating queries in pandas query engine (6935)
- Add metadata filtering support for Postgres Vector Storage integration (6968)
- Proper llama2 support for agents and query engines (6969)

Bug Fixes / Nits

- Added `model_name` to LLMMetadata (6911)
- Fallback to retriever service context in query engines (6911)
- Fixed `as_chat_engine()` ValueError with extra kwargs (6971

New Features

- Add support for Replicate LLM (vicuna & llama 2!)

Bug Fixes / Nits

- fix streaming for condense chat engine (6958)

New Features

- Add support for chroma v0.4.0 (6937)
- Log embedding vectors to callback manager (6962)

Bug Fixes / Nits

- add more robust embedding timeouts (6779)
- improved connection session management on postgres vector store (6843)