Langroid

LanceDB-related bug fixes:
- Use limit=None in various queries to ensure we get full collections list and get all documents
- Fix add_documents() bug where ids were not being indexed correctly

Chainlit, LiteLLM version bumps

Make more dependencies optional:
* `chromadb` (has some strange sqlite requirements that mess with dockerization in some envs)
* `mkdocs` (only need this for doc generation of course)
* `huggingface-hub`
See `pyproject.toml` for how to install these as extra dependencies using, e.g. `pip install "langroid[chromadb,transformers]"`

DocChatAgent:
* set default embedding config based on whether sentence_transformer is available
* set default `cross_encoder_reranking_model` to "cross-encoder/ms-marco-MiniLM-L-6-v2" if sentence_transformer available, else ""

* Remove all dependencies on Haystack
* Make transformers an extra (eliminates torch dependency); use `pip install "langroid[transformers]"` to get it
* Make `unstructured` library optional + extra; use `pip install "langroid[unstructured]"`) to get it
* Update ChromaDB to latest 0.4.23
* Default DocChatAgent to OpenAI Embeddings (eliminates dependency on transformers in core-langroid).
- To use hugging-face embeddings, install langroid with `pip install "langroid[hf-embeddings]"`

* Task: fix SEND_TO handling
* json tool detection: handle weak LLM producing unquoted string values
* Misc minor fixes, example tweaks