Langroid

UnstructuredDocParser: fix partition_doc arg to allow bytes

DocChatAgent: allow ingest_doc_paths to take bytes not just doc paths

JSON parsing (relevant for parsing tools/function calls): improved repair of un-quoted keys or values via yaml.

Intended to handle cases where a weak LLM may produce a JSON-like string
containing, e.g. "rent": DO-NOT-KNOW, where it "forgot" to put quotes on the value,
or city: "New York" where it "forgot" to put quotes on the key.
It will even handle cases like 'address: do not know'.

Further improvements in batch/concurrent running of DocChatAgent.
See `test_doc_chat_batch` here https://github.com/langroid/langroid/blob/main/tests/main/test_doc_chat_agent.py

Now to run multiple instances of `DocChatAgent` concurrently, you can use either `run_batch_tasks` where you pass in a single agent,
or `run_batch_task_gen` where you pass in a task-generator.

* Concurrency: Improvements to allow concurrent runs of `DocChatAgent`, see the
[`test_doc_chat_agent.py`](https://github.com/langroid/langroid/blob/main/tests/main/test_doc_chat_agent.py) in particular the `test_doc_chat_batch()`;
* Batch running of tasks: New task run utility: [`run_batch_task_gen`](https://github.com/langroid/langroid/blob/main/langroid/agent/batch.py)
where a task generator can be specified, to generate one task per input.

LanceDB nearest neighbor search - use `prefilter=True` when using a filter