Langroid

Update toml to latest DuckDuckGo (6.0.0) so we no longer get the rate limit error

Support OpenAI GPT-4o -- this is now the default LLM when no model is specified.

To explicitly specify the LLM, you can do, for example:


import langroid.language_models as lm
llm = lm.OpenAIGPT( lm.OpenAIGPTConfig(chat_model = lm.OpenAIChatModel.GPT4o))


And recall you can run most of the example scripts with a model specified via `-m gpt-4o`,
and pytests using `--m gpt-4o`

Gemini support via litellm. See docs https://langroid.github.io/langroid/tutorials/non-openai-llms/

Essentially, you need to:
- install `langroid` with the `litellm` extra, e.g. `pip install "langroid[litellm]"`
- set up your `GEMINI_API_KEY` in the `.env` file or shell env
- specify `chat_model="litellm/gemini/gemini-1.5-pro-latest"`

QdrantDB, QdrantDBConfig: support for sparse embeddings

Change python range to >= 3.10 < 3.12 to avoid colab errors (used to be >= 3.11)

Minor type sig change