Co-authored-by: Ismail Ashraq <59014721+ashraq1455@users.noreply.github.com>

Co-authored-by: Ismail Ashraq <59014721+ashraq1455@users.noreply.github.com>

Co-authored-by: Ismail Ashraq <59014721+ashraq1455@users.noreply.github.com>

Co-authored-by: Ismail Ashraq <59014721+ashraq1455@users.noreply.github.com>

Co-authored-by: Ismail Ashraq <59014721+ashraq1455@users.noreply.github.com>

Co-authored-by: Ismail Ashraq <59014721+ashraq1455@users.noreply.github.com>

Co-authored-by: Ismail Ashraq <59014721+ashraq1455@users.noreply.github.com>

installed poetry and ran make.  added mistralai to the pyproject.toml (first time using poetry, nice tool)

new encoder and a new LLMS. The encoder is a
simple wrapper around the MistralAI API, and the
LLMS is a simple wrapper around the encoder.
The encoder is tested with a simple unit test,
and the LLMS is tested with a simple unit test.

Changes to the code meant we needed to change some pytests.

New pytests added for Conversation splitter method.

Also fixed a bug in cumulative_sim.py where we weren't limiting curr_split_docs to only latter docs after a split.

Ensured that splitters embed in the __call__ method, rather than on initialization.

Also updated the Conversation class to uttilize splitters in assigning topic ids to Messages as the list of Messages grows.