L2m2

Added

- [Mistral](https://mistral.ai/) provider support via La Plateforme.
- [Mistral Large 2](https://mistral.ai/news/mistral-large-2407/) model availibility from Mistral.
- Mistral 7B, Mixtral 8x7B, and Mixtral 8x22B model availibility from Mistral in addition to existing providers.

- _0.0.30 and 0.0.31 are skipped due to a packaging error and a model key typo._

> [!CAUTION]
> This release has breaking changes! Please read the changelog carefully.

Added

- `alt_memory` and `bypass_memory` have been added as parameters to `call` and `call_custom` in `LLMClient` and `AsyncLLMClient`. These parameters allow you to specify alternative memory streams to use for the call, or to bypass memory entirely.

Changed

- Previously, the `LLMClient` and `AsyncLLMClient` constructors took `memory_type`, `memory_window_size`, and `memory_loading_type` as arguments. Now, it just takes `memory` as an argument, while `window_size` and `loading_type` can be set on the memory object itself. These changes make the memory API far more consistent and easy to use, especially with the additions of `alt_memory` and `bypass_memory`.

Removed

- The `MemoryType` enum has been removed. **This is a breaking change!!!** Instances of `client = LLMClient(memory_type=MemoryType.CHAT)` should be replaced with `client = LLMClient(memory=ChatMemory())`, and so on.

Added

- Providers can now be activated by default via the following environment variables:
- `OPENAI_API_KEY` for OpenAI
- `ANTHROPIC_API_KEY` for Anthropic
- `CO_API_KEY` for Cohere
- `GOOGLE_API_KEY` for Google
- `GROQ_API_KEY` for Groq
- `REPLICATE_API_TOKEN` for Replicate
- `OCTOAI_TOKEN` for OctoAI

Added

- [OctoAI](https://octoai.cloud/) provider support.
- [Llama 3.1](https://ai.meta.com/blog/meta-llama-3-1/) availibility, in sizes 8B (via OctoAI), 70B (via OctoAI), and 405B (via both OctoAI and Replicate).
- [Mistral 7B](https://mistral.ai/news/announcing-mistral-7b/) and [Mixtral 8x22B](https://mistral.ai/news/mixtral-8x22b/) via OctoAI.
- `LLMOperationError` exception, raised when a feature or mode is not supported by a particular model.

Fixed

- Rate limit errors would sometimes give the model id as `None` in the error message. This has been fixed.

Added

- [GPT-4o-mini](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) availibility.

Added

- Custom exception `LLMRateLimitError`, raised when an LLM call returns a 429 status code.