llms: add cohere support

[lowczarc]

This pull request introduces support for cohere's LLM text generation
It doesn't incorporate yet all the options from cohere's API, currently only the prompt is available.

I tried to keep the same structure as the other LLM implementations.

I also added the dependency github.com/cohere-ai/tokenizer. This was necessary to implement the GetNumTokens function without necessitating a request to cohere's API.

Mirroring the OpenAI implementation, the token must be specified via the COHERE_API_TOKEN environment variable, while the model is set with the COHERE_MODEL variable.

Python Implementation

PR Checklist

• Read the Contributing documentation.
• Read the Code of conduct documentation.
• Name your Pull Request title clearly, concisely, and prefixed with the name of the primarily affected package you changed according to Good commit messages (such as memory: add interfaces for X, Y or util: add whizzbang helpers).
• Check that there isn't already a PR that solves the problem the same way to avoid creating a duplicate.
• Provide a description in this PR that addresses what the PR is solving, or reference the issue that it solves (e.g. Fixes #123).
• Describes the source of new concepts.
• References existing implementations as appropriate.
• Contains test coverage for new functions.
• Passes all golangci-lint checks.

[tmc]

LGTM