embeddings: refactor EmbedderClient interface to reduce code duplication

[eliben]

Starting with the vertex embedder, but this is applicable to others too.

The common code fixes the combined vector issue, similarly to #357, for #356

This replaces a completely duplicated method in two places with a common function; the same function can be used for the embedders of other LLMs as well, if this approach is deemed good.

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]

Much better, thank you. LGTM

[eliben]

Thanks @tmc - I'd be happy to apply this to other embeddings backends, but it's not clear to me why there are two at all - why is there one instance of LLM and one of Chat with the same embeddings methods and implementations? E.g. https://github.com/tmc/langchaingo/blob/main/embeddings/ollama/ollamachat/ollama_chat.go#L31 and https://github.com/tmc/langchaingo/blob/main/embeddings/ollama/ollama.go#L32 -- could you clarify?