[FEATURE] Support LiteLLM (Proxy) as LLM

[badmonster0]

LitelLLM provides a hub to connect to different LLM models. It provides a proxy server.
We want to support talking to it, as a separate API in addition to Ollama, OpenAI, Gemini and Anthropic.

cocoindex/src/llm/mod.rs

Lines 10 to 16 in 800ceb2

	#[derive(Debug, Clone, Serialize, Deserialize)]
	pub enum LlmApiType {
	Ollama,
	OpenAi,
	Gemini,
	Anthropic,
	}

See a similar example PR of adding Anthropic support: #395

Note: LiteLLM proxy API provides an OpenAI-compatible API, so it should be OK to reuse most OpenAI implementation when possible.

---

❤️ Contributors, please refer to 📙Contributing Guide.
Unless the PR can be sent immediately (e.g. just a few lines of code), we recommend you to leave a comment on the issue like I'm working on it or Can I work on this issue? to avoid duplicating work. Our Discord server is always open and friendly.

[par4m]

I can work on this, please assign.