Add OpenRouterEmbeddings to langchain-openrouter

### Submission checklist - [x] This is a feature request, not a bug report or usage question. - [x] I added a clear and descriptive title that summarizes the feature request. - [x] I used the GitHub search to find a similar feature request and didn't find it. - [x] I checked the LangChain documentation and API reference to see if this feature already exists. - [x] This is not related to the langchain-community package. ### Package (Required) - [ ] langchain - [ ] langchain-openai - [ ] langchain-anthropic - [ ] langchain-classic - [ ] langchain-core - [ ] langchain-model-profiles - [ ] langchain-tests - [ ] langchain-text-splitters - [ ] langchain-chroma - [ ] langchain-deepseek - [ ] langchain-exa - [ ] langchain-fireworks - [ ] langchain-groq - [ ] langchain-huggingface - [ ] langchain-mistralai - [ ] langchain-nomic - [ ] langchain-ollama - [x] langchain-openrouter - [ ] langchain-perplexity - [ ] langchain-qdrant - [ ] langchain-xai - [ ] Other / not sure / general ### Feature Description Currently, developers using OpenRouter for embeddings are forced to route calls through the generic `OpenAIEmbeddings` class by overriding the `base_url`. While this works for OpenAI models, it frequently causes schema mismatch errors (e.g., `"No embedding data received"`) when interacting with non-OpenAI models on OpenRouter, such as `BAAI/bge-m3` or Gemini multimodal embeddings. With the recent addition of the dedicated `langchain-openrouter` partner package, there is a clear gap for a native `OpenRouterEmbeddings` class that mirrors the standard `Embeddings` interface and leverages the official OpenRouter Python SDK. ### Proposal Add `OpenRouterEmbeddings` to `libs/partners/openrouter`. The implementation should: - Support standard sync and async embedding methods (`embed_documents`, `embed_query`, `aembed_documents`, `aembed_query`). - Use the standard `httpx` client / OpenRouter API payload structure to natively handle non-OpenAI model outputs. I have already built this im…