Perplexity uncomplete usage metadata parsing

### Checked other resources - [x] I added a very descriptive title to this issue. - [x] I used the GitHub search to find a similar question and didn't find it. - [x] I am sure that this is a bug in LangChain rather than my code. - [x] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package). - [x] I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS. ### Example Code ```python response.usage_metadata.get("num_search_queries", 0) ``` will always returns 0 ### Error Message and Stack Trace (if applicable) _No response_ ### Description In the perplexity chat model with find the code : ```python def _create_usage_metadata(token_usage: dict) -> UsageMetadata: input_tokens = token_usage.get("prompt_tokens", 0) output_tokens = token_usage.get("completion_tokens", 0) total_tokens = token_usage.get("total_tokens", input_tokens + output_tokens) return UsageMetadata( input_tokens=input_tokens, output_tokens=output_tokens, total_tokens=total_tokens, ) ``` But according to http://docs.perplexity.ai/api-reference/chat-completions-post the API now returns  So metadata will be missing ### System Info python3.10 ubuntu, langchain-perplexity 0.1.1