import torch
from transformers import AutoModel, AutoTokenizer, AutoModelForCausalLM
from typing import Dict, List, Any

class EndpointHandler():
    def __init__(self, path=""):
        self.tokenizer = AutoTokenizer.from_pretrained(path, padding_side='left')
        self.model = AutoModelForCausalLM.from_pretrained(path, device_map="cpu", torch_dtype="auto").eval()

        self.token_false_id = self.tokenizer.convert_tokens_to_ids("no")
        self.token_true_id = self.tokenizer.convert_tokens_to_ids("yes")

        prefix = "<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be \"yes\" or \"no\".<|im_end|>\n<|im_start|>user\n"
        suffix = "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n"
        self.prefix_tokens = self.tokenizer.encode(prefix, add_special_tokens=False)
        self.suffix_tokens = self.tokenizer.encode(suffix, add_special_tokens=False)

    def format_instruction(self, instruction, query, doc):
        if instruction is None:
            instruction = 'Given a web search query, retrieve relevant passages that answer the query'
        output = "<Instruct>: {instruction}\n<Query>: {query}\n<Document>: {doc}".format(instruction=instruction,query=query, doc=doc)
        return output


    def process_inputs(self, pairs):
        max_length = 8192
        inputs = self.tokenizer(
            pairs, padding=False, truncation='longest_first',
            return_attention_mask=False, max_length=max_length - len(self.prefix_tokens) - len(self.suffix_tokens)
        )
        for i, ele in enumerate(inputs['input_ids']):
            inputs['input_ids'][i] = self.prefix_tokens + ele + self.suffix_tokens
        inputs = self.tokenizer.pad(inputs, padding=True, return_tensors="pt", max_length=max_length)
        for key in inputs:
            inputs[key] = inputs[key].to(self.model.device)
        return inputs


    def compute_logits(self, inputs, **kwargs):
        batch_scores = self.model(**inputs, cache_implementation="static").logits[:, -1, :]
        true_vector = batch_scores[:, self.token_true_id]
        false_vector = batch_scores[:, self.token_false_id]
        batch_scores = torch.stack([false_vector, true_vector], dim=1)
        batch_scores = torch.nn.functional.log_softmax(batch_scores, dim=1)
        scores = batch_scores[:, 1].exp().tolist()
        return scores

    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
                
        task = 'Given a web search query, retrieve relevant passages that answer the query'

        inputs = data.pop("inputs", data)

        if 'query' not in inputs or 'documents' not in inputs:
            raise ValueError("query and documents are required.")

        pairs = [self.format_instruction(task, inputs['query'], doc) for doc in inputs['documents']]

        # Tokenize the input texts
        inputs = self.process_inputs(pairs)
        scores = self.compute_logits(inputs)

        return dict(scores=scores)