_Ref-LLM-Predictor:

LLMPredictor

我们的LLMPredictor是Langchain的`LLMChain`的一个包装器，可以轻松集成到LlamaIndex中。

Wrapper functions around an LLM chain.

我们的MockLLMPredictor用于令牌预测。有关更多信息，请参阅`成本分析How-To <../../how_to/analysis/cost_analysis.html>`_。

Mock chain wrapper.

class llama_index.token_counter.mock_chain_wrapper.MockLLMPredictor(max_tokens: int = 256, llm: Optional[BaseLLM] = None)

Mock LLM Predictor.

async apredict(prompt: Prompt, **prompt_args: Any) → Tuple[str, str]

Async predict the answer to a query.

参数

prompt (Prompt) -- Prompt to use for prediction.

返回

Tuple of the predicted answer and the formatted prompt.

返回类型

Tuple[str, str]

get_llm_metadata() → LLMMetadata

Get LLM metadata.

property last_token_usage: int

Get the last token usage.

property llm: BaseLanguageModel

Get LLM.

predict(prompt: Prompt, **prompt_args: Any) → Tuple[str, str]

Predict the answer to a query.

参数

prompt (Prompt) -- Prompt to use for prediction.

返回

Tuple of the predicted answer and the formatted prompt.

返回类型

Tuple[str, str]

stream(prompt: Prompt, **prompt_args: Any) → Tuple[Generator, str]

Stream the answer to a query.

NOTE: this is a beta feature. Will try to build or use better abstractions about response handling.

参数

prompt (Prompt) -- Prompt to use for prediction.

返回

The predicted answer.

返回类型

str

property total_tokens_used: int

Get the total tokens used so far.